| Benchmark | Muse Spark 1.1 | Qwen3.6 35B A3B |
|---|---|---|
| AA Agentic Index | 39.7 | 21.6 |
| AA Intelligence | 53.2 | 32.1 |
| AA-LCR | 81.3 | 66.7 |
| AA-Omniscience | 28.1 | -22.2 |
| Artificial Analysis Coding Index | 71.3 | 41.9 |
| critpt | 15.1 | 0.3 |
| gdpval | 43.7 | 27.8 |
| GPQA Diamond | 89.8 | 86 |
| HLE | 62.1 | 22.2 |
| MCP Atlas | 88.1 | 62.8 |
| OmniScience Accuracy | 52 | 18.8 |
| OmniScience Non-Hallucination | 50 | 49.5 |
| scicode | 58.2 | 35.8 |
| SWE-bench Pro | 61.5 | 49.5 |
| TauBench V3 - Banking | 31.8 | 9.3 |
| Terminal-Bench 2.1 | 80 | 44.9 |
| toolathlon | 75.6 | 26.9 |
Best tracked score per model per benchmark (default configuration; source-attributed). ↓ marks lower-is-better metrics. Open either model for its full surface, provenance and pricing.