GPT-6.1 Sol scores 69.4 on the Respan Index (#4), ahead of GPT-5.5 at 52.5 (#15). GPT-6.1 Sol leads on 20 of the 22 benchmarks both report. GPT-6.1 Sol is 2.8x 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
| 85.3% |
| 93.7% |
| Furniture Assembly (Epoch AI) | 44.2% | 80% |
| GPQA Diamond | 90.7% | 95.4% |
| LiveBench Agentic Coding (LiveBench) | 54% | 56.8% |
| LiveBench Coding (LiveBench) | 82.1% | 80.7% |
| LiveBench Data Analysis (LiveBench) | 81.6% | 82.7% |
| LiveBench Instruction Following (LiveBench) | 70.7% | 74.2% |
| LiveBench Language (LiveBench) | 87.4% | 90.1% |
| LiveBench Mathematics (LiveBench) | 95.9% | 96.8% |
| LiveBench Reasoning (LiveBench) | 89.7% | 92.6% |
| Mystery Game Puzzles (Epoch AI) | 56% | 80% |
| OTIS Mock AIME 2024-2025 (Epoch AI) | 84.4% | 100% |
| SAGE (Vals AI) | 51.5% | 46.5% |
| SimpleQA Verified | 63% | 73.9% |
| LMArena Agent (LMArena) | 0.0415 | 0.1123 |
| LMArena Elo | 1466 | 1483 |
| LMArena Vision (LMArena) | 1287 | 1291 |
| SimpleBench (SimpleBench) | 69% | 82.9% |
Higher is better. Each score links to where it was published.