Score vs. cost per question
OpenAI models in color, every other model in grey
Provider
13 models tested, compared with 65 models from other labs.
OpenAI models in color, every other model in grey
OpenAI models in color, every other model in grey
OpenAI models highlighted against every model in this run · higher is better
OpenAI models highlighted against every model in this run · higher is better
OpenAI models highlighted against every model in this run · lower is better
OpenAI models highlighted against every model in this run · lower is better
OpenAI models highlighted against every model in this run · lower is better
OpenAI models highlighted against every model in this run · higher is better
| # | ||||||||
|---|---|---|---|---|---|---|---|---|
| 1 | GPT-5.3-Codex OpenAI · served by OpenAI | 82.5 | 66 / 80 | 95 | 1.4 s | $0.01 | $1.75 / $14 | 400k |
| 2 | GPT-6 Astra OpenAI · served by OpenAI | 76.2 | 61 / 80 | 49 | 1.3 s | $0.013 | $10 / $50 | 1.1M |
| 3 | GPT-6.1 Terra Pro OpenAI · served by OpenAI | 76.2 | 61 / 80 | — | 8.5 s | $0.005 | $1 / $5 | 1.1M |
| 4 | GPT-6.1 Sol OpenAI · served by OpenAI | 76.2 | 61 / 80 | 41 | 2.1 s | $0.0029 | $2 / $10 | 1.1M |
| 5 | GPT-5.6 Terra OpenAI · served by OpenAI | 75.0 | 60 / 80 | 101 | 1.1 s | $0.0063 | $2 / $12 | 1.1M |
| 6 | GPT-6.1 Terra OpenAI · served by OpenAI | 73.8 | 59 / 80 | 122 | 2.4 s | $0.0013 | $1 / $5 | 1.1M |
| 7 | GPT-6 Sol OpenAI · served by OpenAI | 73.8 | 59 / 80 | 92 | 0.9 s | $0.0024 | $2 / $10 | 1.1M |
| 8 | o3 OpenAI · served by OpenAI | 72.5 | 58 / 80 | 163 | 1.2 s | $0.0088 | $2 / $8 | 200k |
| 9 | GPT-5.4 OpenAI · served by OpenAI | 72.5 | 58 / 80 | 55 | 1.7 s | $0.011 | $2.5 / $15 | 1.1M |
| 10 | GPT-6 Luna OpenAI · served by OpenAI | 72.5 | 58 / 80 | 137 | 1.2 s | $0.00025 | $0.1 / $0.5 | 1.1M |
| 11 | gpt-oss-120b OpenAI · served by CoreWeave | 58.8 | 47 / 80 | 82 | 0.5 s | $0.00013 | $0.15 / $0.6 | 131k |
| 12 | gpt-oss-20b OpenAI · served by Darkbloom | 51.2 | 41 / 80 | 103 | 0.7 s | $0.000066 | $0.018 / $0.09 | 131k |
| 13 | GPT-5.5 Pro OpenAI · served by OpenAI | — | 0 / 0 | — | 33.8 s | — | $30 / $180 | 1.1M |