Comparing 2 models
Claude Fable 5.1 vs Muse Spark 1.3
Benchmarks through
Verdict
Claude Fable 5.1 places higher on 15 of the 18 tasks where both are ranked. Muse Spark 1.3 costs 8.0x less per input token. Muse Spark 1.3 accepts 1.0x more context.
- Choose Claude Fable 5.1 for Competition Math (#1), Tool & Function Calling (#1), Math & Reasoning (#1).
- Choose Muse Spark 1.3 for Marketing Copy (#4), Business Writing (#4), Image Understanding (#6).
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 1.3 | Source |
|---|---|---|---|
| Design Arena Coding | 1338 Elo | 1353 Elo | source · 2026-10-16 |
| Design Arena Full-stack Agent | 1326 Elo | 1295 Elo | source · 2026-10-14 |
| Design Arena UI | 1338 Elo | 1344 Elo | source · 2026-10-16 |
| Design Arena Web-app Agent | 1311 Elo | 1289 Elo | source · 2026-10-14 |
| Design Arena Website | 1314 Elo | 1348 Elo | source · 2026-10-16 |
| FrontierMath Tiers 1-3 (Epoch AI) | 90.2% ± 1.8 | 74.4% ± 2.6 | source · 2026-09-01 |
| LiveBench Agentic Coding | 66.1% | 64.1% | source · 2026-10-16 |
| LiveBench Coding | 86.4% | 81.1% | source · 2026-10-16 |
| LiveBench Data Analysis | 80.3% | 79.6% | source · 2026-10-16 |
| LiveBench Instruction Following | 73.0% | 78% | source · 2026-10-16 |
| LiveBench Language | 89.5% | 82.8% | source · 2026-10-16 |
| LiveBench Math | 97.0% | 96.0% | source · 2026-10-16 |
| LiveBench Reasoning | 91.7% | 89.7% | source · 2026-10-16 |
| LMArena Agent | 14.1 | 3.6 | source · 2026-10-14 |
| LMArena Agent Bash Recovery | 11.6 | 6.1 | source · 2026-10-08 |
| LMArena Agent Steerability | 14.7 | 5.6 | source · 2026-10-14 |
| LMArena Agent Task Outcome | 15.7 | 4.9 | source · 2026-10-14 |
| LMArena Agent Tool Hallucination | 0.6 | 0.6 | source · 2026-10-14 |
| LMArena Creative Writing | 1508 Elo | 1460 Elo | source · 2026-10-15 |
| LMArena Instruction Following | 1517 Elo | 1478 Elo | source · 2026-10-15 |
| LMArena Long Query | 1523 Elo | 1488 Elo | source · 2026-10-15 |
| LMArena Math | 1528 Elo | 1496 Elo | source · 2026-10-15 |
| LMArena Text | 1502 Elo | 1494 Elo | source · 2026-10-15 |
| LMArena Text Factuality | 1498 Elo | 1479 Elo | source · 2026-10-15 |
| LMArena Vision | 1286 Elo | 1290 Elo | source · 2026-10-09 |
| LMArena Vision Diagrams | 1326 Elo | 1321 Elo | source · 2026-10-09 |
| LMArena Vision OCR | 1302 Elo | 1306 Elo | source · 2026-10-09 |
| LMArena WebDev | 1743 Elo | 1659 Elo | source · 2026-10-13 |
| LMArena WebDev Image-to-Web | 1720 Elo | 1642 Elo | source · 2026-10-09 |
| OTIS Mock AIME (Epoch AI) | 100% ± 0 | 99.2% ± 0.6 | source · 2026-09-01 |
| Terminal-Bench (4.0) | 57.9% | 14.6% | source · 2026-10-16 |
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.