OpenAI
availableShows if the model has enough results for an index.GPT-6 Sol
GPT-6 Sol is a reasoning model from OpenAI in the GPT-6 family. 16 benchmarks count toward its score, in 5 categories.
IndexOverall score. 50 is the middle.76.9 ±6.0
CoverageShare of the index weight with results.80%
SpeedOutput tokens per second.—
Input / 1MUS dollars per 1M input tokens.$2
Output / 1MUS dollars per 1M output tokens.$10
ContextMaximum tokens in one request.1.05M
EloLMArena rating and rank.N/A
50 is the middle of the board. The range shows the doubt in the index.
CapabilitiesScore per category. 50 is the middle.
50 is the middleResults
16 counted| BenchmarkThe test name. | CategoryThe capability that the test measures. | ResultThe score from the publisher. | IndexThis result on the index scale. | RunThe settings of the run. | DateDate of the result. | Published byThe source of the result. |
|---|---|---|---|---|---|---|
| Artificial Analysis Long Context Reasoning | Reasoning | 83.7% | 66.1 | — | — | Artificial Analysis |
| Artificial Analysis MMMU-Pro | Multimodal | 83.3% | 68.9 | — | — | Artificial Analysis |
| DeepSWE | Agentic | 68.8% | 73.8 | — | — | Datacurve AI |
| Artificial Analysis AutomationBench | Agentic | 61.6% | 74.1 | — | — | Artificial Analysis |
| HealthBench Professional | Knowledge | 60.8% | — | — | — | Rebecca Soskin Hicks et al. |
| OSWorld 2.0 | Agentic | 60.5% | 84.7 | — | — | Mengqi Yuan et al. |
| HealthBench Professional raw score | Knowledge | 59.5% | — | — | — | Anthropic |
| Artificial Analysis SciCode | Coding | 57.6% | 72.8 | — | — | Artificial Analysis |
| Agents' Last Exam | Agentic | 56.4% | 94.3 | — | — | DeepSeek-AI |
| Artificial Analysis Omniscience Accuracy | Knowledge | 54.5% | 81.3 | — | — | Artificial Analysis |
| HealthBench length-adjusted score | Knowledge | 53.2% | — | — | — | Anthropic |
| GDPval-AA normalized | Agentic | 49.3% | 73.4 | — | — | Artificial Analysis |
| Artificial Analysis Humanity's Last Exam | Knowledge | 47.9% | 76.5 | — | — | Artificial Analysis |
| Artificial Analysis Intelligence Index | Knowledge | 47.5% | 81.8 | — | — | Artificial Analysis |
| HealthBench raw score | Knowledge | 47.1% | — | — | — | Anthropic |
| AutomationBench | Agentic | 33.2% | 70.8 | — | — | Moonshot AI |
| Critical Physics Tasks | Reasoning | 30.9% | 95.0 | — | — | Artificial Analysis |
| HealthBench Hard | Knowledge | 30.1% | 69.8 | — | — | Meta AI |
| Artificial Analysis GDP.pdf | Agentic | 24.8% | 76.2 | — | — | Artificial Analysis |
| ExploitGym | Agentic | 22.1% | 77.0 | — | — | Zhun Wang et al. |
16 benchmarks count, from 16 of 20 results. A grey row does not count. Too few models took that benchmark.