Comparing 2 models
Claude Fable 5.1 vs Muse Spark 1.2
Benchmarks through
Verdict
Claude Fable 5.1 places higher on 6 of the 9 tasks where both are ranked. Muse Spark 1.2 costs 8.0x less per input token. Muse Spark 1.2 accepts 1.0x more context.
- Choose Claude Fable 5.1 for Charts & Diagrams (#2), Document Summarization (#4), Summarization (#4).
- Choose Muse Spark 1.2 for Image Understanding (#4), Document Parsing (#4), OCR & Documents (#4).
Built from the published task rankings below; ranks come from each task's own weighted benchmarks, so a win on one task says nothing about another.
Measured head to head
Benchmarks both models were run on
| Evaluation | Claude Fable 5.1 | Muse Spark 1.2 | Source |
|---|---|---|---|
| Design Arena Coding | 1338 Elo | 1315 Elo | source · 2026-10-16 |
| Design Arena Full-stack Agent | 1326 Elo | 1210 Elo | source · 2026-10-14 |
| Design Arena UI | 1338 Elo | 1302 Elo | source · 2026-10-16 |
| Design Arena Web-app Agent | 1311 Elo | 1216 Elo | source · 2026-10-14 |
| Design Arena Website | 1314 Elo | 1315 Elo | source · 2026-10-16 |
| LiveBench Agentic Coding | 66.1% | 57.6% | source · 2026-10-16 |
| LiveBench Coding | 86.4% | 77.5% | source · 2026-10-16 |
| LiveBench Data Analysis | 80.3% | 76.5% | source · 2026-10-16 |
| LiveBench Instruction Following | 73.0% | 74.3% | source · 2026-10-16 |
| LiveBench Language | 89.5% | 78.6% | source · 2026-10-16 |
| LiveBench Math | 97.0% | 91.2% | source · 2026-10-16 |
| LiveBench Reasoning | 91.7% | 90% | source · 2026-10-16 |
| LMArena Agent | 14.1 | -6.5 | source · 2026-10-14 |
| LMArena Agent Bash Recovery | 11.6 | 5.8 | source · 2026-10-08 |
| LMArena Agent Steerability | 14.7 | -8.3 | source · 2026-10-14 |
| LMArena Agent Task Outcome | 15.7 | -7.9 | source · 2026-10-14 |
| LMArena Agent Tool Hallucination | 0.6 | 0.2 | source · 2026-10-14 |
| LMArena Creative Writing | 1508 Elo | 1440 Elo | source · 2026-10-15 |
| LMArena Instruction Following | 1517 Elo | 1462 Elo | source · 2026-10-15 |
| LMArena Long Query | 1523 Elo | 1476 Elo | source · 2026-10-15 |
| LMArena Math | 1528 Elo | 1476 Elo | source · 2026-10-15 |
| LMArena Text | 1502 Elo | 1493 Elo | source · 2026-10-15 |
| LMArena Text Factuality | 1498 Elo | 1481 Elo | source · 2026-10-15 |
| LMArena Vision | 1286 Elo | 1293 Elo | source · 2026-10-09 |
| LMArena Vision Diagrams | 1326 Elo | 1317 Elo | source · 2026-10-09 |
| LMArena Vision OCR | 1302 Elo | 1307 Elo | source · 2026-10-09 |
| LMArena WebDev | 1743 Elo | 1533 Elo | source · 2026-10-13 |
| SimpleQA Verified (Epoch AI) | 70.8% ± 1.4 | 60.3% ± 1.6 | source · 2026-09-01 |
Values are as published by each evaluator, in its own units; rows from different evaluators are not on a common scale.
task evidence
How they place when the question changes
Lower ranks are better. “Best” marks the strongest option in this shortlist for that task.