GPT-5.6 Sol Pro
GPT-5.6 Sol Pro ranks first on 2 of the 12 benchmarks with five or more models scored.
12
Benchmarks with a score
2
Ranked first, out of five or more models
3
In the top three
OpenAI Jul 2026
GPT-5.6 Sol Pro
Closed weights Flagship
No Epoch Capabilities Index score yet
- $OneMillion-Bench 32.2% #4 /13
- LMCA 59.2% #10 /147
- xbench-ScienceQA 71% #16 /29
Where it ranks
Its best score on each benchmark, and where that ranks among every model with a score there. We rank each model once, at its best setting.
Math and science
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| Leipzig Benchmark | 91% | #1 of 19 | Official leaderboard | |
| ForecastBench | 0.12 | #8 of 82 | Official leaderboard | |
| DTBench | 96% | #18 of 180 | Official leaderboard | |
| SimpleBench | 71.7% | #23 of 106 | Official leaderboard | |
| xbench-ScienceQA | 71% | #16 of 29 | Official leaderboard |
Professional work
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| prinzbench | 91.0 | #1 of 26 | Official leaderboard | |
| RadLE 2.0 | 665.0 | #3 of 12 | Official leaderboard | |
| $OneMillion-Bench | 32.2% | #4 of 13 | Official leaderboard |
Vision, audio and robotics
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| MineBench | 1,973 | #9 of 75 | Official leaderboard |
Other
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| LMCA | 59.2% | #10 of 147 | Official leaderboard | |
| Conceptual Reasoning Index | 70.0 | #11 of 151 | Official leaderboard | |
| ACCoRD | 78.9 | #17 of 152 | Official leaderboard |