Claude Fable 5.1 and GPT-6.1 Sol tie on the Respan Index at 69.4. GPT-6.1 Sol leads on 12 of the 23 benchmarks both report. GPT-6.1 Sol is 5.0x 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
| FrontierMath Tiers 1-3 v2 (Epoch AI) |
| 90.2% |
| 93.7% |
| Furniture Assembly (Epoch AI) | 70% | 80% |
| LiveBench Agentic Coding (LiveBench) | 66.1% | 56.8% |
| LiveBench Coding (LiveBench) | 86.4% | 80.7% |
| LiveBench Data Analysis (LiveBench) | 80.3% | 82.7% |
| LiveBench Instruction Following (LiveBench) | 73% | 74.2% |
| LiveBench Language (LiveBench) | 89.5% | 90.1% |
| LiveBench Mathematics (LiveBench) | 97% | 96.8% |
| LiveBench Reasoning (LiveBench) | 91.7% | 92.6% |
| Mystery Game Puzzles (Epoch AI) | 58% | 80% |
| OTIS Mock AIME 2024-2025 (Epoch AI) | 100% | 100% |
| SAGE (Vals AI) | 48.5% | 46.5% |
| SimpleQA Verified | 70.8% | 73.9% |
| Terminal-Bench 4.0 (Vals AI) | 58.1% | 55.1% |
| LMArena Agent (LMArena) | 0.1431 | 0.1123 |
| LMArena Elo | 1501 | 1483 |
| LMArena Vision (LMArena) | 1288 | 1291 |
| LMArena WebDev (LMArena) | 1749 | 1758 |
| SimpleBench (SimpleBench) | 86.6% | 82.9% |
Higher is better. Each score links to where it was published.