Claude Fable 5.1 scores 69.4 on the Respan Index (#4), ahead of Kimi K2.6 at 34.4 (#55). Claude Fable 5.1 leads on 19 of the 21 benchmarks both report. Kimi K2.6 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
| Furniture Assembly (Epoch AI) |
| 70% |
| 21.7% |
| LiveBench Agentic Coding (LiveBench) | 66.1% | 46.9% |
| LiveBench Coding (LiveBench) | 86.4% | 78.6% |
| LiveBench Data Analysis (LiveBench) | 80.3% | 65.1% |
| LiveBench Instruction Following (LiveBench) | 73% | 64.4% |
| LiveBench Language (LiveBench) | 89.5% | 75.1% |
| LiveBench Mathematics (LiveBench) | 97% | 84.3% |
| LiveBench Reasoning (LiveBench) | 91.7% | 79.4% |
| Mystery Game Puzzles (Epoch AI) | 58% | 18% |
| OTIS Mock AIME 2024-2025 (Epoch AI) | 100% | 96.1% |
| SAGE (Vals AI) | 48.5% | 50.2% |
| SimpleQA Verified | 70.8% | 34.9% |
| Vending-Bench 2 (Andon Labs) | 5421.56 | 6204.57 |
| WeirdML (Håvard Tveit Ihle) | 92.9% | 55.9% |
| LMArena Elo | 1501 | 1455 |
| LMArena Vision (LMArena) | 1288 | 1265 |
| LMArena WebDev (LMArena) | 1749 | 1509 |
Higher is better. Each score links to where it was published.