Up to four models
GPT-5.6 Sol vs Muse Wonder
On the index (GPT-4 = 100), GPT-5.6 Sol scores 179 and Muse Wonder 177. Side by side on the same third-party tests, with price and context. The link in your address bar shares this exact comparison.
GPT-5.6 Sol
179164–195
WeightsClosed
ReleasedJul 2026
Price in / out$4.0 / $20
Context1.05M
Core tests taken5 of 9
177160–193
WeightsClosed
ReleasedOct 2026
Price in / out$4.0 / $20
Context1.05M
Core tests taken2 of 9
GPT-5.6 Sol and Muse Wonder are too close to call (3 points apart, within the uncertainty), ahead on 1 of 1 shared core tests, at a similar price.
Test by testthird-party results
GPT-5.6 Sol
Muse Wonder
Every result as a table
| Test | GPT-5.6 Sol | Muse Wonder |
|---|---|---|
| Reasoning & knowledge | ||
| EBR-bench | 44.8% | 31.4% |
| Maths | ||
| FrontierMath (tiers 1-3) | 89.1% | 82.1% |
| AIME-style maths (OTIS mock) | 100.0% | 99.4% |
| FrontierMath (tier 4) | 82.9% | 70.7% |
| Coding | ||
| MirrorCode | 20.0% | 45.6% |
| Agents | ||
| DTBench | 95.7% | 95.2% |
| Furniture assembly | 56.7% | 54.2% |
| LMCA | 58.5% | 56.8% |
| Mystery game puzzles | 58.0% | 51.0% |
Tests at least two of these models have taken. Bold rows are the core tests.