Side by side
| Muse Spark 1.1 | Qwen3.8 Max (0902) | |
|---|---|---|
| Lab | Meta | Qwen |
| Listed | Jul 16, 2026 | Sep 3, 2026 |
| Input per 1M tokens | $1.88 | $3.00 |
| Output per 1M tokens | $6.38 | $9.00 |
| Cached input per 1M | $0.23 | $0.38 |
| Blended (3:1) per 1M | $3.00 | $4.50 |
| Context window | 1M | 1M |
| Max output | 944K | 131K |
| Knowledge cutoff | - | - |
| Intelligence index | 34.3 | 33.7 |
| Coding index | 71.3 | 76.2 |
| Reasoning | Yes | Yes |
| Reads images | Yes | Yes |
| Tool use | Yes | Yes |
| Structured output | Yes | Yes |
Every benchmark both are scored on
Each model's best score per benchmark, with its source. Scores from different sources or settings are not always comparable; each links to where it was published.
| Benchmark | Muse Spark 1.1 | Qwen3.8 Max (0902) | Leader |
|---|---|---|---|
| Artificial Analysis Agentic Index | 25.8Artificial Analysis and OpenRouter | 56Artificial Analysis and OpenRouter | Qwen3.8 Max (0902) |
| Artificial Analysis Coding Index | 71.3Artificial Analysis and OpenRouter | 76.2Artificial Analysis and OpenRouter | Qwen3.8 Max (0902) |
| Artificial Analysis Intelligence Index | 34.3Artificial Analysis and OpenRouter | 33.6Artificial Analysis and OpenRouter | Muse Spark 1.1 |
| Chess Puzzles | 34%Epoch AI | 37%Epoch AI | Qwen3.8 Max (0902) |
| LMArena (Coding) | 1498 EloLMArena | 1501 EloLMArena | Qwen3.8 Max (0902) |
| LMArena (Overall) | 1478 EloLMArena | 1481 EloLMArena | Qwen3.8 Max (0902) |
| SciCode | 58.8%Epoch AI | 52.1%Epoch AI | Muse Spark 1.1 |
| SimpleQA Verified | 57.8%Epoch AI | 47.3%Epoch AI | Muse Spark 1.1 |
More comparisons
- Llama 4 Maverick vs Muse Spark 1.1
- Muse Spark 1.1 vs Muse Spark 1.2
- DeepSeek V4 Flash 0731 vs Muse Spark 1.1
- Gemini 3.6 Flash vs Muse Spark 1.1
- Muse Spark 1.1 vs GLM 5.2
- Qwen3.8 27B vs Qwen3.8 Max (0902)
- Qwen3.8 Max (0902) vs GLM 5.2
- Gemini 3.6 Flash vs Qwen3.8 Max (0902)
- Gemini 3.5 Flash vs Qwen3.8 Max (0902)
Where these figures come from
Prices are GenMagic's own, what the studio and the API charge, recomputed from each provider's price list every few minutes. The indices are the Artificial Analysis indices, and every benchmark score links to its source, re-read daily. Measured speed is GenMagic's own generation records, in aggregate. See Meta models, Qwen models, every LLM's price and our sources.