Up to four models
Muse Wonder vs DeepSeek V4.1 Flash 1017
On the index (GPT-4 = 100), Muse Wonder scores 182 and DeepSeek V4.1 Flash 1017 176. 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
DeepSeek V4.1 Flash 1017176160–192
WeightsOpen
ReleasedOct 2026
Price in / out$0.30 / $1.2
Context1.05M
Core tests taken5 of 9
Muse Wonder leads DeepSeek V4.1 Flash 1017 by 6 points, ahead on 1 of 1 shared core tests, at 15× the price.
Test by testthird-party results
Muse WonderDeepSeek V4.1 Flash 1017Every result as a table
| Test | Muse Wonder | DeepSeek V4.1 Flash 1017 |
|---|---|---|
| Maths | ||
| FrontierMath (tiers 1-3) | 82.1% | 71.2% |
| AIME-style maths (OTIS mock) | 99.4% | 99.4% |
| FrontierMath (tier 4) | 70.7% | 46.3% |
| Agents | ||
| Mystery game puzzles | 51.0% | 49.0% |
Tests at least two of these models have taken. Bold rows are the core tests.
