GPT-6 Astra Pro
GPT-6 Astra Pro ranks first on 3 of the 6 benchmarks with five or more models scored.
6
Benchmarks with a score
3
Ranked first, out of five or more models
4
In the top three
OpenAI Sep 2026
GPT-6 Astra Pro
Closed weights Flagship
No Epoch Capabilities Index score yet
- WitnessBench 25.6% #2 /12
- WeirdML 93.6% #1 /112
- SimpleBench 86.5% #6 /106
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.
Knowledge and language
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| Last Translation Benchmark | 45.3 | #1 of 36 | Official leaderboard |
Math and science
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| SimpleBench | 86.5% | #6 of 106 | Official leaderboard | |
| Leipzig Benchmark | 88% | #4 of 19 | Official leaderboard |
Coding
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| WeirdML | 93.6% | #1 of 112 | Official leaderboard |
Agents and tools
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| WitnessBench | 25.6% | #2 of 12 | Official leaderboard |
Vision, audio and robotics
| Benchmark | Score | Rank | Source | |
|---|---|---|---|---|
| MineBench | 2,206 | #1 of 75 | Official leaderboard |