Claude Fable 5 scores 62.2 on the Respan Index (#9), ahead of Muse Spark 1.3 at 54.1 (#13). Claude Fable 5 leads on 15 of the 21 benchmarks both report. Muse Spark 1.3 is 10x cheaper per token at list price. Muse Spark 1.3 has the larger context window (1.0M tokens).
* Estimated: no published scores in that category. How the Respan Index works
| LiveBench Agentic Coding (LiveBench) | 62.2% | 64.1% |
| LiveBench Coding (LiveBench) | 86% | 81.1% |
| LiveBench Data Analysis (LiveBench) | 80.5% | 79.6% |
| LiveBench Instruction Following (LiveBench) | 75.8% | 78% |
| LiveBench Language (LiveBench) | 90.7% | 82.8% |
| LiveBench Mathematics (LiveBench) | 96% | 95.9% |
| LiveBench Reasoning (LiveBench) | 89.7% | 89.7% |
| Mystery Game Puzzles (Epoch AI) | 52% | 25% |
| OTIS Mock AIME 2024-2025 (Epoch AI) | 100% | 99.2% |
| Terminal-Bench 4.0 (Vals AI) | 41.4% | 24.7% |
| LMArena Agent (LMArena) | 0.0821 | 0.04 |
| LMArena Elo | 1504 | 1494 |
| LMArena Vision (LMArena) | 1309 | 1290 |
| LMArena WebDev (LMArena) | 1625 | 1657 |
| SimpleBench (SimpleBench) | 81.9% | 81.8% |
| AutomationBench | 17.4% | 49.6% |
| Terminal-Bench 2.1 | 84.3% | 88.8% |
Higher is better. Each score links to where it was published.