Claude Fable 5.1 scores 69.4 on the Respan Index (#4), ahead of Claude Fable 5 at 62.2 (#9). Claude Fable 5.1 leads on 19 of the 28 benchmarks both report. Both cost about the same per token at list price.
* Estimated: no published scores in that category. How the Respan Index works
| FrontierMath Tiers 1-3 v2 (Epoch AI) |
| 87% |
| 90.2% |
| FrontierSWE V2 (Proximal Labs) | 47% | 56.3% |
| Furniture Assembly (Epoch AI) | 35.8% | 70% |
| LiveBench Agentic Coding (LiveBench) | 62.2% | 66.1% |
| LiveBench Coding (LiveBench) | 86% | 86.4% |
| LiveBench Data Analysis (LiveBench) | 80.5% | 80.3% |
| LiveBench Instruction Following (LiveBench) | 75.8% | 73% |
| LiveBench Language (LiveBench) | 90.7% | 89.5% |
| LiveBench Mathematics (LiveBench) | 96% | 97% |
| LiveBench Reasoning (LiveBench) | 89.7% | 91.7% |
| MirrorCode (Epoch AI) | 63.9% | 73.3% |
| Mystery Game Puzzles (Epoch AI) | 52% | 58% |
| OTIS Mock AIME 2024-2025 (Epoch AI) | 100% | 100% |
| SAGE (Vals AI) | 51.9% | 48.5% |
| SimpleQA Verified | 70.7% | 70.8% |
| Terminal-Bench 4.0 (Vals AI) | 41.4% | 58.1% |
| Vending-Bench 2 (Andon Labs) | 5680.26 | 5421.56 |
| WeirdML (Håvard Tveit Ihle) | 91.9% | 92.9% |
| LMArena Agent (LMArena) | 0.0821 | 0.1431 |
| LMArena Elo | 1504 | 1501 |
| LMArena Vision (LMArena) | 1309 | 1288 |
| LMArena WebDev (LMArena) | 1625 | 1749 |
| GSO Opt@1 (GSO) | 76.5% | 87.3% |
| SimpleBench (SimpleBench) | 81.9% | 86.6% |
Higher is better. Each score links to where it was published.