| 1 | Gemini 3.8 FlashGoogle | 6 / 6 | 100.0% | 61–100% |
| 1 | Gemini 4 ArgonGoogle · statistically tied with #1 | 6 / 6 | 100.0% | 61–100% |
| 3 | Claude Fable 5.1Anthropic · statistically tied with #1 | 5 / 6 | 83.3% | 44–97% |
| 3 | o3OpenAI · statistically tied with #1 | 5 / 6 | 83.3% | 44–97% |
| 3 | Claude Opus 5.5Anthropic · statistically tied with #1 | 5 / 6 | 83.3% | 44–97% |
| 6 | InklingThinking Machines · statistically tied with #1 | 4 / 6 | 66.7% | 30–90% |
| 6 | Muse WonderMeta · statistically tied with #1 | 4 / 6 | 66.7% | 30–90% |
| 6 | Grok 4.7SpaceXAI · statistically tied with #1 | 4 / 6 | 66.7% | 30–90% |
| 6 | GPT-5.6 TerraOpenAI · statistically tied with #1 | 4 / 6 | 66.7% | 30–90% |
| 6 | GPT-5.3-CodexOpenAI · statistically tied with #1 | 4 / 6 | 66.7% | 30–90% |
| 6 | Hy3Tencent · statistically tied with #1 | 4 / 6 | 66.7% | 30–90% |
| 6 | GLM 5.3 FlashZ.ai · statistically tied with #1 | 4 / 6 | 66.7% | 30–90% |
| 6 | Qwen3 Coder NextQwen · statistically tied with #1 | 4 / 6 | 66.7% | 30–90% |
| 6 | Inkling SmallThinking Machines · statistically tied with #1 | 4 / 6 | 66.7% | 30–90% |
| 6 | Gemini 3.5 Flash LiteGoogle · statistically tied with #1 | 4 / 6 | 66.7% | 30–90% |
| 6 | DeepSeek V4 Pro 0813DeepSeek · statistically tied with #1 | 4 / 6 | 66.7% | 30–90% |
| 6 | Muse Spark OpenMeta · statistically tied with #1 | 4 / 6 | 66.7% | 30–90% |
| 6 | GLM 5.3Z.ai · statistically tied with #1 | 4 / 6 | 66.7% | 30–90% |
| 6 | DeepSeek V4.1 Flash 1017DeepSeek · statistically tied with #1 | 4 / 6 | 66.7% | 30–90% |
| 6 | GPT-5.4OpenAI · statistically tied with #1 | 4 / 6 | 66.7% | 30–90% |
| 6 | GPT-6 SolOpenAI · statistically tied with #1 | 4 / 6 | 66.7% | 30–90% |
| 6 | Qwen3.8 Max (0902)Qwen · statistically tied with #1 | 4 / 6 | 66.7% | 30–90% |
| 23 | Kimi K2.7 CodeMoonshotAI · statistically tied with #1 | 3 / 6 | 50.0% | 19–81% |
| 23 | Command ACohere · statistically tied with #1 | 3 / 6 | 50.0% | 19–81% |
| 23 | Qwen3.7 PlusQwen · statistically tied with #1 | 3 / 6 | 50.0% | 19–81% |
| 23 | GPT-6 AstraOpenAI · statistically tied with #1 | 3 / 6 | 50.0% | 19–81% |
| 23 | GPT-6.1 TerraOpenAI · statistically tied with #1 | 3 / 6 | 50.0% | 19–81% |
| 23 | GPT-6.1 Terra ProOpenAI · statistically tied with #1 | 3 / 6 | 50.0% | 19–81% |
| 23 | Mercury 2.5Inception · statistically tied with #1 | 3 / 6 | 50.0% | 19–81% |
| 23 | MiMo-V2.6-FlashXiaomi · statistically tied with #1 | 3 / 6 | 50.0% | 19–81% |
| 23 | MiniMax M3MiniMax · statistically tied with #1 | 3 / 6 | 50.0% | 19–81% |
| 23 | Qwen3.8 27BQwen · statistically tied with #1 | 3 / 6 | 50.0% | 19–81% |
| 23 | Gemini 3.1 Pro PreviewGoogle · statistically tied with #1 | 3 / 6 | 50.0% | 19–81% |
| 23 | GPT-6.1 SolOpenAI · statistically tied with #1 | 3 / 6 | 50.0% | 19–81% |
| 23 | GPT-6 LunaOpenAI · statistically tied with #1 | 3 / 6 | 50.0% | 19–81% |
| 23 | MiMo-V2.6-ProXiaomi · statistically tied with #1 | 3 / 6 | 50.0% | 19–81% |
| 23 | Llama 4 MaverickMeta · statistically tied with #1 | 3 / 6 | 50.0% | 19–81% |
| 23 | Kimi K3.1 ProMoonshotAI · statistically tied with #1 | 3 / 6 | 50.0% | 19–81% |
| 23 | Claude Sonnet 5.5Anthropic · statistically tied with #1 | 3 / 6 | 50.0% | 19–81% |
| 40 | Step 5 PreviewStepFun · statistically tied with #1 | 2 / 6 | 33.3% | 10–70% |
| 40 | Mistral Medium 3.5Mistral · statistically tied with #1 | 2 / 6 | 33.3% | 10–70% |
| 40 | Qwen3.8 2.4T A95BQwen · statistically tied with #1 | 2 / 6 | 33.3% | 10–70% |
| 40 | Llama 4 ScoutMeta · statistically tied with #1 | 2 / 6 | 33.3% | 10–70% |
| 40 | Hermes 4 405BNous · statistically tied with #1 | 2 / 6 | 33.3% | 10–70% |
| 40 | gpt-oss-20bOpenAI · statistically tied with #1 | 2 / 6 | 33.3% | 10–70% |
| 40 | Phi 4Microsoft · statistically tied with #1 | 2 / 6 | 33.3% | 10–70% |
| 40 | Granite 4.2 8BIBM · statistically tied with #1 | 2 / 6 | 33.3% | 10–70% |
| 40 | Ministral 3 14B 2512Mistral · statistically tied with #1 | 2 / 6 | 33.3% | 10–70% |
| 40 | Mistral Small 4Mistral · statistically tied with #1 | 2 / 6 | 33.3% | 10–70% |
| 40 | DeepSeek V4 Flash Vision ExpDeepSeek · statistically tied with #1 | 2 / 6 | 33.3% | 10–70% |
| 40 | Trinity Large ThinkingArcee AI · statistically tied with #1 | 2 / 6 | 33.3% | 10–70% |
| 40 | LongCat 2.0Meituan · statistically tied with #1 | 2 / 6 | 33.3% | 10–70% |
| 40 | Mistral Large 4Mistral · statistically tied with #1 | 2 / 6 | 33.3% | 10–70% |
| 40 | Claude Haiku 5.5Anthropic · statistically tied with #1 | 2 / 6 | 33.3% | 10–70% |
| 40 | MiniMax M3.1 FlashMiniMax · statistically tied with #1 | 2 / 6 | 33.3% | 10–70% |
| 56 | Gemma 4 26B A4BGoogle | 1 / 6 | 16.7% | 3–56% |
| 56 | Gemma 4 31BGoogle | 1 / 6 | 16.7% | 3–56% |
| 56 | Ling 3.1 FlashinclusionAI | 1 / 6 | 16.7% | 3–56% |
| 56 | Qwen3.5 397B A17BQwen | 1 / 6 | 16.7% | 3–56% |
| 56 | Granite 4.0 MicroIBM | 1 / 6 | 16.7% | 3–56% |
| 56 | Ministral 3 3B 2512Mistral | 1 / 6 | 16.7% | 3–56% |
| 56 | Nova Micro 1.0Amazon | 1 / 6 | 16.7% | 3–56% |
| 56 | Ministral 3 8B 2512Mistral | 1 / 6 | 16.7% | 3–56% |
| 56 | Nemotron 3.5 LightningNVIDIA | 1 / 6 | 16.7% | 3–56% |
| 56 | Llama 3.3 70B InstructMeta | 1 / 6 | 16.7% | 3–56% |
| 56 | Solar Pro 4Upstage | 1 / 6 | 16.7% | 3–56% |
| 56 | Qwen3.6 35B A3BQwen | 1 / 6 | 16.7% | 3–56% |
| 56 | Nemotron 3 UltraNVIDIA | 1 / 6 | 16.7% | 3–56% |
| 56 | gpt-oss-120bOpenAI | 1 / 6 | 16.7% | 3–56% |
| 70 | Reka Flash 3rekaai | 0 / 6 | 0.0% | 0–39% |
| 70 | Nemotron 3.5 Super VLNVIDIA | 0 / 6 | 0.0% | 0–39% |
| 70 | Solar Mini 4Upstage | 0 / 6 | 0.0% | 0–39% |