{
  "name": "LLM Verifications AI model benchmark results",
  "publisher": "LLM Verifications",
  "editor": "LLM Verifications team",
  "data_as_of": "2026-10-27T17:31:31.658Z",
  "methodology": "https://www.llmverifications.com/methodology",
  "terms": "https://www.llmverifications.com/terms",
  "citation": "LLM Verifications team. LLM Verifications AI model benchmark results, data as of 2026-10-27. https://www.llmverifications.com/downloads",
  "suite": {
    "name": "Verification suite v2",
    "questions": 80,
    "sha256": "cd444ee142dc6b87e74967c9925ea9b7b171b90fe0e18b5a214c4587d964121a"
  },
  "datasets": [
    {
      "id": "supergpqa",
      "name": "SuperGPQA",
      "questions": 50,
      "license": "ODC-BY 1.0",
      "url": "https://huggingface.co/datasets/m-a-p/SuperGPQA",
      "paper": "https://arxiv.org/abs/2502.14739"
    },
    {
      "id": "mmlu-pro",
      "name": "MMLU-Pro",
      "questions": 30,
      "license": "MIT",
      "url": "https://huggingface.co/datasets/TIGER-Lab/MMLU-Pro",
      "paper": "https://arxiv.org/abs/2406.01574"
    }
  ],
  "speed_runs_per_model": 3,
  "models": [
    {
      "model_id": "thinkingmachines/inkling",
      "name": "Inkling",
      "creator": "Thinking Machines",
      "url": "https://www.llmverifications.com/models/inkling",
      "open_weights": true,
      "reasoning": true,
      "score_pct": 66.2,
      "correct": 53,
      "graded": 80,
      "failed_requests": 0,
      "cost_per_question_usd": 0.001238,
      "cost_per_correct_usd": 0.00187,
      "output_tokens_per_s": 117.9,
      "time_to_first_token_s": 0.553,
      "end_to_end_s": 4.98,
      "output_tokens_per_question": 228,
      "context_window": 524288,
      "list_input_usd_per_m": 1,
      "list_output_usd_per_m": 4.05,
      "quality_tested_at": "2026-10-27T17:31:31.658Z",
      "speed_tested_at": "2026-10-25T15:26:31.948Z",
      "supergpqa_correct": "27/50",
      "mmlu-pro_correct": "26/30",
      "subject_science_correct": "21/30",
      "subject_engineering_correct": "6/15",
      "subject_medicine_correct": "6/11",
      "subject_economics_correct": "8/9",
      "subject_law_correct": "4/6",
      "subject_humanities_social_science_correct": "8/9"
    },
    {
      "model_id": "stepfun/step-5-preview",
      "name": "Step 5 Preview",
      "creator": "StepFun",
      "url": "https://www.llmverifications.com/models/step-5-preview",
      "open_weights": true,
      "reasoning": true,
      "score_pct": 63.8,
      "correct": 51,
      "graded": 80,
      "failed_requests": 0,
      "cost_per_question_usd": 0.004704,
      "cost_per_correct_usd": 0.007373,
      "output_tokens_per_s": 92.7,
      "time_to_first_token_s": 0.629,
      "end_to_end_s": 8.16,
      "output_tokens_per_question": 1630,
      "context_window": 1048576,
      "list_input_usd_per_m": 1,
      "list_output_usd_per_m": 2.7,
      "quality_tested_at": "2026-10-27T17:31:31.658Z",
      "speed_tested_at": "2026-10-25T15:26:31.948Z",
      "supergpqa_correct": "26/50",
      "mmlu-pro_correct": "25/30",
      "subject_science_correct": "24/30",
      "subject_engineering_correct": "6/15",
      "subject_medicine_correct": "4/11",
      "subject_economics_correct": "7/9",
      "subject_law_correct": "2/6",
      "subject_humanities_social_science_correct": "8/9"
    },
    {
      "model_id": "mistralai/mistral-medium-3-5",
      "name": "Mistral Medium 3.5",
      "creator": "Mistral",
      "url": "https://www.llmverifications.com/models/mistral-medium-3-5",
      "open_weights": null,
      "reasoning": true,
      "score_pct": 28.8,
      "correct": 23,
      "graded": 80,
      "failed_requests": 0,
      "cost_per_question_usd": 0.024982,
      "cost_per_correct_usd": 0.086744,
      "output_tokens_per_s": 145,
      "time_to_first_token_s": 0.458,
      "end_to_end_s": 5.36,
      "output_tokens_per_question": 3268,
      "context_window": 262144,
      "list_input_usd_per_m": 1.5,
      "list_output_usd_per_m": 7.5,
      "quality_tested_at": "2026-10-27T17:31:31.658Z",
      "speed_tested_at": "2026-10-25T15:26:31.948Z",
      "supergpqa_correct": "5/50",
      "mmlu-pro_correct": "18/30",
      "subject_science_correct": "5/30",
      "subject_engineering_correct": "0/15",
      "subject_medicine_correct": "3/11",
      "subject_economics_correct": "6/9",
      "subject_law_correct": "2/6",
      "subject_humanities_social_science_correct": "7/9"
    },
    {
      "model_id": "qwen/qwen3.8-2.4t-a95b",
      "name": "Qwen3.8 2.4T A95B",
      "creator": "Qwen",
      "url": "https://www.llmverifications.com/models/qwen3-8-2-4t-a95b",
      "open_weights": true,
      "reasoning": true,
      "score_pct": 57.5,
      "correct": 46,
      "graded": 80,
      "failed_requests": 0,
      "cost_per_question_usd": 0.01518,
      "cost_per_correct_usd": 0.0264,
      "output_tokens_per_s": 44.3,
      "time_to_first_token_s": 3.143,
      "end_to_end_s": 14.79,
      "output_tokens_per_question": 2408,
      "context_window": 1048576,
      "list_input_usd_per_m": 2,
      "list_output_usd_per_m": 6,
      "quality_tested_at": "2026-10-27T17:31:31.658Z",
      "speed_tested_at": "2026-10-25T15:26:31.948Z",
      "supergpqa_correct": "23/50",
      "mmlu-pro_correct": "23/30",
      "subject_science_correct": "21/30",
      "subject_engineering_correct": "5/15",
      "subject_medicine_correct": "4/11",
      "subject_economics_correct": "7/9",
      "subject_law_correct": "2/6",
      "subject_humanities_social_science_correct": "7/9"
    },
    {
      "model_id": "moonshotai/kimi-k2.7-code",
      "name": "Kimi K2.7 Code",
      "creator": "MoonshotAI",
      "url": "https://www.llmverifications.com/models/kimi-k2-7-code",
      "open_weights": true,
      "reasoning": true,
      "score_pct": 65,
      "correct": 52,
      "graded": 80,
      "failed_requests": 0,
      "cost_per_question_usd": 0.006006,
      "cost_per_correct_usd": 0.00924,
      "output_tokens_per_s": 136.4,
      "time_to_first_token_s": 0.362,
      "end_to_end_s": 5.26,
      "output_tokens_per_question": 1781,
      "context_window": 262144,
      "list_input_usd_per_m": 0.56,
      "list_output_usd_per_m": 3.1,
      "quality_tested_at": "2026-10-27T17:31:31.658Z",
      "speed_tested_at": "2026-10-25T15:26:31.948Z",
      "supergpqa_correct": "25/50",
      "mmlu-pro_correct": "27/30",
      "subject_science_correct": "22/30",
      "subject_engineering_correct": "7/15",
      "subject_medicine_correct": "5/11",
      "subject_economics_correct": "7/9",
      "subject_law_correct": "3/6",
      "subject_humanities_social_science_correct": "8/9"
    },
    {
      "model_id": "cohere/command-a",
      "name": "Command A",
      "creator": "Cohere",
      "url": "https://www.llmverifications.com/models/command-a",
      "open_weights": true,
      "reasoning": false,
      "score_pct": 45,
      "correct": 36,
      "graded": 80,
      "failed_requests": 0,
      "cost_per_question_usd": 0.00697,
      "cost_per_correct_usd": 0.01549,
      "output_tokens_per_s": 7.2,
      "time_to_first_token_s": 1.846,
      "end_to_end_s": 53.35,
      "output_tokens_per_question": 616,
      "context_window": 256000,
      "list_input_usd_per_m": 2.5,
      "list_output_usd_per_m": 10,
      "quality_tested_at": "2026-10-27T17:31:31.658Z",
      "speed_tested_at": "2026-10-25T15:26:31.948Z",
      "supergpqa_correct": "12/50",
      "mmlu-pro_correct": "24/30",
      "subject_science_correct": "12/30",
      "subject_engineering_correct": "3/15",
      "subject_medicine_correct": "6/11",
      "subject_economics_correct": "6/9",
      "subject_law_correct": "3/6",
      "subject_humanities_social_science_correct": "6/9"
    },
    {
      "model_id": "rekaai/reka-flash-3",
      "name": "Reka Flash 3",
      "creator": "rekaai",
      "url": "https://www.llmverifications.com/models/reka-flash-3",
      "open_weights": true,
      "reasoning": true,
      "score_pct": 1.2,
      "correct": 1,
      "graded": 80,
      "failed_requests": 0,
      "cost_per_question_usd": 0.000803,
      "cost_per_correct_usd": 0.066915,
      "output_tokens_per_s": 101.4,
      "time_to_first_token_s": 0.476,
      "end_to_end_s": 7.38,
      "output_tokens_per_question": 3855,
      "context_window": 65536,
      "list_input_usd_per_m": 0.1,
      "list_output_usd_per_m": 0.2,
      "quality_tested_at": "2026-10-27T17:31:31.658Z",
      "speed_tested_at": "2026-10-25T15:26:31.948Z",
      "supergpqa_correct": "1/50",
      "mmlu-pro_correct": "0/30",
      "subject_science_correct": "0/30",
      "subject_engineering_correct": "0/15",
      "subject_medicine_correct": "1/11",
      "subject_economics_correct": "0/9",
      "subject_law_correct": "0/6",
      "subject_humanities_social_science_correct": "0/9"
    },
    {
      "model_id": "meta-llama/llama-4-scout",
      "name": "Llama 4 Scout",
      "creator": "Meta",
      "url": "https://www.llmverifications.com/models/llama-4-scout",
      "open_weights": true,
      "reasoning": false,
      "score_pct": 41.2,
      "correct": 33,
      "graded": 80,
      "failed_requests": 0,
      "cost_per_question_usd": 0.000369,
      "cost_per_correct_usd": 0.000896,
      "output_tokens_per_s": 15.3,
      "time_to_first_token_s": 1.162,
      "end_to_end_s": 25.62,
      "output_tokens_per_question": 723,
      "context_window": 1310720,
      "list_input_usd_per_m": 0.1,
      "list_output_usd_per_m": 0.3,
      "quality_tested_at": "2026-10-27T17:31:31.658Z",
      "speed_tested_at": "2026-10-25T15:26:31.948Z",
      "supergpqa_correct": "13/50",
      "mmlu-pro_correct": "20/30",
      "subject_science_correct": "13/30",
      "subject_engineering_correct": "2/15",
      "subject_medicine_correct": "6/11",
      "subject_economics_correct": "4/9",
      "subject_law_correct": "2/6",
      "subject_humanities_social_science_correct": "6/9"
    },
    {
      "model_id": "qwen/qwen3.7-plus",
      "name": "Qwen3.7 Plus",
      "creator": "Qwen",
      "url": "https://www.llmverifications.com/models/qwen3-7-plus",
      "open_weights": null,
      "reasoning": true,
      "score_pct": 60,
      "correct": 48,
      "graded": 80,
      "failed_requests": 0,
      "cost_per_question_usd": 0.003256,
      "cost_per_correct_usd": 0.005427,
      "output_tokens_per_s": 62.5,
      "time_to_first_token_s": 1.141,
      "end_to_end_s": 12.35,
      "output_tokens_per_question": 2462,
      "context_window": 1000000,
      "list_input_usd_per_m": 0.32,
      "list_output_usd_per_m": 1.28,
      "quality_tested_at": "2026-10-27T17:31:31.658Z",
      "speed_tested_at": "2026-10-25T15:26:31.948Z",
      "supergpqa_correct": "21/50",
      "mmlu-pro_correct": "27/30",
      "subject_science_correct": "19/30",
      "subject_engineering_correct": "4/15",
      "subject_medicine_correct": "6/11",
      "subject_economics_correct": "7/9",
      "subject_law_correct": "3/6",
      "subject_humanities_social_science_correct": "9/9"
    },
    {
      "model_id": "nvidia/nemotron-3.5-super-vl",
      "name": "Nemotron 3.5 Super VL",
      "creator": "NVIDIA",
      "url": "https://www.llmverifications.com/models/nemotron-3-5-super-vl",
      "open_weights": true,
      "reasoning": true,
      "score_pct": 40,
      "correct": 32,
      "graded": 80,
      "failed_requests": 0,
      "cost_per_question_usd": 0.001269,
      "cost_per_correct_usd": 0.003173,
      "output_tokens_per_s": 714.9,
      "time_to_first_token_s": 0.647,
      "end_to_end_s": 1.53,
      "output_tokens_per_question": 2771,
      "context_window": 1048576,
      "list_input_usd_per_m": 0.15,
      "list_output_usd_per_m": 0.5,
      "quality_tested_at": "2026-10-27T17:31:31.658Z",
      "speed_tested_at": "2026-10-25T15:26:31.948Z",
      "supergpqa_correct": "12/50",
      "mmlu-pro_correct": "20/30",
      "subject_science_correct": "13/30",
      "subject_engineering_correct": "4/15",
      "subject_medicine_correct": "2/11",
      "subject_economics_correct": "6/9",
      "subject_law_correct": "0/6",
      "subject_humanities_social_science_correct": "7/9"
    },
    {
      "model_id": "google/gemma-4-26b-a4b-it",
      "name": "Gemma 4 26B A4B",
      "creator": "Google",
      "url": "https://www.llmverifications.com/models/gemma-4-26b-a4b-it",
      "open_weights": true,
      "reasoning": true,
      "score_pct": 15,
      "correct": 12,
      "graded": 80,
      "failed_requests": 0,
      "cost_per_question_usd": 0.001073,
      "cost_per_correct_usd": 0.00715,
      "output_tokens_per_s": 171.9,
      "time_to_first_token_s": 0.682,
      "end_to_end_s": 4.84,
      "output_tokens_per_question": 3722,
      "context_window": 262144,
      "list_input_usd_per_m": 0.09,
      "list_output_usd_per_m": 0.3,
      "quality_tested_at": "2026-10-27T17:31:31.658Z",
      "speed_tested_at": "2026-10-25T15:26:31.948Z",
      "supergpqa_correct": "1/50",
      "mmlu-pro_correct": "11/30",
      "subject_science_correct": "4/30",
      "subject_engineering_correct": "0/15",
      "subject_medicine_correct": "1/11",
      "subject_economics_correct": "4/9",
      "subject_law_correct": "1/6",
      "subject_humanities_social_science_correct": "2/9"
    },
    {
      "model_id": "google/gemma-4-31b-it",
      "name": "Gemma 4 31B",
      "creator": "Google",
      "url": "https://www.llmverifications.com/models/gemma-4-31b-it",
      "open_weights": true,
      "reasoning": true,
      "score_pct": 30,
      "correct": 24,
      "graded": 80,
      "failed_requests": 0,
      "cost_per_question_usd": 0.00139,
      "cost_per_correct_usd": 0.004633,
      "output_tokens_per_s": 58.4,
      "time_to_first_token_s": 0.643,
      "end_to_end_s": 12.62,
      "output_tokens_per_question": 3307,
      "context_window": 262144,
      "list_input_usd_per_m": 0.2,
      "list_output_usd_per_m": 0.4,
      "quality_tested_at": "2026-10-27T17:31:31.658Z",
      "speed_tested_at": "2026-10-25T15:26:31.948Z",
      "supergpqa_correct": "7/50",
      "mmlu-pro_correct": "17/30",
      "subject_science_correct": "11/30",
      "subject_engineering_correct": "0/15",
      "subject_medicine_correct": "2/11",
      "subject_economics_correct": "5/9",
      "subject_law_correct": "1/6",
      "subject_humanities_social_science_correct": "5/9"
    },
    {
      "model_id": "inclusionai/ling-3.1-flash",
      "name": "Ling 3.1 Flash",
      "creator": "inclusionAI",
      "url": "https://www.llmverifications.com/models/ling-3-1-flash",
      "open_weights": null,
      "reasoning": true,
      "score_pct": 41.2,
      "correct": 33,
      "graded": 80,
      "failed_requests": 0,
      "cost_per_question_usd": 0.000613,
      "cost_per_correct_usd": 0.001489,
      "output_tokens_per_s": 7.1,
      "time_to_first_token_s": 1.064,
      "end_to_end_s": 81.35,
      "output_tokens_per_question": 2616,
      "context_window": 262144,
      "list_input_usd_per_m": 0.075,
      "list_output_usd_per_m": 0.225,
      "quality_tested_at": "2026-10-27T17:31:31.658Z",
      "speed_tested_at": "2026-10-25T15:26:31.948Z",
      "supergpqa_correct": "12/50",
      "mmlu-pro_correct": "21/30",
      "subject_science_correct": "16/30",
      "subject_engineering_correct": "1/15",
      "subject_medicine_correct": "2/11",
      "subject_economics_correct": "6/9",
      "subject_law_correct": "1/6",
      "subject_humanities_social_science_correct": "7/9"
    },
    {
      "model_id": "qwen/qwen3.5-397b-a17b",
      "name": "Qwen3.5 397B A17B",
      "creator": "Qwen",
      "url": "https://www.llmverifications.com/models/qwen3-5-397b-a17b",
      "open_weights": true,
      "reasoning": true,
      "score_pct": 32.5,
      "correct": 26,
      "graded": 80,
      "failed_requests": 0,
      "cost_per_question_usd": 0.013352,
      "cost_per_correct_usd": 0.041082,
      "output_tokens_per_s": 239.6,
      "time_to_first_token_s": 0.647,
      "end_to_end_s": 3.53,
      "output_tokens_per_question": 4010,
      "context_window": 262144,
      "list_input_usd_per_m": 0.5,
      "list_output_usd_per_m": 3.6,
      "quality_tested_at": "2026-10-27T17:31:31.658Z",
      "speed_tested_at": "2026-10-25T15:26:31.948Z",
      "supergpqa_correct": "5/50",
      "mmlu-pro_correct": "21/30",
      "subject_science_correct": "10/30",
      "subject_engineering_correct": "0/15",
      "subject_medicine_correct": "2/11",
      "subject_economics_correct": "5/9",
      "subject_law_correct": "1/6",
      "subject_humanities_social_science_correct": "8/9"
    },
    {
      "model_id": "nousresearch/hermes-4-405b",
      "name": "Hermes 4 405B",
      "creator": "Nous",
      "url": "https://www.llmverifications.com/models/hermes-4-405b",
      "open_weights": true,
      "reasoning": true,
      "score_pct": 26.2,
      "correct": 21,
      "graded": 80,
      "failed_requests": 0,
      "cost_per_question_usd": 0.01,
      "cost_per_correct_usd": 0.038167,
      "output_tokens_per_s": 40.8,
      "time_to_first_token_s": 0.35,
      "end_to_end_s": 17.52,
      "output_tokens_per_question": 3223,
      "context_window": 131072,
      "list_input_usd_per_m": 1,
      "list_output_usd_per_m": 3,
      "quality_tested_at": "2026-10-27T17:31:31.658Z",
      "speed_tested_at": "2026-10-25T15:26:31.948Z",
      "supergpqa_correct": "3/50",
      "mmlu-pro_correct": "18/30",
      "subject_science_correct": "5/30",
      "subject_engineering_correct": "0/15",
      "subject_medicine_correct": "3/11",
      "subject_economics_correct": "5/9",
      "subject_law_correct": "2/6",
      "subject_humanities_social_science_correct": "6/9"
    },
    {
      "model_id": "anthropic/claude-fable-5.1",
      "name": "Claude Fable 5.1",
      "creator": "Anthropic",
      "url": "https://www.llmverifications.com/models/claude-fable-5-1",
      "open_weights": null,
      "reasoning": true,
      "score_pct": 81.2,
      "correct": 65,
      "graded": 80,
      "failed_requests": 0,
      "cost_per_question_usd": 0.016054,
      "cost_per_correct_usd": 0.01977,
      "output_tokens_per_s": 70.4,
      "time_to_first_token_s": 2.095,
      "end_to_end_s": 11.04,
      "output_tokens_per_question": 238,
      "context_window": 1000000,
      "list_input_usd_per_m": 10,
      "list_output_usd_per_m": 50,
      "quality_tested_at": "2026-10-27T17:30:24.045Z",
      "speed_tested_at": "2026-10-25T15:26:31.948Z",
      "supergpqa_correct": "38/50",
      "mmlu-pro_correct": "27/30",
      "subject_science_correct": "25/30",
      "subject_engineering_correct": "13/15",
      "subject_medicine_correct": "7/11",
      "subject_economics_correct": "7/9",
      "subject_law_correct": "5/6",
      "subject_humanities_social_science_correct": "8/9"
    },
    {
      "model_id": "openai/gpt-6-astra",
      "name": "GPT-6 Astra",
      "creator": "OpenAI",
      "url": "https://www.llmverifications.com/models/gpt-6-astra",
      "open_weights": null,
      "reasoning": true,
      "score_pct": 76.2,
      "correct": 61,
      "graded": 80,
      "failed_requests": 0,
      "cost_per_question_usd": 0.013326,
      "cost_per_correct_usd": 0.017488,
      "output_tokens_per_s": 48.9,
      "time_to_first_token_s": 1.291,
      "end_to_end_s": 8.92,
      "output_tokens_per_question": 205,
      "context_window": 1050000,
      "list_input_usd_per_m": 10,
      "list_output_usd_per_m": 50,
      "quality_tested_at": "2026-10-27T17:30:24.045Z",
      "speed_tested_at": "2026-10-25T15:26:31.948Z",
      "supergpqa_correct": "35/50",
      "mmlu-pro_correct": "26/30",
      "subject_science_correct": "26/30",
      "subject_engineering_correct": "10/15",
      "subject_medicine_correct": "6/11",
      "subject_economics_correct": "8/9",
      "subject_law_correct": "3/6",
      "subject_humanities_social_science_correct": "8/9"
    },
    {
      "model_id": "meta/muse-wonder",
      "name": "Muse Wonder",
      "creator": "Meta",
      "url": "https://www.llmverifications.com/models/muse-wonder",
      "open_weights": null,
      "reasoning": true,
      "score_pct": 78.8,
      "correct": 63,
      "graded": 80,
      "failed_requests": 0,
      "cost_per_question_usd": 0.021439,
      "cost_per_correct_usd": 0.027206,
      "output_tokens_per_s": 174.9,
      "time_to_first_token_s": 16.063,
      "end_to_end_s": 20.8,
      "output_tokens_per_question": 1014,
      "context_window": 1048576,
      "list_input_usd_per_m": 4,
      "list_output_usd_per_m": 20,
      "quality_tested_at": "2026-10-27T17:30:24.045Z",
      "speed_tested_at": "2026-10-25T15:26:31.948Z",
      "supergpqa_correct": "35/50",
      "mmlu-pro_correct": "28/30",
      "subject_science_correct": "26/30",
      "subject_engineering_correct": "11/15",
      "subject_medicine_correct": "5/11",
      "subject_economics_correct": "8/9",
      "subject_law_correct": "4/6",
      "subject_humanities_social_science_correct": "9/9"
    },
    {
      "model_id": "x-ai/grok-4.7",
      "name": "Grok 4.7",
      "creator": "SpaceXAI",
      "url": "https://www.llmverifications.com/models/grok-4-7",
      "open_weights": null,
      "reasoning": true,
      "score_pct": 80,
      "correct": 64,
      "graded": 80,
      "failed_requests": 0,
      "cost_per_question_usd": 0.025053,
      "cost_per_correct_usd": 0.031316,
      "output_tokens_per_s": 77.1,
      "time_to_first_token_s": 1.881,
      "end_to_end_s": 8,
      "output_tokens_per_question": 3952,
      "context_window": 500000,
      "list_input_usd_per_m": 2,
      "list_output_usd_per_m": 6,
      "quality_tested_at": "2026-10-27T17:30:24.045Z",
      "speed_tested_at": "2026-10-25T15:04:38.754Z",
      "supergpqa_correct": "37/50",
      "mmlu-pro_correct": "27/30",
      "subject_science_correct": "27/30",
      "subject_engineering_correct": "11/15",
      "subject_medicine_correct": "6/11",
      "subject_economics_correct": "8/9",
      "subject_law_correct": "4/6",
      "subject_humanities_social_science_correct": "8/9"
    },
    {
      "model_id": "openai/o3",
      "name": "o3",
      "creator": "OpenAI",
      "url": "https://www.llmverifications.com/models/o3",
      "open_weights": null,
      "reasoning": true,
      "score_pct": 72.5,
      "correct": 58,
      "graded": 80,
      "failed_requests": 0,
      "cost_per_question_usd": 0.008812,
      "cost_per_correct_usd": 0.012155,
      "output_tokens_per_s": 163.1,
      "time_to_first_token_s": 1.232,
      "end_to_end_s": 3.92,
      "output_tokens_per_question": 1025,
      "context_window": 200000,
      "list_input_usd_per_m": 2,
      "list_output_usd_per_m": 8,
      "quality_tested_at": "2026-10-27T17:30:24.045Z",
      "speed_tested_at": "2026-10-25T15:26:31.948Z",
      "supergpqa_correct": "30/50",
      "mmlu-pro_correct": "28/30",
      "subject_science_correct": "23/30",
      "subject_engineering_correct": "8/15",
      "subject_medicine_correct": "7/11",
      "subject_economics_correct": "7/9",
      "subject_law_correct": "5/6",
      "subject_humanities_social_science_correct": "8/9"
    },
    {
      "model_id": "openai/gpt-5.6-terra",
      "name": "GPT-5.6 Terra",
      "creator": "OpenAI",
      "url": "https://www.llmverifications.com/models/gpt-5-6-terra",
      "open_weights": null,
      "reasoning": true,
      "score_pct": 75,
      "correct": 60,
      "graded": 80,
      "failed_requests": 0,
      "cost_per_question_usd": 0.006278,
      "cost_per_correct_usd": 0.008371,
      "output_tokens_per_s": 101,
      "time_to_first_token_s": 1.149,
      "end_to_end_s": 5.29,
      "output_tokens_per_question": 472,
      "context_window": 1050000,
      "list_input_usd_per_m": 2,
      "list_output_usd_per_m": 12,
      "quality_tested_at": "2026-10-27T17:30:24.045Z",
      "speed_tested_at": "2026-10-25T15:26:31.948Z",
      "supergpqa_correct": "33/50",
      "mmlu-pro_correct": "27/30",
      "subject_science_correct": "26/30",
      "subject_engineering_correct": "11/15",
      "subject_medicine_correct": "4/11",
      "subject_economics_correct": "7/9",
      "subject_law_correct": "4/6",
      "subject_humanities_social_science_correct": "8/9"
    },
    {
      "model_id": "openai/gpt-5.3-codex",
      "name": "GPT-5.3-Codex",
      "creator": "OpenAI",
      "url": "https://www.llmverifications.com/models/gpt-5-3-codex",
      "open_weights": null,
      "reasoning": true,
      "score_pct": 82.5,
      "correct": 66,
      "graded": 80,
      "failed_requests": 0,
      "cost_per_question_usd": 0.010318,
      "cost_per_correct_usd": 0.012506,
      "output_tokens_per_s": 95.1,
      "time_to_first_token_s": 1.357,
      "end_to_end_s": 5.25,
      "output_tokens_per_question": 699,
      "context_window": 400000,
      "list_input_usd_per_m": 1.75,
      "list_output_usd_per_m": 14,
      "quality_tested_at": "2026-10-27T17:30:24.045Z",
      "speed_tested_at": "2026-10-25T15:26:31.948Z",
      "supergpqa_correct": "39/50",
      "mmlu-pro_correct": "27/30",
      "subject_science_correct": "28/30",
      "subject_engineering_correct": "11/15",
      "subject_medicine_correct": "7/11",
      "subject_economics_correct": "8/9",
      "subject_law_correct": "4/6",
      "subject_humanities_social_science_correct": "8/9"
    },
    {
      "model_id": "openai/gpt-6.1-terra",
      "name": "GPT-6.1 Terra",
      "creator": "OpenAI",
      "url": "https://www.llmverifications.com/models/gpt-6-1-terra",
      "open_weights": null,
      "reasoning": true,
      "score_pct": 73.8,
      "correct": 59,
      "graded": 80,
      "failed_requests": 0,
      "cost_per_question_usd": 0.001278,
      "cost_per_correct_usd": 0.001732,
      "output_tokens_per_s": 122.3,
      "time_to_first_token_s": 2.403,
      "end_to_end_s": 5.83,
      "output_tokens_per_question": 195,
      "context_window": 1050000,
      "list_input_usd_per_m": 1,
      "list_output_usd_per_m": 5,
      "quality_tested_at": "2026-10-27T10:07:30.431Z",
      "speed_tested_at": "2026-10-27T10:07:30.431Z",
      "supergpqa_correct": "33/50",
      "mmlu-pro_correct": "26/30",
      "subject_science_correct": "26/30",
      "subject_engineering_correct": "9/15",
      "subject_medicine_correct": "6/11",
      "subject_economics_correct": "7/9",
      "subject_law_correct": "3/6",
      "subject_humanities_social_science_correct": "8/9"
    },
    {
      "model_id": "openai/gpt-6.1-terra-pro",
      "name": "GPT-6.1 Terra Pro",
      "creator": "OpenAI",
      "url": "https://www.llmverifications.com/models/gpt-6-1-terra-pro",
      "open_weights": null,
      "reasoning": true,
      "score_pct": 76.2,
      "correct": 61,
      "graded": 80,
      "failed_requests": 0,
      "cost_per_question_usd": 0.004962,
      "cost_per_correct_usd": 0.006512,
      "output_tokens_per_s": null,
      "time_to_first_token_s": 8.535,
      "end_to_end_s": 9.02,
      "output_tokens_per_question": 453,
      "context_window": 1050000,
      "list_input_usd_per_m": 1,
      "list_output_usd_per_m": 5,
      "quality_tested_at": "2026-10-27T10:07:30.431Z",
      "speed_tested_at": "2026-10-27T10:07:30.431Z",
      "supergpqa_correct": "35/50",
      "mmlu-pro_correct": "26/30",
      "subject_science_correct": "26/30",
      "subject_engineering_correct": "10/15",
      "subject_medicine_correct": "6/11",
      "subject_economics_correct": "8/9",
      "subject_law_correct": "3/6",
      "subject_humanities_social_science_correct": "8/9"
    },
    {
      "model_id": "openai/gpt-oss-20b",
      "name": "gpt-oss-20b",
      "creator": "OpenAI",
      "url": "https://www.llmverifications.com/models/gpt-oss-20b",
      "open_weights": true,
      "reasoning": true,
      "score_pct": 51.2,
      "correct": 41,
      "graded": 80,
      "failed_requests": 0,
      "cost_per_question_usd": 0.000066,
      "cost_per_correct_usd": 0.000128,
      "output_tokens_per_s": 102.8,
      "time_to_first_token_s": 0.69,
      "end_to_end_s": 4.03,
      "output_tokens_per_question": 472,
      "context_window": 131072,
      "list_input_usd_per_m": 0.018,
      "list_output_usd_per_m": 0.09,
      "quality_tested_at": "2026-10-26T05:22:44.688Z",
      "speed_tested_at": "2026-10-25T15:26:31.948Z",
      "supergpqa_correct": "18/50",
      "mmlu-pro_correct": "23/30",
      "subject_science_correct": "18/30",
      "subject_engineering_correct": "4/15",
      "subject_medicine_correct": "4/11",
      "subject_economics_correct": "6/9",
      "subject_law_correct": "2/6",
      "subject_humanities_social_science_correct": "7/9"
    },
    {
      "model_id": "ibm-granite/granite-4.0-h-micro",
      "name": "Granite 4.0 Micro",
      "creator": "IBM",
      "url": "https://www.llmverifications.com/models/granite-4-0-h-micro",
      "open_weights": true,
      "reasoning": false,
      "score_pct": 25,
      "correct": 20,
      "graded": 80,
      "failed_requests": 0,
      "cost_per_question_usd": 0.000051,
      "cost_per_correct_usd": 0.000203,
      "output_tokens_per_s": 38.2,
      "time_to_first_token_s": 0.697,
      "end_to_end_s": 8.89,
      "output_tokens_per_question": 403,
      "context_window": 131000,
      "list_input_usd_per_m": 0.017,
      "list_output_usd_per_m": 0.112,
      "quality_tested_at": "2026-10-26T05:22:44.688Z",
      "speed_tested_at": "2026-10-25T15:26:31.948Z",
      "supergpqa_correct": "8/50",
      "mmlu-pro_correct": "12/30",
      "subject_science_correct": "7/30",
      "subject_engineering_correct": "1/15",
      "subject_medicine_correct": "4/11",
      "subject_economics_correct": "2/9",
      "subject_law_correct": "1/6",
      "subject_humanities_social_science_correct": "5/9"
    },
    {
      "model_id": "mistralai/ministral-3b-2512",
      "name": "Ministral 3 3B 2512",
      "creator": "Mistral",
      "url": "https://www.llmverifications.com/models/ministral-3b-2512",
      "open_weights": true,
      "reasoning": false,
      "score_pct": 26.2,
      "correct": 21,
      "graded": 80,
      "failed_requests": 0,
      "cost_per_question_usd": 0.000195,
      "cost_per_correct_usd": 0.000743,
      "output_tokens_per_s": 251.9,
      "time_to_first_token_s": 0.305,
      "end_to_end_s": 1.61,
      "output_tokens_per_question": 1652,
      "context_window": 131072,
      "list_input_usd_per_m": 0.1,
      "list_output_usd_per_m": 0.1,
      "quality_tested_at": "2026-10-26T05:22:44.688Z",
      "speed_tested_at": "2026-10-25T15:26:31.948Z",
      "supergpqa_correct": "7/50",
      "mmlu-pro_correct": "14/30",
      "subject_science_correct": "5/30",
      "subject_engineering_correct": "2/15",
      "subject_medicine_correct": "4/11",
      "subject_economics_correct": "4/9",
      "subject_law_correct": "1/6",
      "subject_humanities_social_science_correct": "5/9"
    },
    {
      "model_id": "amazon/nova-micro-v1",
      "name": "Nova Micro 1.0",
      "creator": "Amazon",
      "url": "https://www.llmverifications.com/models/nova-micro-v1",
      "open_weights": null,
      "reasoning": false,
      "score_pct": 22.5,
      "correct": 18,
      "graded": 80,
      "failed_requests": 0,
      "cost_per_question_usd": 0.000087,
      "cost_per_correct_usd": 0.000387,
      "output_tokens_per_s": 179.9,
      "time_to_first_token_s": 0.467,
      "end_to_end_s": 2.11,
      "output_tokens_per_question": 545,
      "context_window": 128000,
      "list_input_usd_per_m": 0.035,
      "list_output_usd_per_m": 0.14,
      "quality_tested_at": "2026-10-26T05:22:44.688Z",
      "speed_tested_at": "2026-10-25T15:26:31.948Z",
      "supergpqa_correct": "3/50",
      "mmlu-pro_correct": "15/30",
      "subject_science_correct": "3/30",
      "subject_engineering_correct": "1/15",
      "subject_medicine_correct": "3/11",
      "subject_economics_correct": "6/9",
      "subject_law_correct": "1/6",
      "subject_humanities_social_science_correct": "4/9"
    },
    {
      "model_id": "inception/mercury-2.5",
      "name": "Mercury 2.5",
      "creator": "Inception",
      "url": "https://www.llmverifications.com/models/mercury-2-5",
      "open_weights": null,
      "reasoning": true,
      "score_pct": 58.2,
      "correct": 46,
      "graded": 79,
      "failed_requests": 1,
      "cost_per_question_usd": 0.000113,
      "cost_per_correct_usd": 0.000195,
      "output_tokens_per_s": 157.3,
      "time_to_first_token_s": 2.252,
      "end_to_end_s": 6.5,
      "output_tokens_per_question": 673,
      "context_window": 260000,
      "list_input_usd_per_m": 0.04,
      "list_output_usd_per_m": 0.15,
      "quality_tested_at": "2026-10-26T05:22:44.688Z",
      "speed_tested_at": "2026-10-25T15:26:31.948Z",
      "supergpqa_correct": "21/50",
      "mmlu-pro_correct": "25/29",
      "subject_science_correct": "19/30",
      "subject_engineering_correct": "6/15",
      "subject_medicine_correct": "4/11",
      "subject_economics_correct": "8/9",
      "subject_law_correct": "3/6",
      "subject_humanities_social_science_correct": "6/8"
    },
    {
      "model_id": "microsoft/phi-4",
      "name": "Phi 4",
      "creator": "Microsoft",
      "url": "https://www.llmverifications.com/models/phi-4",
      "open_weights": true,
      "reasoning": false,
      "score_pct": 41.2,
      "correct": 33,
      "graded": 80,
      "failed_requests": 0,
      "cost_per_question_usd": 0.000119,
      "cost_per_correct_usd": 0.00029,
      "output_tokens_per_s": 102.9,
      "time_to_first_token_s": 0.466,
      "end_to_end_s": 4.88,
      "output_tokens_per_question": 699,
      "context_window": 16384,
      "list_input_usd_per_m": 0.07,
      "list_output_usd_per_m": 0.14,
      "quality_tested_at": "2026-10-26T05:22:44.688Z",
      "speed_tested_at": "2026-10-25T15:26:31.948Z",
      "supergpqa_correct": "12/50",
      "mmlu-pro_correct": "21/30",
      "subject_science_correct": "12/30",
      "subject_engineering_correct": "6/15",
      "subject_medicine_correct": "4/11",
      "subject_economics_correct": "5/9",
      "subject_law_correct": "2/6",
      "subject_humanities_social_science_correct": "4/9"
    },
    {
      "model_id": "upstage/solar-mini4",
      "name": "Solar Mini 4",
      "creator": "Upstage",
      "url": "https://www.llmverifications.com/models/solar-mini4",
      "open_weights": null,
      "reasoning": true,
      "score_pct": 41.2,
      "correct": 33,
      "graded": 80,
      "failed_requests": 0,
      "cost_per_question_usd": 0.000527,
      "cost_per_correct_usd": 0.00128,
      "output_tokens_per_s": 107,
      "time_to_first_token_s": 0.693,
      "end_to_end_s": 7.43,
      "output_tokens_per_question": 2552,
      "context_window": 524288,
      "list_input_usd_per_m": 0.05,
      "list_output_usd_per_m": 0.2,
      "quality_tested_at": "2026-10-26T05:22:44.688Z",
      "speed_tested_at": "2026-10-25T15:26:31.948Z",
      "supergpqa_correct": "13/50",
      "mmlu-pro_correct": "20/30",
      "subject_science_correct": "16/30",
      "subject_engineering_correct": "2/15",
      "subject_medicine_correct": "2/11",
      "subject_economics_correct": "7/9",
      "subject_law_correct": "0/6",
      "subject_humanities_social_science_correct": "6/9"
    },
    {
      "model_id": "mistralai/ministral-8b-2512",
      "name": "Ministral 3 8B 2512",
      "creator": "Mistral",
      "url": "https://www.llmverifications.com/models/ministral-8b-2512",
      "open_weights": true,
      "reasoning": false,
      "score_pct": 42.5,
      "correct": 34,
      "graded": 80,
      "failed_requests": 0,
      "cost_per_question_usd": 0.000269,
      "cost_per_correct_usd": 0.000634,
      "output_tokens_per_s": 123.8,
      "time_to_first_token_s": 0.324,
      "end_to_end_s": 3.5,
      "output_tokens_per_question": 1496,
      "context_window": 262144,
      "list_input_usd_per_m": 0.15,
      "list_output_usd_per_m": 0.15,
      "quality_tested_at": "2026-10-26T05:22:44.688Z",
      "speed_tested_at": "2026-10-25T15:26:31.948Z",
      "supergpqa_correct": "10/50",
      "mmlu-pro_correct": "24/30",
      "subject_science_correct": "10/30",
      "subject_engineering_correct": "4/15",
      "subject_medicine_correct": "5/11",
      "subject_economics_correct": "7/9",
      "subject_law_correct": "1/6",
      "subject_humanities_social_science_correct": "7/9"
    },
    {
      "model_id": "nvidia/nemotron-3.5-lightning",
      "name": "Nemotron 3.5 Lightning",
      "creator": "NVIDIA",
      "url": "https://www.llmverifications.com/models/nemotron-3-5-lightning",
      "open_weights": true,
      "reasoning": true,
      "score_pct": 43.8,
      "correct": 35,
      "graded": 80,
      "failed_requests": 0,
      "cost_per_question_usd": 0.000489,
      "cost_per_correct_usd": 0.001117,
      "output_tokens_per_s": 116.3,
      "time_to_first_token_s": 0.495,
      "end_to_end_s": 6.52,
      "output_tokens_per_question": 2846,
      "context_window": 262144,
      "list_input_usd_per_m": 0.07,
      "list_output_usd_per_m": 0.2,
      "quality_tested_at": "2026-10-26T05:22:44.688Z",
      "speed_tested_at": "2026-10-25T15:26:31.948Z",
      "supergpqa_correct": "16/50",
      "mmlu-pro_correct": "19/30",
      "subject_science_correct": "14/30",
      "subject_engineering_correct": "4/15",
      "subject_medicine_correct": "4/11",
      "subject_economics_correct": "6/9",
      "subject_law_correct": "1/6",
      "subject_humanities_social_science_correct": "6/9"
    },
    {
      "model_id": "ibm-granite/granite-4.2-8b",
      "name": "Granite 4.2 8B",
      "creator": "IBM",
      "url": "https://www.llmverifications.com/models/granite-4-2-8b",
      "open_weights": true,
      "reasoning": true,
      "score_pct": 36.2,
      "correct": 29,
      "graded": 80,
      "failed_requests": 0,
      "cost_per_question_usd": 0.000077,
      "cost_per_correct_usd": 0.000213,
      "output_tokens_per_s": 59.6,
      "time_to_first_token_s": 0.632,
      "end_to_end_s": 7.34,
      "output_tokens_per_question": 227,
      "context_window": 131072,
      "list_input_usd_per_m": 0.06,
      "list_output_usd_per_m": 0.25,
      "quality_tested_at": "2026-10-26T05:22:44.688Z",
      "speed_tested_at": "2026-10-25T15:26:31.948Z",
      "supergpqa_correct": "11/50",
      "mmlu-pro_correct": "18/30",
      "subject_science_correct": "13/30",
      "subject_engineering_correct": "4/15",
      "subject_medicine_correct": "1/11",
      "subject_economics_correct": "5/9",
      "subject_law_correct": "2/6",
      "subject_humanities_social_science_correct": "4/9"
    },
    {
      "model_id": "mistralai/ministral-14b-2512",
      "name": "Ministral 3 14B 2512",
      "creator": "Mistral",
      "url": "https://www.llmverifications.com/models/ministral-14b-2512",
      "open_weights": true,
      "reasoning": false,
      "score_pct": 33.8,
      "correct": 27,
      "graded": 80,
      "failed_requests": 0,
      "cost_per_question_usd": 0.000311,
      "cost_per_correct_usd": 0.000921,
      "output_tokens_per_s": 32.2,
      "time_to_first_token_s": 0.648,
      "end_to_end_s": 12.74,
      "output_tokens_per_question": 1255,
      "context_window": 262144,
      "list_input_usd_per_m": 0.2,
      "list_output_usd_per_m": 0.2,
      "quality_tested_at": "2026-10-26T05:22:44.688Z",
      "speed_tested_at": "2026-10-25T15:26:31.948Z",
      "supergpqa_correct": "8/50",
      "mmlu-pro_correct": "19/30",
      "subject_science_correct": "8/30",
      "subject_engineering_correct": "2/15",
      "subject_medicine_correct": "6/11",
      "subject_economics_correct": "4/9",
      "subject_law_correct": "2/6",
      "subject_humanities_social_science_correct": "5/9"
    },
    {
      "model_id": "xiaomi/mimo-v2.6-flash",
      "name": "MiMo-V2.6-Flash",
      "creator": "Xiaomi",
      "url": "https://www.llmverifications.com/models/mimo-v2-6-flash",
      "open_weights": true,
      "reasoning": true,
      "score_pct": 62.5,
      "correct": 50,
      "graded": 80,
      "failed_requests": 0,
      "cost_per_question_usd": 0.00056,
      "cost_per_correct_usd": 0.000897,
      "output_tokens_per_s": 77.2,
      "time_to_first_token_s": 0.414,
      "end_to_end_s": 5.38,
      "output_tokens_per_question": 1850,
      "context_window": 1050000,
      "list_input_usd_per_m": 0.14,
      "list_output_usd_per_m": 0.28,
      "quality_tested_at": "2026-10-26T05:22:44.688Z",
      "speed_tested_at": "2026-10-25T15:26:31.948Z",
      "supergpqa_correct": "27/50",
      "mmlu-pro_correct": "23/30",
      "subject_science_correct": "20/30",
      "subject_engineering_correct": "7/15",
      "subject_medicine_correct": "6/11",
      "subject_economics_correct": "7/9",
      "subject_law_correct": "3/6",
      "subject_humanities_social_science_correct": "7/9"
    },
    {
      "model_id": "meta-llama/llama-3.3-70b-instruct",
      "name": "Llama 3.3 70B Instruct",
      "creator": "Meta",
      "url": "https://www.llmverifications.com/models/llama-3-3-70b-instruct",
      "open_weights": true,
      "reasoning": false,
      "score_pct": 42.5,
      "correct": 34,
      "graded": 80,
      "failed_requests": 0,
      "cost_per_question_usd": 0.000535,
      "cost_per_correct_usd": 0.001258,
      "output_tokens_per_s": 41.8,
      "time_to_first_token_s": 0.678,
      "end_to_end_s": 8.82,
      "output_tokens_per_question": 855,
      "context_window": 131072,
      "list_input_usd_per_m": 0.1,
      "list_output_usd_per_m": 0.32,
      "quality_tested_at": "2026-10-26T05:22:44.688Z",
      "speed_tested_at": "2026-10-25T15:26:31.948Z",
      "supergpqa_correct": "9/50",
      "mmlu-pro_correct": "25/30",
      "subject_science_correct": "11/30",
      "subject_engineering_correct": "2/15",
      "subject_medicine_correct": "6/11",
      "subject_economics_correct": "5/9",
      "subject_law_correct": "1/6",
      "subject_humanities_social_science_correct": "9/9"
    },
    {
      "model_id": "tencent/hy3",
      "name": "Hy3",
      "creator": "Tencent",
      "url": "https://www.llmverifications.com/models/hy3",
      "open_weights": true,
      "reasoning": true,
      "score_pct": 58.8,
      "correct": 47,
      "graded": 80,
      "failed_requests": 0,
      "cost_per_question_usd": 0.001237,
      "cost_per_correct_usd": 0.002103,
      "output_tokens_per_s": 95.7,
      "time_to_first_token_s": 1.702,
      "end_to_end_s": 9.02,
      "output_tokens_per_question": 2355,
      "context_window": 262144,
      "list_input_usd_per_m": 0.132,
      "list_output_usd_per_m": 0.528,
      "quality_tested_at": "2026-10-26T05:22:44.688Z",
      "speed_tested_at": "2026-10-25T15:26:31.948Z",
      "supergpqa_correct": "22/50",
      "mmlu-pro_correct": "25/30",
      "subject_science_correct": "20/30",
      "subject_engineering_correct": "6/15",
      "subject_medicine_correct": "4/11",
      "subject_economics_correct": "7/9",
      "subject_law_correct": "4/6",
      "subject_humanities_social_science_correct": "6/9"
    },
    {
      "model_id": "z-ai/glm-5.3-flash",
      "name": "GLM 5.3 Flash",
      "creator": "Z.ai",
      "url": "https://www.llmverifications.com/models/glm-5-3-flash",
      "open_weights": true,
      "reasoning": true,
      "score_pct": 67.5,
      "correct": 54,
      "graded": 80,
      "failed_requests": 0,
      "cost_per_question_usd": 0.000146,
      "cost_per_correct_usd": 0.000216,
      "output_tokens_per_s": 83.2,
      "time_to_first_token_s": 0.497,
      "end_to_end_s": 7.39,
      "output_tokens_per_question": 560,
      "context_window": 1048576,
      "list_input_usd_per_m": 0.15,
      "list_output_usd_per_m": 0.5,
      "quality_tested_at": "2026-10-26T05:22:44.688Z",
      "speed_tested_at": "2026-10-25T15:26:31.948Z",
      "supergpqa_correct": "27/50",
      "mmlu-pro_correct": "27/30",
      "subject_science_correct": "22/30",
      "subject_engineering_correct": "8/15",
      "subject_medicine_correct": "5/11",
      "subject_economics_correct": "7/9",
      "subject_law_correct": "4/6",
      "subject_humanities_social_science_correct": "8/9"
    },
    {
      "model_id": "upstage/solar-pro4",
      "name": "Solar Pro 4",
      "creator": "Upstage",
      "url": "https://www.llmverifications.com/models/solar-pro4",
      "open_weights": null,
      "reasoning": true,
      "score_pct": 45,
      "correct": 36,
      "graded": 80,
      "failed_requests": 0,
      "cost_per_question_usd": 0.001823,
      "cost_per_correct_usd": 0.00405,
      "output_tokens_per_s": 91.1,
      "time_to_first_token_s": 0.606,
      "end_to_end_s": 8.32,
      "output_tokens_per_question": 2952,
      "context_window": 524288,
      "list_input_usd_per_m": 0.15,
      "list_output_usd_per_m": 0.6,
      "quality_tested_at": "2026-10-26T05:22:44.688Z",
      "speed_tested_at": "2026-10-25T15:26:31.948Z",
      "supergpqa_correct": "14/50",
      "mmlu-pro_correct": "22/30",
      "subject_science_correct": "18/30",
      "subject_engineering_correct": "1/15",
      "subject_medicine_correct": "5/11",
      "subject_economics_correct": "5/9",
      "subject_law_correct": "1/6",
      "subject_humanities_social_science_correct": "6/9"
    },
    {
      "model_id": "mistralai/mistral-small-2603",
      "name": "Mistral Small 4",
      "creator": "Mistral",
      "url": "https://www.llmverifications.com/models/mistral-small-2603",
      "open_weights": true,
      "reasoning": true,
      "score_pct": 32.5,
      "correct": 26,
      "graded": 80,
      "failed_requests": 0,
      "cost_per_question_usd": 0.001859,
      "cost_per_correct_usd": 0.00572,
      "output_tokens_per_s": 170.2,
      "time_to_first_token_s": 0.482,
      "end_to_end_s": 4.51,
      "output_tokens_per_question": 3021,
      "context_window": 262144,
      "list_input_usd_per_m": 0.15,
      "list_output_usd_per_m": 0.6,
      "quality_tested_at": "2026-10-26T05:22:44.688Z",
      "speed_tested_at": "2026-10-25T15:26:31.948Z",
      "supergpqa_correct": "7/50",
      "mmlu-pro_correct": "19/30",
      "subject_science_correct": "7/30",
      "subject_engineering_correct": "0/15",
      "subject_medicine_correct": "5/11",
      "subject_economics_correct": "6/9",
      "subject_law_correct": "2/6",
      "subject_humanities_social_science_correct": "6/9"
    },
    {
      "model_id": "deepseek/deepseek-v4-flash-vision-exp",
      "name": "DeepSeek V4 Flash Vision Exp",
      "creator": "DeepSeek",
      "url": "https://www.llmverifications.com/models/deepseek-v4-flash-vision-exp",
      "open_weights": true,
      "reasoning": true,
      "score_pct": 71.2,
      "correct": 57,
      "graded": 80,
      "failed_requests": 0,
      "cost_per_question_usd": 0.001066,
      "cost_per_correct_usd": 0.001498,
      "output_tokens_per_s": 170.1,
      "time_to_first_token_s": 0.737,
      "end_to_end_s": 3.18,
      "output_tokens_per_question": 1301,
      "context_window": 1048576,
      "list_input_usd_per_m": 0.2156,
      "list_output_usd_per_m": 0.6468,
      "quality_tested_at": "2026-10-26T05:22:44.688Z",
      "speed_tested_at": "2026-10-25T15:26:31.948Z",
      "supergpqa_correct": "31/50",
      "mmlu-pro_correct": "26/30",
      "subject_science_correct": "25/30",
      "subject_engineering_correct": "10/15",
      "subject_medicine_correct": "4/11",
      "subject_economics_correct": "8/9",
      "subject_law_correct": "2/6",
      "subject_humanities_social_science_correct": "8/9"
    },
    {
      "model_id": "qwen/qwen3-coder-next",
      "name": "Qwen3 Coder Next",
      "creator": "Qwen",
      "url": "https://www.llmverifications.com/models/qwen3-coder-next",
      "open_weights": true,
      "reasoning": false,
      "score_pct": 62.5,
      "correct": 50,
      "graded": 80,
      "failed_requests": 0,
      "cost_per_question_usd": 0.001686,
      "cost_per_correct_usd": 0.002697,
      "output_tokens_per_s": 106.1,
      "time_to_first_token_s": 0.425,
      "end_to_end_s": 4.19,
      "output_tokens_per_question": 2059,
      "context_window": 262144,
      "list_input_usd_per_m": 0.12,
      "list_output_usd_per_m": 0.8,
      "quality_tested_at": "2026-10-26T05:22:44.688Z",
      "speed_tested_at": "2026-10-25T15:26:31.948Z",
      "supergpqa_correct": "23/50",
      "mmlu-pro_correct": "27/30",
      "subject_science_correct": "19/30",
      "subject_engineering_correct": "6/15",
      "subject_medicine_correct": "5/11",
      "subject_economics_correct": "7/9",
      "subject_law_correct": "4/6",
      "subject_humanities_social_science_correct": "9/9"
    },
    {
      "model_id": "arcee-ai/trinity-large-thinking",
      "name": "Trinity Large Thinking",
      "creator": "Arcee AI",
      "url": "https://www.llmverifications.com/models/trinity-large-thinking",
      "open_weights": null,
      "reasoning": true,
      "score_pct": 28.8,
      "correct": 23,
      "graded": 80,
      "failed_requests": 0,
      "cost_per_question_usd": 0.002507,
      "cost_per_correct_usd": 0.008704,
      "output_tokens_per_s": 328.7,
      "time_to_first_token_s": 0.566,
      "end_to_end_s": 2.73,
      "output_tokens_per_question": 3043,
      "context_window": 262144,
      "list_input_usd_per_m": 0.25,
      "list_output_usd_per_m": 0.8,
      "quality_tested_at": "2026-10-26T05:22:44.688Z",
      "speed_tested_at": "2026-10-25T15:26:31.948Z",
      "supergpqa_correct": "5/50",
      "mmlu-pro_correct": "18/30",
      "subject_science_correct": "6/30",
      "subject_engineering_correct": "0/15",
      "subject_medicine_correct": "3/11",
      "subject_economics_correct": "6/9",
      "subject_law_correct": "2/6",
      "subject_humanities_social_science_correct": "6/9"
    },
    {
      "model_id": "qwen/qwen3.6-35b-a3b",
      "name": "Qwen3.6 35B A3B",
      "creator": "Qwen",
      "url": "https://www.llmverifications.com/models/qwen3-6-35b-a3b",
      "open_weights": true,
      "reasoning": true,
      "score_pct": 37.5,
      "correct": 30,
      "graded": 80,
      "failed_requests": 0,
      "cost_per_question_usd": 0.003724,
      "cost_per_correct_usd": 0.00993,
      "output_tokens_per_s": 134.8,
      "time_to_first_token_s": 0.424,
      "end_to_end_s": 5.62,
      "output_tokens_per_question": 3563,
      "context_window": 262144,
      "list_input_usd_per_m": 0.1,
      "list_output_usd_per_m": 0.95,
      "quality_tested_at": "2026-10-26T05:22:44.688Z",
      "speed_tested_at": "2026-10-25T15:26:31.948Z",
      "supergpqa_correct": "9/50",
      "mmlu-pro_correct": "21/30",
      "subject_science_correct": "9/30",
      "subject_engineering_correct": "2/15",
      "subject_medicine_correct": "6/11",
      "subject_economics_correct": "5/9",
      "subject_law_correct": "1/6",
      "subject_humanities_social_science_correct": "7/9"
    },
    {
      "model_id": "minimax/minimax-m3",
      "name": "MiniMax M3",
      "creator": "MiniMax",
      "url": "https://www.llmverifications.com/models/minimax-m3",
      "open_weights": true,
      "reasoning": true,
      "score_pct": 57.5,
      "correct": 46,
      "graded": 80,
      "failed_requests": 0,
      "cost_per_question_usd": 0.002568,
      "cost_per_correct_usd": 0.004467,
      "output_tokens_per_s": 121,
      "time_to_first_token_s": 0.517,
      "end_to_end_s": 4.23,
      "output_tokens_per_question": 2129,
      "context_window": 1048576,
      "list_input_usd_per_m": 0.3,
      "list_output_usd_per_m": 1.2,
      "quality_tested_at": "2026-10-26T05:22:44.688Z",
      "speed_tested_at": "2026-10-25T15:26:31.948Z",
      "supergpqa_correct": "23/50",
      "mmlu-pro_correct": "23/30",
      "subject_science_correct": "24/30",
      "subject_engineering_correct": "5/15",
      "subject_medicine_correct": "3/11",
      "subject_economics_correct": "6/9",
      "subject_law_correct": "3/6",
      "subject_humanities_social_science_correct": "5/9"
    },
    {
      "model_id": "meituan/longcat-2.0",
      "name": "LongCat 2.0",
      "creator": "Meituan",
      "url": "https://www.llmverifications.com/models/longcat-2-0",
      "open_weights": true,
      "reasoning": true,
      "score_pct": 48.8,
      "correct": 39,
      "graded": 80,
      "failed_requests": 0,
      "cost_per_question_usd": 0.003209,
      "cost_per_correct_usd": 0.006576,
      "output_tokens_per_s": 66.8,
      "time_to_first_token_s": 1.363,
      "end_to_end_s": 9.99,
      "output_tokens_per_question": 2600,
      "context_window": 1048756,
      "list_input_usd_per_m": 0.3,
      "list_output_usd_per_m": 1.2,
      "quality_tested_at": "2026-10-26T05:22:44.688Z",
      "speed_tested_at": "2026-10-25T15:26:31.948Z",
      "supergpqa_correct": "17/50",
      "mmlu-pro_correct": "22/30",
      "subject_science_correct": "18/30",
      "subject_engineering_correct": "1/15",
      "subject_medicine_correct": "4/11",
      "subject_economics_correct": "7/9",
      "subject_law_correct": "2/6",
      "subject_humanities_social_science_correct": "7/9"
    },
    {
      "model_id": "thinkingmachines/inkling-small",
      "name": "Inkling Small",
      "creator": "Thinking Machines",
      "url": "https://www.llmverifications.com/models/inkling-small",
      "open_weights": true,
      "reasoning": true,
      "score_pct": 67.5,
      "correct": 54,
      "graded": 80,
      "failed_requests": 0,
      "cost_per_question_usd": 0.000468,
      "cost_per_correct_usd": 0.000694,
      "output_tokens_per_s": 233.4,
      "time_to_first_token_s": 0.512,
      "end_to_end_s": 3.59,
      "output_tokens_per_question": 273,
      "context_window": 524288,
      "list_input_usd_per_m": 0.45,
      "list_output_usd_per_m": 1.2,
      "quality_tested_at": "2026-10-26T05:22:44.688Z",
      "speed_tested_at": "2026-10-25T15:26:31.948Z",
      "supergpqa_correct": "28/50",
      "mmlu-pro_correct": "26/30",
      "subject_science_correct": "24/30",
      "subject_engineering_correct": "6/15",
      "subject_medicine_correct": "6/11",
      "subject_economics_correct": "7/9",
      "subject_law_correct": "4/6",
      "subject_humanities_social_science_correct": "7/9"
    },
    {
      "model_id": "qwen/qwen3.8-27b",
      "name": "Qwen3.8 27B",
      "creator": "Qwen",
      "url": "https://www.llmverifications.com/models/qwen3-8-27b",
      "open_weights": true,
      "reasoning": true,
      "score_pct": 63.8,
      "correct": 51,
      "graded": 80,
      "failed_requests": 0,
      "cost_per_question_usd": 0.004303,
      "cost_per_correct_usd": 0.006745,
      "output_tokens_per_s": 48.5,
      "time_to_first_token_s": 0.528,
      "end_to_end_s": 10.59,
      "output_tokens_per_question": 1913,
      "context_window": 1000000,
      "list_input_usd_per_m": 0.2,
      "list_output_usd_per_m": 2.5,
      "quality_tested_at": "2026-10-26T05:22:44.688Z",
      "speed_tested_at": "2026-10-25T15:26:31.948Z",
      "supergpqa_correct": "28/50",
      "mmlu-pro_correct": "23/30",
      "subject_science_correct": "21/30",
      "subject_engineering_correct": "6/15",
      "subject_medicine_correct": "5/11",
      "subject_economics_correct": "8/9",
      "subject_law_correct": "3/6",
      "subject_humanities_social_science_correct": "8/9"
    },
    {
      "model_id": "google/gemini-3.5-flash-lite",
      "name": "Gemini 3.5 Flash Lite",
      "creator": "Google",
      "url": "https://www.llmverifications.com/models/gemini-3-5-flash-lite",
      "open_weights": null,
      "reasoning": true,
      "score_pct": 75,
      "correct": 60,
      "graded": 80,
      "failed_requests": 0,
      "cost_per_question_usd": 0.003371,
      "cost_per_correct_usd": 0.004495,
      "output_tokens_per_s": 409.1,
      "time_to_first_token_s": 1.067,
      "end_to_end_s": 2.77,
      "output_tokens_per_question": 1311,
      "context_window": 1048576,
      "list_input_usd_per_m": 0.3,
      "list_output_usd_per_m": 2.5,
      "quality_tested_at": "2026-10-26T05:22:44.688Z",
      "speed_tested_at": "2026-10-25T15:26:31.948Z",
      "supergpqa_correct": "33/50",
      "mmlu-pro_correct": "27/30",
      "subject_science_correct": "23/30",
      "subject_engineering_correct": "10/15",
      "subject_medicine_correct": "7/11",
      "subject_economics_correct": "7/9",
      "subject_law_correct": "4/6",
      "subject_humanities_social_science_correct": "9/9"
    },
    {
      "model_id": "nvidia/nemotron-3-ultra-550b-a55b",
      "name": "Nemotron 3 Ultra",
      "creator": "NVIDIA",
      "url": "https://www.llmverifications.com/models/nemotron-3-ultra-550b-a55b",
      "open_weights": true,
      "reasoning": true,
      "score_pct": 60,
      "correct": 48,
      "graded": 80,
      "failed_requests": 0,
      "cost_per_question_usd": 0.00566,
      "cost_per_correct_usd": 0.009433,
      "output_tokens_per_s": 135.8,
      "time_to_first_token_s": 0.805,
      "end_to_end_s": 3.65,
      "output_tokens_per_question": 2177,
      "context_window": 262144,
      "list_input_usd_per_m": 0.6,
      "list_output_usd_per_m": 2.4,
      "quality_tested_at": "2026-10-26T05:22:44.688Z",
      "speed_tested_at": "2026-10-25T15:26:31.948Z",
      "supergpqa_correct": "23/50",
      "mmlu-pro_correct": "25/30",
      "subject_science_correct": "22/30",
      "subject_engineering_correct": "6/15",
      "subject_medicine_correct": "4/11",
      "subject_economics_correct": "6/9",
      "subject_law_correct": "1/6",
      "subject_humanities_social_science_correct": "9/9"
    },
    {
      "model_id": "liquid/lfm-2.5-2.6b",
      "name": "LFM2.5-2.6B",
      "creator": "LiquidAI",
      "url": "https://www.llmverifications.com/models/lfm-2-5-2-6b",
      "open_weights": true,
      "reasoning": true,
      "score_pct": null,
      "correct": null,
      "graded": null,
      "failed_requests": 80,
      "cost_per_question_usd": null,
      "cost_per_correct_usd": null,
      "output_tokens_per_s": null,
      "time_to_first_token_s": null,
      "end_to_end_s": null,
      "output_tokens_per_question": null,
      "context_window": 128000,
      "list_input_usd_per_m": 0.35,
      "list_output_usd_per_m": 0.5,
      "quality_tested_at": "2026-10-26T04:44:39.525Z",
      "speed_tested_at": "2026-10-26T04:44:39.525Z",
      "supergpqa_correct": null,
      "mmlu-pro_correct": null,
      "subject_science_correct": null,
      "subject_engineering_correct": null,
      "subject_medicine_correct": null,
      "subject_economics_correct": null,
      "subject_law_correct": null,
      "subject_humanities_social_science_correct": null
    },
    {
      "model_id": "google/gemini-3.1-pro-preview",
      "name": "Gemini 3.1 Pro Preview",
      "creator": "Google",
      "url": "https://www.llmverifications.com/models/gemini-3-1-pro-preview",
      "open_weights": null,
      "reasoning": true,
      "score_pct": 77.5,
      "correct": 62,
      "graded": 80,
      "failed_requests": 0,
      "cost_per_question_usd": 0.017202,
      "cost_per_correct_usd": 0.022195,
      "output_tokens_per_s": 124,
      "time_to_first_token_s": 3.43,
      "end_to_end_s": 8.9,
      "output_tokens_per_question": 1382,
      "context_window": 1048576,
      "list_input_usd_per_m": 2,
      "list_output_usd_per_m": 12,
      "quality_tested_at": "2026-10-26T03:44:50.952Z",
      "speed_tested_at": "2026-10-25T15:26:31.948Z",
      "supergpqa_correct": "36/50",
      "mmlu-pro_correct": "26/30",
      "subject_science_correct": "26/30",
      "subject_engineering_correct": "10/15",
      "subject_medicine_correct": "7/11",
      "subject_economics_correct": "8/9",
      "subject_law_correct": "3/6",
      "subject_humanities_social_science_correct": "8/9"
    },
    {
      "model_id": "deepseek/deepseek-v4-pro-0813",
      "name": "DeepSeek V4 Pro 0813",
      "creator": "DeepSeek",
      "url": "https://www.llmverifications.com/models/deepseek-v4-pro-0813",
      "open_weights": true,
      "reasoning": true,
      "score_pct": 71.2,
      "correct": 57,
      "graded": 80,
      "failed_requests": 0,
      "cost_per_question_usd": 0.003617,
      "cost_per_correct_usd": 0.00508,
      "output_tokens_per_s": 56.1,
      "time_to_first_token_s": 0.81,
      "end_to_end_s": 10.07,
      "output_tokens_per_question": 1318,
      "context_window": 1048576,
      "list_input_usd_per_m": 1.32,
      "list_output_usd_per_m": 3.96,
      "quality_tested_at": "2026-10-26T03:44:50.952Z",
      "speed_tested_at": "2026-10-25T15:26:31.948Z",
      "supergpqa_correct": "30/50",
      "mmlu-pro_correct": "27/30",
      "subject_science_correct": "25/30",
      "subject_engineering_correct": "8/15",
      "subject_medicine_correct": "4/11",
      "subject_economics_correct": "8/9",
      "subject_law_correct": "4/6",
      "subject_humanities_social_science_correct": "8/9"
    },
    {
      "model_id": "mistralai/mistral-large-4-0",
      "name": "Mistral Large 4",
      "creator": "Mistral",
      "url": "https://www.llmverifications.com/models/mistral-large-4-0",
      "open_weights": null,
      "reasoning": true,
      "score_pct": 50,
      "correct": 40,
      "graded": 80,
      "failed_requests": 0,
      "cost_per_question_usd": 0.011316,
      "cost_per_correct_usd": 0.022631,
      "output_tokens_per_s": 83.2,
      "time_to_first_token_s": 1.055,
      "end_to_end_s": 9.49,
      "output_tokens_per_question": 2613,
      "context_window": 1048576,
      "list_input_usd_per_m": 1.36,
      "list_output_usd_per_m": 4.18,
      "quality_tested_at": "2026-10-26T03:44:50.952Z",
      "speed_tested_at": "2026-10-25T15:26:31.948Z",
      "supergpqa_correct": "17/50",
      "mmlu-pro_correct": "23/30",
      "subject_science_correct": "20/30",
      "subject_engineering_correct": "3/15",
      "subject_medicine_correct": "2/11",
      "subject_economics_correct": "7/9",
      "subject_law_correct": "2/6",
      "subject_humanities_social_science_correct": "6/9"
    },
    {
      "model_id": "meta/muse-spark-open",
      "name": "Muse Spark Open",
      "creator": "Meta",
      "url": "https://www.llmverifications.com/models/muse-spark-open",
      "open_weights": true,
      "reasoning": true,
      "score_pct": 77.5,
      "correct": 62,
      "graded": 80,
      "failed_requests": 0,
      "cost_per_question_usd": 0.00452,
      "cost_per_correct_usd": 0.005832,
      "output_tokens_per_s": 220.1,
      "time_to_first_token_s": 0.496,
      "end_to_end_s": 3.25,
      "output_tokens_per_question": 964,
      "context_window": 1048576,
      "list_input_usd_per_m": 1.25,
      "list_output_usd_per_m": 4.25,
      "quality_tested_at": "2026-10-26T03:44:50.952Z",
      "speed_tested_at": "2026-10-25T15:26:31.948Z",
      "supergpqa_correct": "35/50",
      "mmlu-pro_correct": "27/30",
      "subject_science_correct": "25/30",
      "subject_engineering_correct": "11/15",
      "subject_medicine_correct": "6/11",
      "subject_economics_correct": "8/9",
      "subject_law_correct": "4/6",
      "subject_humanities_social_science_correct": "8/9"
    },
    {
      "model_id": "anthropic/claude-opus-5.5",
      "name": "Claude Opus 5.5",
      "creator": "Anthropic",
      "url": "https://www.llmverifications.com/models/claude-opus-5-5",
      "open_weights": null,
      "reasoning": true,
      "score_pct": 85,
      "correct": 68,
      "graded": 80,
      "failed_requests": 0,
      "cost_per_question_usd": 0.01465,
      "cost_per_correct_usd": 0.017235,
      "output_tokens_per_s": 129.4,
      "time_to_first_token_s": 2.34,
      "end_to_end_s": 7.58,
      "output_tokens_per_question": 645,
      "context_window": 1000000,
      "list_input_usd_per_m": 4,
      "list_output_usd_per_m": 20,
      "quality_tested_at": "2026-10-25T17:56:53.343Z",
      "speed_tested_at": "2026-10-25T15:04:38.754Z",
      "supergpqa_correct": "40/50",
      "mmlu-pro_correct": "28/30",
      "subject_science_correct": "28/30",
      "subject_engineering_correct": "12/15",
      "subject_medicine_correct": "7/11",
      "subject_economics_correct": "8/9",
      "subject_law_correct": "5/6",
      "subject_humanities_social_science_correct": "8/9"
    },
    {
      "model_id": "google/gemini-3.8-flash",
      "name": "Gemini 3.8 Flash",
      "creator": "Google",
      "url": "https://www.llmverifications.com/models/gemini-3-8-flash",
      "open_weights": null,
      "reasoning": true,
      "score_pct": 82.5,
      "correct": 66,
      "graded": 80,
      "failed_requests": 0,
      "cost_per_question_usd": 0.003703,
      "cost_per_correct_usd": 0.004488,
      "output_tokens_per_s": 142.2,
      "time_to_first_token_s": 3.173,
      "end_to_end_s": 5.64,
      "output_tokens_per_question": 925,
      "context_window": 1048576,
      "list_input_usd_per_m": 0.825,
      "list_output_usd_per_m": 4.125,
      "quality_tested_at": "2026-10-25T17:56:53.343Z",
      "speed_tested_at": "2026-10-25T15:04:38.754Z",
      "supergpqa_correct": "37/50",
      "mmlu-pro_correct": "29/30",
      "subject_science_correct": "26/30",
      "subject_engineering_correct": "12/15",
      "subject_medicine_correct": "6/11",
      "subject_economics_correct": "8/9",
      "subject_law_correct": "6/6",
      "subject_humanities_social_science_correct": "8/9"
    },
    {
      "model_id": "z-ai/glm-5.3",
      "name": "GLM 5.3",
      "creator": "Z.ai",
      "url": "https://www.llmverifications.com/models/glm-5-3",
      "open_weights": true,
      "reasoning": true,
      "score_pct": 67.5,
      "correct": 54,
      "graded": 80,
      "failed_requests": 0,
      "cost_per_question_usd": 0.000933,
      "cost_per_correct_usd": 0.001382,
      "output_tokens_per_s": 153.7,
      "time_to_first_token_s": 0.763,
      "end_to_end_s": 3.35,
      "output_tokens_per_question": 523,
      "context_window": 1048576,
      "list_input_usd_per_m": 0.079,
      "list_output_usd_per_m": 1.4,
      "quality_tested_at": "2026-10-25T17:56:53.343Z",
      "speed_tested_at": "2026-10-25T15:04:38.754Z",
      "supergpqa_correct": "27/50",
      "mmlu-pro_correct": "27/30",
      "subject_science_correct": "20/30",
      "subject_engineering_correct": "10/15",
      "subject_medicine_correct": "5/11",
      "subject_economics_correct": "7/9",
      "subject_law_correct": "4/6",
      "subject_humanities_social_science_correct": "8/9"
    },
    {
      "model_id": "deepseek/deepseek-v4.1-flash-1017",
      "name": "DeepSeek V4.1 Flash 1017",
      "creator": "DeepSeek",
      "url": "https://www.llmverifications.com/models/deepseek-v4-1-flash-1017",
      "open_weights": true,
      "reasoning": true,
      "score_pct": 73.8,
      "correct": 59,
      "graded": 80,
      "failed_requests": 0,
      "cost_per_question_usd": 0.000906,
      "cost_per_correct_usd": 0.001227,
      "output_tokens_per_s": 57.4,
      "time_to_first_token_s": 0.877,
      "end_to_end_s": 7.31,
      "output_tokens_per_question": 1318,
      "context_window": 1048576,
      "list_input_usd_per_m": 0.15,
      "list_output_usd_per_m": 0.6,
      "quality_tested_at": "2026-10-25T17:56:53.343Z",
      "speed_tested_at": "2026-10-25T15:04:38.754Z",
      "supergpqa_correct": "31/50",
      "mmlu-pro_correct": "28/30",
      "subject_science_correct": "26/30",
      "subject_engineering_correct": "9/15",
      "subject_medicine_correct": "4/11",
      "subject_economics_correct": "7/9",
      "subject_law_correct": "4/6",
      "subject_humanities_social_science_correct": "9/9"
    },
    {
      "model_id": "openai/gpt-6.1-sol",
      "name": "GPT-6.1 Sol",
      "creator": "OpenAI",
      "url": "https://www.llmverifications.com/models/gpt-6-1-sol",
      "open_weights": null,
      "reasoning": true,
      "score_pct": 76.2,
      "correct": 61,
      "graded": 80,
      "failed_requests": 0,
      "cost_per_question_usd": 0.002855,
      "cost_per_correct_usd": 0.003746,
      "output_tokens_per_s": 41.2,
      "time_to_first_token_s": 2.099,
      "end_to_end_s": 10.81,
      "output_tokens_per_question": 224,
      "context_window": 1050000,
      "list_input_usd_per_m": 2,
      "list_output_usd_per_m": 10,
      "quality_tested_at": "2026-10-25T17:56:53.343Z",
      "speed_tested_at": "2026-10-25T15:04:38.754Z",
      "supergpqa_correct": "35/50",
      "mmlu-pro_correct": "26/30",
      "subject_science_correct": "27/30",
      "subject_engineering_correct": "10/15",
      "subject_medicine_correct": "5/11",
      "subject_economics_correct": "8/9",
      "subject_law_correct": "3/6",
      "subject_humanities_social_science_correct": "8/9"
    },
    {
      "model_id": "google/gemini-4-argon",
      "name": "Gemini 4 Argon",
      "creator": "Google",
      "url": "https://www.llmverifications.com/models/gemini-4-argon",
      "open_weights": null,
      "reasoning": true,
      "score_pct": 84.8,
      "correct": 67,
      "graded": 79,
      "failed_requests": 1,
      "cost_per_question_usd": 0.006261,
      "cost_per_correct_usd": 0.007383,
      "output_tokens_per_s": 68.9,
      "time_to_first_token_s": 3.29,
      "end_to_end_s": 9.88,
      "output_tokens_per_question": 558,
      "context_window": 1048576,
      "list_input_usd_per_m": 2,
      "list_output_usd_per_m": 10,
      "quality_tested_at": "2026-10-25T17:56:53.343Z",
      "speed_tested_at": "2026-10-25T15:04:38.754Z",
      "supergpqa_correct": "38/49",
      "mmlu-pro_correct": "29/30",
      "subject_science_correct": "25/30",
      "subject_engineering_correct": "13/14",
      "subject_medicine_correct": "7/11",
      "subject_economics_correct": "8/9",
      "subject_law_correct": "6/6",
      "subject_humanities_social_science_correct": "8/9"
    },
    {
      "model_id": "openai/gpt-5.4",
      "name": "GPT-5.4",
      "creator": "OpenAI",
      "url": "https://www.llmverifications.com/models/gpt-5-4",
      "open_weights": null,
      "reasoning": true,
      "score_pct": 72.5,
      "correct": 58,
      "graded": 80,
      "failed_requests": 0,
      "cost_per_question_usd": 0.011346,
      "cost_per_correct_usd": 0.015649,
      "output_tokens_per_s": 55.2,
      "time_to_first_token_s": 1.717,
      "end_to_end_s": 8.73,
      "output_tokens_per_question": 706,
      "context_window": 1050000,
      "list_input_usd_per_m": 2.5,
      "list_output_usd_per_m": 15,
      "quality_tested_at": "2026-10-25T17:56:53.343Z",
      "speed_tested_at": "2026-10-25T15:04:38.754Z",
      "supergpqa_correct": "32/50",
      "mmlu-pro_correct": "26/30",
      "subject_science_correct": "25/30",
      "subject_engineering_correct": "10/15",
      "subject_medicine_correct": "4/11",
      "subject_economics_correct": "8/9",
      "subject_law_correct": "4/6",
      "subject_humanities_social_science_correct": "7/9"
    },
    {
      "model_id": "anthropic/claude-haiku-5.5",
      "name": "Claude Haiku 5.5",
      "creator": "Anthropic",
      "url": "https://www.llmverifications.com/models/claude-haiku-5-5",
      "open_weights": null,
      "reasoning": true,
      "score_pct": 68.8,
      "correct": 55,
      "graded": 80,
      "failed_requests": 0,
      "cost_per_question_usd": 0.00048,
      "cost_per_correct_usd": 0.000698,
      "output_tokens_per_s": 191.7,
      "time_to_first_token_s": 0.677,
      "end_to_end_s": 3.92,
      "output_tokens_per_question": 873,
      "context_window": 1000000,
      "list_input_usd_per_m": 0.1,
      "list_output_usd_per_m": 0.5,
      "quality_tested_at": "2026-10-25T17:56:53.343Z",
      "speed_tested_at": "2026-10-25T15:26:31.948Z",
      "supergpqa_correct": "30/50",
      "mmlu-pro_correct": "25/30",
      "subject_science_correct": "23/30",
      "subject_engineering_correct": "10/15",
      "subject_medicine_correct": "5/11",
      "subject_economics_correct": "8/9",
      "subject_law_correct": "2/6",
      "subject_humanities_social_science_correct": "7/9"
    },
    {
      "model_id": "openai/gpt-6-sol",
      "name": "GPT-6 Sol",
      "creator": "OpenAI",
      "url": "https://www.llmverifications.com/models/gpt-6-sol",
      "open_weights": null,
      "reasoning": true,
      "score_pct": 73.8,
      "correct": 59,
      "graded": 80,
      "failed_requests": 0,
      "cost_per_question_usd": 0.002355,
      "cost_per_correct_usd": 0.003191,
      "output_tokens_per_s": 92.3,
      "time_to_first_token_s": 0.909,
      "end_to_end_s": 4.35,
      "output_tokens_per_question": 174,
      "context_window": 1050000,
      "list_input_usd_per_m": 2,
      "list_output_usd_per_m": 10,
      "quality_tested_at": "2026-10-25T17:56:53.343Z",
      "speed_tested_at": "2026-10-25T15:26:31.948Z",
      "supergpqa_correct": "33/50",
      "mmlu-pro_correct": "26/30",
      "subject_science_correct": "27/30",
      "subject_engineering_correct": "8/15",
      "subject_medicine_correct": "5/11",
      "subject_economics_correct": "7/9",
      "subject_law_correct": "4/6",
      "subject_humanities_social_science_correct": "8/9"
    },
    {
      "model_id": "openai/gpt-6-luna",
      "name": "GPT-6 Luna",
      "creator": "OpenAI",
      "url": "https://www.llmverifications.com/models/gpt-6-luna",
      "open_weights": null,
      "reasoning": true,
      "score_pct": 72.5,
      "correct": 58,
      "graded": 80,
      "failed_requests": 0,
      "cost_per_question_usd": 0.000246,
      "cost_per_correct_usd": 0.00034,
      "output_tokens_per_s": 136.9,
      "time_to_first_token_s": 1.196,
      "end_to_end_s": 4.26,
      "output_tokens_per_question": 431,
      "context_window": 1050000,
      "list_input_usd_per_m": 0.1,
      "list_output_usd_per_m": 0.5,
      "quality_tested_at": "2026-10-25T17:56:53.343Z",
      "speed_tested_at": "2026-10-25T15:26:31.948Z",
      "supergpqa_correct": "33/50",
      "mmlu-pro_correct": "25/30",
      "subject_science_correct": "25/30",
      "subject_engineering_correct": "9/15",
      "subject_medicine_correct": "6/11",
      "subject_economics_correct": "7/9",
      "subject_law_correct": "3/6",
      "subject_humanities_social_science_correct": "8/9"
    },
    {
      "model_id": "minimax/minimax-m3.1-flash",
      "name": "MiniMax M3.1 Flash",
      "creator": "MiniMax",
      "url": "https://www.llmverifications.com/models/minimax-m3-1-flash",
      "open_weights": true,
      "reasoning": true,
      "score_pct": 66.2,
      "correct": 53,
      "graded": 80,
      "failed_requests": 0,
      "cost_per_question_usd": 0.000868,
      "cost_per_correct_usd": 0.001312,
      "output_tokens_per_s": 130.5,
      "time_to_first_token_s": 0.526,
      "end_to_end_s": 4.17,
      "output_tokens_per_question": 1376,
      "context_window": 1048576,
      "list_input_usd_per_m": 0.15,
      "list_output_usd_per_m": 0.6,
      "quality_tested_at": "2026-10-25T17:56:53.343Z",
      "speed_tested_at": "2026-10-25T15:26:31.948Z",
      "supergpqa_correct": "28/50",
      "mmlu-pro_correct": "25/30",
      "subject_science_correct": "25/30",
      "subject_engineering_correct": "6/15",
      "subject_medicine_correct": "5/11",
      "subject_economics_correct": "8/9",
      "subject_law_correct": "2/6",
      "subject_humanities_social_science_correct": "7/9"
    },
    {
      "model_id": "xiaomi/mimo-v2.6-pro",
      "name": "MiMo-V2.6-Pro",
      "creator": "Xiaomi",
      "url": "https://www.llmverifications.com/models/mimo-v2-6-pro",
      "open_weights": true,
      "reasoning": true,
      "score_pct": 68.8,
      "correct": 55,
      "graded": 80,
      "failed_requests": 0,
      "cost_per_question_usd": 0.001967,
      "cost_per_correct_usd": 0.002859,
      "output_tokens_per_s": 58.1,
      "time_to_first_token_s": 0.668,
      "end_to_end_s": 7.92,
      "output_tokens_per_question": 2157,
      "context_window": 1050000,
      "list_input_usd_per_m": 0.435,
      "list_output_usd_per_m": 0.87,
      "quality_tested_at": "2026-10-25T17:56:53.343Z",
      "speed_tested_at": "2026-10-25T15:26:31.948Z",
      "supergpqa_correct": "28/50",
      "mmlu-pro_correct": "27/30",
      "subject_science_correct": "22/30",
      "subject_engineering_correct": "8/15",
      "subject_medicine_correct": "6/11",
      "subject_economics_correct": "8/9",
      "subject_law_correct": "3/6",
      "subject_humanities_social_science_correct": "8/9"
    },
    {
      "model_id": "openai/gpt-oss-120b",
      "name": "gpt-oss-120b",
      "creator": "OpenAI",
      "url": "https://www.llmverifications.com/models/gpt-oss-120b",
      "open_weights": true,
      "reasoning": true,
      "score_pct": 58.8,
      "correct": 47,
      "graded": 80,
      "failed_requests": 0,
      "cost_per_question_usd": 0.000126,
      "cost_per_correct_usd": 0.000214,
      "output_tokens_per_s": 81.8,
      "time_to_first_token_s": 0.529,
      "end_to_end_s": 5.43,
      "output_tokens_per_question": 546,
      "context_window": 131072,
      "list_input_usd_per_m": 0.15,
      "list_output_usd_per_m": 0.6,
      "quality_tested_at": "2026-10-25T17:56:53.343Z",
      "speed_tested_at": "2026-10-25T15:26:31.948Z",
      "supergpqa_correct": "25/50",
      "mmlu-pro_correct": "22/30",
      "subject_science_correct": "23/30",
      "subject_engineering_correct": "6/15",
      "subject_medicine_correct": "4/11",
      "subject_economics_correct": "7/9",
      "subject_law_correct": "1/6",
      "subject_humanities_social_science_correct": "6/9"
    },
    {
      "model_id": "meta-llama/llama-4-maverick",
      "name": "Llama 4 Maverick",
      "creator": "Meta",
      "url": "https://www.llmverifications.com/models/llama-4-maverick",
      "open_weights": true,
      "reasoning": false,
      "score_pct": 59,
      "correct": 46,
      "graded": 78,
      "failed_requests": 2,
      "cost_per_question_usd": 0.000587,
      "cost_per_correct_usd": 0.000995,
      "output_tokens_per_s": 13.4,
      "time_to_first_token_s": 0.665,
      "end_to_end_s": 27.93,
      "output_tokens_per_question": 784,
      "context_window": 524288,
      "list_input_usd_per_m": 0.1875,
      "list_output_usd_per_m": 0.6525,
      "quality_tested_at": "2026-10-25T17:56:53.343Z",
      "speed_tested_at": "2026-10-25T15:26:31.948Z",
      "supergpqa_correct": "23/49",
      "mmlu-pro_correct": "23/29",
      "subject_science_correct": "18/30",
      "subject_engineering_correct": "6/14",
      "subject_medicine_correct": "5/10",
      "subject_economics_correct": "7/9",
      "subject_law_correct": "3/6",
      "subject_humanities_social_science_correct": "7/9"
    },
    {
      "model_id": "moonshotai/kimi-k3.1-pro",
      "name": "Kimi K3.1 Pro",
      "creator": "MoonshotAI",
      "url": "https://www.llmverifications.com/models/kimi-k3-1-pro",
      "open_weights": null,
      "reasoning": true,
      "score_pct": 77.5,
      "correct": 62,
      "graded": 80,
      "failed_requests": 0,
      "cost_per_question_usd": 0.010484,
      "cost_per_correct_usd": 0.013528,
      "output_tokens_per_s": 38.1,
      "time_to_first_token_s": 1.313,
      "end_to_end_s": 19.62,
      "output_tokens_per_question": 973,
      "context_window": 1048576,
      "list_input_usd_per_m": 2,
      "list_output_usd_per_m": 10,
      "quality_tested_at": "2026-10-25T17:56:53.343Z",
      "speed_tested_at": "2026-10-25T15:04:38.754Z",
      "supergpqa_correct": "36/50",
      "mmlu-pro_correct": "26/30",
      "subject_science_correct": "26/30",
      "subject_engineering_correct": "11/15",
      "subject_medicine_correct": "6/11",
      "subject_economics_correct": "8/9",
      "subject_law_correct": "3/6",
      "subject_humanities_social_science_correct": "8/9"
    },
    {
      "model_id": "qwen/qwen3.8-max-0902",
      "name": "Qwen3.8 Max (0902)",
      "creator": "Qwen",
      "url": "https://www.llmverifications.com/models/qwen3-8-max-0902",
      "open_weights": null,
      "reasoning": true,
      "score_pct": 75,
      "correct": 60,
      "graded": 80,
      "failed_requests": 0,
      "cost_per_question_usd": 0.011063,
      "cost_per_correct_usd": 0.014751,
      "output_tokens_per_s": 46,
      "time_to_first_token_s": 1.163,
      "end_to_end_s": 12.22,
      "output_tokens_per_question": 1722,
      "context_window": 1000000,
      "list_input_usd_per_m": 2,
      "list_output_usd_per_m": 6,
      "quality_tested_at": "2026-10-25T17:56:53.343Z",
      "speed_tested_at": "2026-10-25T15:04:38.754Z",
      "supergpqa_correct": "32/50",
      "mmlu-pro_correct": "28/30",
      "subject_science_correct": "24/30",
      "subject_engineering_correct": "9/15",
      "subject_medicine_correct": "6/11",
      "subject_economics_correct": "8/9",
      "subject_law_correct": "4/6",
      "subject_humanities_social_science_correct": "9/9"
    },
    {
      "model_id": "anthropic/claude-sonnet-5.5",
      "name": "Claude Sonnet 5.5",
      "creator": "Anthropic",
      "url": "https://www.llmverifications.com/models/claude-sonnet-5-5",
      "open_weights": null,
      "reasoning": true,
      "score_pct": 78.8,
      "correct": 63,
      "graded": 80,
      "failed_requests": 0,
      "cost_per_question_usd": 0.005434,
      "cost_per_correct_usd": 0.006895,
      "output_tokens_per_s": 126.2,
      "time_to_first_token_s": 0.732,
      "end_to_end_s": 6.22,
      "output_tokens_per_question": 456,
      "context_window": 1000000,
      "list_input_usd_per_m": 2,
      "list_output_usd_per_m": 10,
      "quality_tested_at": "2026-10-25T17:06:52.146Z",
      "speed_tested_at": "2026-10-25T15:04:38.754Z",
      "supergpqa_correct": "36/50",
      "mmlu-pro_correct": "27/30",
      "subject_science_correct": "24/30",
      "subject_engineering_correct": "13/15",
      "subject_medicine_correct": "7/11",
      "subject_economics_correct": "8/9",
      "subject_law_correct": "3/6",
      "subject_humanities_social_science_correct": "8/9"
    },
    {
      "model_id": "inclusionai/ling-3.0-flash-vl",
      "name": "Ling 3.0 Flash VL",
      "creator": "inclusionAI",
      "url": "https://www.llmverifications.com/models/ling-3-0-flash-vl",
      "open_weights": true,
      "reasoning": true,
      "score_pct": null,
      "correct": null,
      "graded": null,
      "failed_requests": 0,
      "cost_per_question_usd": null,
      "cost_per_correct_usd": null,
      "output_tokens_per_s": null,
      "time_to_first_token_s": null,
      "end_to_end_s": null,
      "output_tokens_per_question": null,
      "context_window": 131072,
      "list_input_usd_per_m": 0.06,
      "list_output_usd_per_m": 0.18,
      "quality_tested_at": "2026-10-25T15:26:31.948Z",
      "speed_tested_at": "2026-10-25T15:26:31.948Z",
      "supergpqa_correct": null,
      "mmlu-pro_correct": null,
      "subject_science_correct": null,
      "subject_engineering_correct": null,
      "subject_medicine_correct": null,
      "subject_economics_correct": null,
      "subject_law_correct": null,
      "subject_humanities_social_science_correct": null
    },
    {
      "model_id": "qwen/qwen3.5-122b-a10b",
      "name": "Qwen3.5-122B-A10B",
      "creator": "Qwen",
      "url": "https://www.llmverifications.com/models/qwen3-5-122b-a10b",
      "open_weights": true,
      "reasoning": true,
      "score_pct": null,
      "correct": null,
      "graded": null,
      "failed_requests": 0,
      "cost_per_question_usd": null,
      "cost_per_correct_usd": null,
      "output_tokens_per_s": 107.6,
      "time_to_first_token_s": 1.244,
      "end_to_end_s": 18.01,
      "output_tokens_per_question": null,
      "context_window": 262144,
      "list_input_usd_per_m": 0.4,
      "list_output_usd_per_m": 3.2,
      "quality_tested_at": "2026-10-25T15:26:31.948Z",
      "speed_tested_at": "2026-10-25T15:26:31.948Z",
      "supergpqa_correct": null,
      "mmlu-pro_correct": null,
      "subject_science_correct": null,
      "subject_engineering_correct": null,
      "subject_medicine_correct": null,
      "subject_economics_correct": null,
      "subject_law_correct": null,
      "subject_humanities_social_science_correct": null
    },
    {
      "model_id": "qwen/qwen3-next-80b-a3b-thinking",
      "name": "Qwen3 Next 80B A3B Thinking",
      "creator": "Qwen",
      "url": "https://www.llmverifications.com/models/qwen3-next-80b-a3b-thinking",
      "open_weights": true,
      "reasoning": true,
      "score_pct": null,
      "correct": null,
      "graded": null,
      "failed_requests": 0,
      "cost_per_question_usd": null,
      "cost_per_correct_usd": null,
      "output_tokens_per_s": null,
      "time_to_first_token_s": null,
      "end_to_end_s": null,
      "output_tokens_per_question": null,
      "context_window": 262144,
      "list_input_usd_per_m": 0.15,
      "list_output_usd_per_m": 1.2,
      "quality_tested_at": "2026-10-25T15:26:31.948Z",
      "speed_tested_at": "2026-10-25T15:26:31.948Z",
      "supergpqa_correct": null,
      "mmlu-pro_correct": null,
      "subject_science_correct": null,
      "subject_engineering_correct": null,
      "subject_medicine_correct": null,
      "subject_economics_correct": null,
      "subject_law_correct": null,
      "subject_humanities_social_science_correct": null
    },
    {
      "model_id": "amazon/nova-premier-v1",
      "name": "Nova Premier 1.0",
      "creator": "Amazon",
      "url": "https://www.llmverifications.com/models/nova-premier-v1",
      "open_weights": null,
      "reasoning": false,
      "score_pct": null,
      "correct": null,
      "graded": null,
      "failed_requests": 0,
      "cost_per_question_usd": null,
      "cost_per_correct_usd": null,
      "output_tokens_per_s": null,
      "time_to_first_token_s": null,
      "end_to_end_s": null,
      "output_tokens_per_question": null,
      "context_window": 1000000,
      "list_input_usd_per_m": 2.5,
      "list_output_usd_per_m": 12.5,
      "quality_tested_at": "2026-10-25T15:26:31.948Z",
      "speed_tested_at": "2026-10-25T15:26:31.948Z",
      "supergpqa_correct": null,
      "mmlu-pro_correct": null,
      "subject_science_correct": null,
      "subject_engineering_correct": null,
      "subject_medicine_correct": null,
      "subject_economics_correct": null,
      "subject_law_correct": null,
      "subject_humanities_social_science_correct": null
    },
    {
      "model_id": "openai/gpt-5.5-pro",
      "name": "GPT-5.5 Pro",
      "creator": "OpenAI",
      "url": "https://www.llmverifications.com/models/gpt-5-5-pro",
      "open_weights": null,
      "reasoning": true,
      "score_pct": null,
      "correct": null,
      "graded": null,
      "failed_requests": 0,
      "cost_per_question_usd": null,
      "cost_per_correct_usd": null,
      "output_tokens_per_s": null,
      "time_to_first_token_s": 33.85,
      "end_to_end_s": 35.39,
      "output_tokens_per_question": null,
      "context_window": 1050000,
      "list_input_usd_per_m": 30,
      "list_output_usd_per_m": 180,
      "quality_tested_at": "2026-10-25T15:26:31.948Z",
      "speed_tested_at": "2026-10-25T15:26:31.948Z",
      "supergpqa_correct": null,
      "mmlu-pro_correct": null,
      "subject_science_correct": null,
      "subject_engineering_correct": null,
      "subject_medicine_correct": null,
      "subject_economics_correct": null,
      "subject_law_correct": null,
      "subject_humanities_social_science_correct": null
    }
  ]
}