GPT-6.1 Sol scores 69.4 on the Respan Index (#4), ahead of Qwen3.7-Max at 40.5 (#45). GPT-6.1 Sol leads on 18 of the 18 benchmarks both report. Qwen3.7-Max is 1.1x cheaper per token at list price. GPT-6.1 Sol has the larger context window (1.1M tokens).
* Estimated: no published scores in that category. How the Respan Index works
| GPQA Diamond |
| 95.4% |
| 90.9% |
| LiveBench Agentic Coding (LiveBench) | 56.8% | 43.6% |
| LiveBench Coding (LiveBench) | 80.7% | 74.2% |
| LiveBench Data Analysis (LiveBench) | 82.7% | 71.8% |
| LiveBench Instruction Following (LiveBench) | 74.2% | 74% |
| LiveBench Language (LiveBench) | 90.1% | 79.7% |
| LiveBench Mathematics (LiveBench) | 96.8% | 85.2% |
| LiveBench Reasoning (LiveBench) | 92.6% | 83.3% |
| Mystery Game Puzzles (Epoch AI) | 80% | 32% |
| OTIS Mock AIME 2024-2025 (Epoch AI) | 100% | 95.6% |
| SimpleQA Verified | 73.9% | 55.8% |
| LMArena Agent (LMArena) | 0.1123 | -0.0513 |
| LMArena WebDev (LMArena) | 1758 | 1515 |
| SimpleBench (SimpleBench) | 82.9% | 70.4% |
Higher is better. Each score links to where it was published.