Claude Fable 5.1 scores 69.4 on the Respan Index (#4), ahead of DeepSeek V4 Flash at 43.3 (#37). Claude Fable 5.1 leads on 18 of the 18 benchmarks both report.
* Estimated: no published scores in that category. How the Respan Index works
| LiveBench Coding (LiveBench) | 86.4% | 75% |
| LiveBench Data Analysis (LiveBench) | 80.3% | 79.3% |
| LiveBench Instruction Following (LiveBench) | 73% | 65.5% |
| LiveBench Language (LiveBench) | 89.5% | 79.2% |
| LiveBench Mathematics (LiveBench) | 97% | 86.8% |
| LiveBench Reasoning (LiveBench) | 91.7% | 86.6% |
| Mystery Game Puzzles (Epoch AI) | 58% | 34% |
| OTIS Mock AIME 2024-2025 (Epoch AI) | 100% | 94.4% |
| SimpleQA Verified | 70.8% | 33.6% |
| Terminal-Bench 4.0 (Vals AI) | 58.1% | 18.7% |
| WeirdML (Håvard Tveit Ihle) | 92.9% | 63% |
| LMArena Elo | 1501 | 1436 |
| LMArena WebDev (LMArena) | 1749 | 1581 |
| SimpleBench (SimpleBench) | 86.6% | 61.1% |
Higher is better. Each score links to where it was published.