Claude Fable 5.1 scores 69.4 on the Respan Index (#4), ahead of Claude Opus 4.8 at 52.2 (#16). Claude Fable 5.1 leads on 25 of the 27 benchmarks both report. Claude Opus 4.8 is 2.0x cheaper per token at list price.
* Estimated: no published scores in that category. How the Respan Index works
| FrontierMath Tiers 1-3 v2 (Epoch AI) |
| 90.2% |
| 80% |
| Furniture Assembly (Epoch AI) | 70% | 42.5% |
| LiveBench Agentic Coding (LiveBench) | 66.1% | 50.5% |
| LiveBench Coding (LiveBench) | 86.4% | 81.8% |
| LiveBench Data Analysis (LiveBench) | 80.3% | 66% |
| LiveBench Instruction Following (LiveBench) | 73% | 72% |
| LiveBench Language (LiveBench) | 89.5% | 79.7% |
| LiveBench Mathematics (LiveBench) | 97% | 94.3% |
| LiveBench Reasoning (LiveBench) | 91.7% | 89.2% |
| Mystery Game Puzzles (Epoch AI) | 58% | 36% |
| OTIS Mock AIME 2024-2025 (Epoch AI) | 100% | 98.3% |
| SAGE (Vals AI) | 48.5% | 54.8% |
| SimpleQA Verified | 70.8% | 53% |
| Terminal-Bench 4.0 (Vals AI) | 58.1% | 23.2% |
| Vending-Bench 2 (Andon Labs) | 5421.56 | 5787.43 |
| WeirdML (Håvard Tveit Ihle) | 92.9% | 82.9% |
| LMArena Agent (LMArena) | 0.1431 | 0.0664 |
| LMArena Elo | 1501 | 1453 |
| LMArena Vision (LMArena) | 1288 | 1286 |
| LMArena WebDev (LMArena) | 1749 | 1556 |
| GSO Opt@1 (GSO) | 87.3% | 47.1% |
| SimpleBench (SimpleBench) | 86.6% | 64.8% |
| Humanity's Last Exam (no tools) | 60.9% | 49.8% |
Higher is better. Each score links to where it was published.