Up to four models
DeepSeek V4.1 Flash 1017 vs Muse Spark 1.3
On the index (GPT-4 = 100), DeepSeek V4.1 Flash 1017 scores 172 and Muse Spark 1.3 169. Side by side on the same third-party tests, with price and context. The link in your address bar shares this exact comparison.
172156–188
WeightsOpen
ReleasedOct 2026
Price in / out$0.036 / $0.50
Context1.05M
Core tests taken6 of 9
169153–186
WeightsClosed
ReleasedSep 2026
Price in / out$1.25 / $4.25
Context1.05M
Core tests taken4 of 9
DeepSeek V4.1 Flash 1017 and Muse Spark 1.3 are too close to call (3 points apart, within the uncertainty), ahead on 2 of 4 shared core tests, and costs 13× less.
Test by testthird-party results
Every result as a table
| Test | DeepSeek V4.1 Flash 1017 | Muse Spark 1.3 |
|---|---|---|
| Maths | ||
| FrontierMath (tiers 1-3) | 71.2% | 74.4% |
| AIME-style maths (OTIS mock) | 99.4% | 99.2% |
| Chess puzzles | 46.0% | 37.0% |
| FrontierMath (tier 4) | 46.3% | 46.3% |
| Coding | ||
| Terminal-Bench 4.0 | 31.8% | 10.6% |
| Code Migration | 44.2% | 27.6% |
| Vibe Code Bench v1.1 | 87.7% | 82.9% |
| Agents | ||
| APEX-Agents | 69.8% | 58.6% |
| Mystery game puzzles | 49.0% | 25.0% |
| Professional work | ||
| Finance Agent (v2) | 57.0% | 58.9% |
| EMB | 61.8% | 62.7% |
| Legal Research Bench | 45.2% | 40.9% |
| Tax Agent Bench | 44.4% | 37.9% |
Tests at least two of these models have taken. Bold rows are the core tests.