Up to four models
Claude Sonnet 5.5 vs Muse Wonder
On the index (GPT-4 = 100), Claude Sonnet 5.5 scores 191 and Muse Wonder 182. Side by side on the same third-party tests, with price and context. The link in your address bar shares this exact comparison.
Claude Sonnet 5.5
191175–207
WeightsClosed
ReleasedSep 2026
Price in / out$2.0 / $10
Context1M
Core tests taken7 of 9
Muse Wonder182166–199
WeightsClosed
ReleasedOct 2026
Price in / out$4.0 / $20
Context1.05M
Core tests taken1 of 9
Claude Sonnet 5.5 leads Muse Wonder by 9 points, ahead on 1 of 1 shared core tests, and costs 2.0× less.
Test by testthird-party results
Claude Sonnet 5.5Muse Wonder
Muse WonderEvery result as a table
| Test | Claude Sonnet 5.5 | Muse Wonder |
|---|---|---|
| Maths | ||
| FrontierMath (tiers 1-3) | 88.8% | 82.1% |
| AIME-style maths (OTIS mock) | 100.0% | 99.4% |
| FrontierMath (tier 4) | 80.5% | 70.7% |
| Agents | ||
| DTBench | 97.3% | 95.2% |
| Furniture assembly | 75.0% | 54.2% |
| LMCA | 68.3% | 56.8% |
| Mystery game puzzles | 65.0% | 51.0% |
Tests at least two of these models have taken. Bold rows are the core tests.
