Claude Fable 5.1 scores 69.4 on the Respan Index (#4), ahead of Claude Opus 5 at 63.9 (#7). Claude Fable 5.1 leads on 26 of the 30 benchmarks both report. Claude Opus 5 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% |
| 85.6% |
| FrontierSWE V2 (Proximal Labs) | 56.3% | 52% |
| Furniture Assembly (Epoch AI) | 70% | 60.8% |
| LiveBench Agentic Coding (LiveBench) | 66.1% | 65.2% |
| LiveBench Coding (LiveBench) | 86.4% | 81.4% |
| LiveBench Data Analysis (LiveBench) | 80.3% | 74.6% |
| LiveBench Instruction Following (LiveBench) | 73% | 63.8% |
| LiveBench Language (LiveBench) | 89.5% | 88.7% |
| LiveBench Mathematics (LiveBench) | 97% | 95.7% |
| LiveBench Reasoning (LiveBench) | 91.7% | 91.2% |
| Mystery Game Puzzles (Epoch AI) | 58% | 59% |
| OTIS Mock AIME 2024-2025 (Epoch AI) | 100% | 98.9% |
| SAGE (Vals AI) | 48.5% | 49.4% |
| SimpleQA Verified | 70.8% | 59.9% |
| Terminal-Bench 4.0 (Vals AI) | 58.1% | 53.5% |
| Vending-Bench 2 (Andon Labs) | 5421.56 | 11181.87 |
| WeirdML (Håvard Tveit Ihle) | 92.9% | 91.8% |
| LMArena Agent (LMArena) | 0.1431 | 0.0867 |
| LMArena Elo | 1501 | 1490 |
| LMArena Vision (LMArena) | 1288 | 1289 |
| LMArena WebDev (LMArena) | 1749 | 1695 |
| SimpleBench (SimpleBench) | 86.6% | 80.6% |
| CursorBench 3.2.0 | 73.4% | 70% |
| GDPval-AA v2 | 1853 | 1824 |
| Humanity's Last Exam (no tools) | 60.9% | 56.6% |
| Terminal-Bench Science 0.1 | 52.6% | 29% |
Higher is better. Each score links to where it was published.