Across 19 shared benchmarks, Muse Spark 1.1 scores higher on 19 and Qwen3.5 122B A10B on 0. The widest gap is OmniScience Non-Hallucination, where Muse Spark 1.1 scores 50 against 12.9. Qwen3.5 122B A10B is the cheaper of the two on tracked API pricing ($0.40 against $1.25 per million input tokens).
| Benchmark | Muse Spark 1.1 | Qwen3.5 122B A10B |
|---|---|---|
| AA Agentic Index | 39.7 | 21.3 |
| AA Intelligence | 53.2 | 32.8 |
| AA-LCR | 81.3 | 70.3 |
| AA-Omniscience | 28.1 | -41.5 |
| arena_vision | 1295 | 1246 |
| Artificial Analysis Coding Index | 71.3 | 45.7 |
| baby_vision | 76.3 | 40.2 |
| coding_arena_elo | 1539 | 1358 |
| critpt | 15.1 | 0.9 |
| gdpval | 43.7 | 24.3 |
| GPQA Diamond | 89.8 | 86.6 |
| HLE | 62.1 | 47.5 |
| multichallenge | 75.3 | 61.5 |
| OmniScience Accuracy | 52 | 24.4 |
| OmniScience Non-Hallucination | 50 | 12.9 |
| OSWorld-Verified | 80.8 | 58 |
| scicode | 58.2 | 42 |
| TauBench V3 - Banking | 31.8 | 15.3 |
| Terminal-Bench 2.1 | 80 | 47.6 |
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. Quoted rates are the price-setter row we currently track for each model — its direct or vendor-official listing where one exists (direct, direct), otherwise the lowest tracked offer.