Claude Fable 5.1 scores 69.4 on the Respan Index (#4), ahead of Kimi K2.7 Code at 34.1 (#58). Claude Fable 5.1 leads on 17 of the 17 benchmarks both report. Kimi K2.7 Code is 12x cheaper per token at list price. Claude Fable 5.1 has the larger context window (1M tokens).
* Estimated: no published scores in that category. How the Respan Index works
| LiveBench Agentic Coding (LiveBench) |
| 66.1% |
| 45.7% |
| LiveBench Coding (LiveBench) | 86.4% | 74% |
| LiveBench Data Analysis (LiveBench) | 80.3% | 62.7% |
| LiveBench Instruction Following (LiveBench) | 73% | 56.3% |
| LiveBench Language (LiveBench) | 89.5% | 77.9% |
| LiveBench Mathematics (LiveBench) | 97% | 79.6% |
| LiveBench Reasoning (LiveBench) | 91.7% | 82.8% |
| OTIS Mock AIME 2024-2025 (Epoch AI) | 100% | 95.6% |
| SimpleQA Verified | 70.8% | 36.5% |
| Vending-Bench 2 (Andon Labs) | 5421.56 | 5082.94 |
| WeirdML (Håvard Tveit Ihle) | 92.9% | 54.1% |
| LMArena WebDev (LMArena) | 1749 | 1473 |
| SimpleBench (SimpleBench) | 86.6% | 57.9% |
Higher is better. Each score links to where it was published.