Up to four models
Muse Spark Open vs Qwen3.8-27B
On the index (GPT-4 = 100), Muse Spark Open scores 161 and Qwen3.8-27B 155. Side by side on the same third-party tests, with price and context. The link in your address bar shares this exact comparison.
161145–177
WeightsOpen
ReleasedOct 2026
Price in / out$1.25 / $4.25
Context1.05M
Core tests taken6 of 9
155139–171
WeightsOpen
ReleasedAug 2026
Price in / out$0.060 / $2.2
Context1.02M
Core tests taken3 of 9
Muse Spark Open leads Qwen3.8-27B by 6 points, ahead on 2 of 3 shared core tests, at 3.4× the price.
Test by testthird-party results
Every result as a table
| Test | Muse Spark Open | Qwen3.8-27B |
|---|---|---|
| Coding | ||
| Code Migration | 21.2% | 14.2% |
| Vibe Code Bench v1.1 | 76.2% | 64.8% |
| Agents | ||
| APEX-Agents | 33.4% | 47.5% |
| Professional work | ||
| Finance Agent (v2) | 61.3% | 48.5% |
| EMB | 53.7% | 59.7% |
| Legal Research Bench | 38.5% | 36.1% |
| Tax Agent Bench | 26.3% | 30.9% |
| Novel problems | ||
| ARC-AGI-2 | 57.5% | 42.4% |
| ARC-AGI-1 | 89.0% | 87.5% |
Tests at least two of these models have taken. Bold rows are the core tests.