GPT-6.1 Sol scores 69.4 on the Respan Index (#4), ahead of GPT-5.6 Terra at 53.5 (#14). GPT-6.1 Sol leads on 21 of the 22 benchmarks both report. GPT-6.1 Sol is 1.1x cheaper per token at list price.
* Estimated: no published scores in that category. How the Respan Index works
| Furniture Assembly (Epoch AI) |
| 54.2% |
| 80% |
| GPQA Diamond | 92.9% | 95.4% |
| LiveBench Agentic Coding (LiveBench) | 54.9% | 56.8% |
| LiveBench Coding (LiveBench) | 78.2% | 80.7% |
| LiveBench Data Analysis (LiveBench) | 79.3% | 82.7% |
| LiveBench Instruction Following (LiveBench) | 64.6% | 74.2% |
| LiveBench Language (LiveBench) | 82.9% | 90.1% |
| LiveBench Mathematics (LiveBench) | 94.9% | 96.8% |
| LiveBench Reasoning (LiveBench) | 90.6% | 92.6% |
| Mystery Game Puzzles (Epoch AI) | 35% | 80% |
| OTIS Mock AIME 2024-2025 (Epoch AI) | 99.7% | 100% |
| SAGE (Vals AI) | 47% | 46.5% |
| SimpleQA Verified | 43.2% | 73.9% |
| Terminal-Bench 4.0 (Vals AI) | 22.7% | 55.1% |
| LMArena Agent (LMArena) | 0.004 | 0.1123 |
| LMArena Elo | 1466 | 1483 |
| LMArena Vision (LMArena) | 1268 | 1291 |
| SimpleBench (SimpleBench) | 48.9% | 82.9% |
Higher is better. Each score links to where it was published.