OpenAI
GPT-6 Sol benchmark results
5 results on 5 benchmarks from 2 sources.
Also listed as: GPT-6 Sol (Max) · gpt-6-sol_max · GPT-6 Sol (max)
All benchmark results
| Benchmarks | Score | Rank | Setting | Source type | Date |
|---|---|---|---|---|---|
| LMArena Text | 1459 | 62 | Overall, style control on; 14707 votes; 95% CI 1453–1465“GPT-6 Sol (Max)” | Official leaderboard | Oct 22, 2026 |
| LMArena WebDev | 1682 | 9 | Overall; 4961 votes; 95% CI 1672–1692“GPT-6 Sol (Max)” | Official leaderboard | Oct 22, 2026 |
| LMArena Vision | 1266 | 39 | Overall, style control on; 3221 votes; 95% CI 1255–1277“GPT-6 Sol (Max)” | Official leaderboard | Oct 19, 2026 |
| GPQA Diamond | 94.3% | 9 | Epoch AI run, accuracy; effort: max | Independent run | Sep 22, 2026 |
| AIME (OTIS Mock AIME 2024–2025) | 100.0% | 1 | Epoch AI run, OTIS Mock AIME 2024–2025; effort: max | Independent run | Sep 22, 2026 |
Where GPT-6 Sol ranks
Primary setting, one best-sourced score per model (official / independent first); neighbours in brackets.
| Benchmark | Score | Rank | Nearby models | #1 |
|---|---|---|---|---|
| AIME (OTIS Mock AIME 2024–2025) | 100.0% | #4 / 200 | GPT-6.1 Sol 100.0% · Claude Sonnet 5.5 100.0% · Claude Opus 5.5 100.0% · Qwen3.8 Max (0902) 100.0% | Gemini 4 Argon100.0% |
| GPQA Diamond | 94.3% | #9 / 217 | GPT-5.4 Pro 94.6% · Gemini 3.1 Pro 94.4% · Grok 4.6 94.0% · GPT-5.5 94.0% | Gemini 4 Argon96.4% |
| LMArena WebDev | 1682 | #8 / 135 | Muse Wonder Full (Max) 1726 · Claude Opus 5 1690 · Qwen3.8 Max (0902) 1673 · Gemini 4 Argon 1673 | Claude Opus 5.51807 |
| LMArena Text | 1459 | #54 / 392 | Kimi K2.6 1461 · Qwen 3.6 Max (Preview) 1461 · DeepSeek-V4-Pro 1458 · GLM-5 1457 | Gemini 4 Argon1517 |
| LMArena Vision | 1266 | #32 / 154 | GPT-5.6 Terra 1268 · Gemini 3.5 Flash-Lite 1267 · Claude Sonnet 5.5 1265 · Kimi K2.6 1265 | Claude Fable 51309 |
Other OpenAI models
GPT-5GPT-5.2o3GPT-4.1GPT-5.4o4-miniGPT-4 Turbo (Nov 2023)GPT-4o (May 2024)GPT-5 miniGPT-5.1GPT-4.1 miniGPT-4o mini
FAQ
Where does GPT-6 Sol rank best?
AIME (OTIS Mock AIME 2024–2025): #4 of 200 (100.0%); #1 there is Gemini 4 Argon (100.0%).
Where do these GPT-6 Sol scores come from?
From Epoch AI Benchmarking Hub and LMArena leaderboard dataset. Each row links to the original leaderboard, dataset or report, and vendor-reported numbers are labelled.