Up to four models
Muse Wonder vs Claude Haiku 5.5
On the index (GPT-4 = 100), Muse Wonder scores 182 and Claude Haiku 5.5 174. Side by side on the same third-party tests, with price and context. The link in your address bar shares this exact comparison.
Muse Wonder182166–199
WeightsClosed
ReleasedOct 2026
Price in / out$4.0 / $20
Context1.05M
Core tests taken1 of 9
Claude Haiku 5.5
174158–191
WeightsClosed
ReleasedOct 2026
Price in / out$0.10 / $0.50
Context1M
Core tests taken7 of 9
Muse Wonder leads Claude Haiku 5.5 by 8 points, ahead on 1 of 1 shared core tests, at 40× the price.
Test by testthird-party results
Muse WonderClaude Haiku 5.5Every result as a table
| Test | Muse Wonder | Claude Haiku 5.5 |
|---|---|---|
| Reasoning & knowledge | ||
| EBR-bench | 31.4% | 43.8% |
| Maths | ||
| FrontierMath (tiers 1-3) | 82.1% | 75.1% |
| AIME-style maths (OTIS mock) | 99.4% | 98.9% |
| FrontierMath (tier 4) | 70.7% | 46.3% |
| Agents | ||
| DTBench | 95.2% | 95.0% |
| Furniture assembly | 54.2% | 47.5% |
| LMCA | 56.8% | 51.1% |
| Mystery game puzzles | 51.0% | 30.0% |
Tests at least two of these models have taken. Bold rows are the core tests.
