GPT-6.1 Sol scores 69.4 on the Respan Index (#4), ahead of Grok 4.5 at 43.2 (#38). GPT-6.1 Sol leads on 22 of the 22 benchmarks both report. Grok 4.5 is 1.3x 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
| Furniture Assembly (Epoch AI) |
| 80% |
| 22.5% |
| GPQA Diamond | 95.4% | 93.4% |
| LiveBench Agentic Coding (LiveBench) | 56.8% | 56.5% |
| LiveBench Coding (LiveBench) | 80.7% | 68.6% |
| LiveBench Data Analysis (LiveBench) | 82.7% | 73% |
| LiveBench Instruction Following (LiveBench) | 74.2% | 71.5% |
| LiveBench Language (LiveBench) | 90.1% | 82.8% |
| LiveBench Mathematics (LiveBench) | 96.8% | 90.8% |
| LiveBench Reasoning (LiveBench) | 92.6% | 87.2% |
| OTIS Mock AIME 2024-2025 (Epoch AI) | 100% | 97.8% |
| SAGE (Vals AI) | 46.5% | 35% |
| SimpleQA Verified | 73.9% | 48.3% |
| Terminal-Bench 4.0 (Vals AI) | 55.1% | 8.6% |
| LMArena Agent (LMArena) | 0.1123 | 0.0121 |
| LMArena Elo | 1483 | 1450 |
| LMArena Vision (LMArena) | 1291 | 1279 |
| LMArena WebDev (LMArena) | 1758 | 1552 |
| SimpleBench (SimpleBench) | 82.9% | 70% |
Higher is better. Each score links to where it was published.