Gemini 4 Argon
Claude Opus 5.5
Muse Wonder
MiMo-V2.6-Pro
Qwen3.8-Max
Kimi K3
GLM-5.3
GPT-5.5
ERNIE 5.1
DeepSeek-V4.1-Flash-20260910
Grok 4.20 Beta
amazon-nova-experimental-chat
Dola Seed 2.0 Pro
NVIDIA-Nemotron-3-Ultra-550B-A55B
Gemma 4 31B
Step 5 PreviewQwen3.7-Max-Preview vs Muse Spark
- Qwen3.7-Max-Preview and Muse Spark are level on LMArena’s text leaderboard (1475 and 1474).
- On the 5 Vals AI benchmarks both have taken, Qwen3.7-Max-Preview wins 3 and Muse Spark wins 2 (Qwen3.7-Max-Preview: Vibe Code Bench, GPQA Diamond, MMLU-Pro).
LatestQwen3.7-Max-Preview 1475Muse Spark 1474
Side by side
Models (2/6)
- Qwen3.7-Max-Preview
- Muse Spark
| Benchmark | Qwen3.7-Max-Preview | Muse Spark |
|---|---|---|
| The model | ||
| Lab | Alibaba | Meta |
| Released | 2026-05-21 | — |
| Weights | Proprietary | Proprietary |
| Context window | 1M | — |
| Input, per 1M tokens | $1.48 | — |
| Output, per 1M tokens | $4.42 | — |
| LMArena, people’s votes | ||
| LMArena TextMillions of people compare two anonymous models side by side and vote for the better answer | 1475#24 of 351 | 1474#26 of 351 |
| LMArena WebDevPeople ask two anonymous models to build the same web app, try both and vote for the better one | 1515#58 of 124 | — |
| LMArena VisionSide-by-side votes on prompts that include an image | — | 1306#15 of 146 |
| LMArena CodingLMArena’s text votes on prompts that ask for code | 1497#29 of 346 | 1481#56 of 346 |
| LMArena MathLMArena’s text votes on math prompts | 1488#23 of 339 | 1456#65 of 339 |
| LMArena Creative writingLMArena’s text votes on stories, poems and other creative writing | 1448#35 of 349 | 1459#26 of 349 |
| LMArena Hard promptsLMArena’s text votes on the hardest prompts | 1482#35 of 351 | 1474#41 of 351 |
| LMArena Instruction followingLMArena’s text votes on prompts with specific instructions to follow | 1460#40 of 351 | 1443#58 of 351 |
| Vals AI, coding | ||
| SWE-benchReal GitHub issues from open-source projects | 68.80%#66 of 85 | 74.40%#45 of 85 |
| Vibe Code BenchBuilding complete web apps from a plain-language brief, graded on whether the app works | 47.67%#63 of 115 | 19.67%#84 of 115 |
| LiveCodeBenchFresh competitive programming problems, collected after models’ training cut-offs to avoid contamination | 87.06%#19 of 143 | — |
| Vals AI, finance | ||
| Tax Agent BenchAgentic research into US corporate tax questions | 15.83%#54 of 76 | — |
| Vals AI, law | ||
| Legal Research BenchAgentic US legal research | 25.48%#59 of 85 | — |
| Vals AI, medicine | ||
| MedCodeAssigning the right medical billing codes from clinical notes | 38.75%#70 of 107 | 51.31%#16 of 107 |
| Vals AI, reasoning | ||
| GPQA DiamondGraduate-level questions in biology, physics and chemistry that experts answer well and search does not | 90.15%#25 of 138 | 89.65%#28 of 138 |
| MMLU-ProHarder, reasoning-focused multiple choice across 14 subjects, from law to engineering | 89.31%#12 of 138 | 87.32%#30 of 138 |
| AIMEProblems from the American Invitational Mathematics Examination, a qualifier for the US Math Olympiad | — | 96.88%#3 of 96 |
| MMMUCollege-level questions that need both an image and text | — | 87.40%#16 of 93 |
Add models in the compare tool.
Questions
Which is better, Qwen3.7-Max-Preview or Muse Spark?
Qwen3.7-Max-Preview and Muse Spark are level on LMArena’s text leaderboard (1475 and 1474). On the 5 Vals AI benchmarks both have taken, Qwen3.7-Max-Preview wins 3 and Muse Spark wins 2 (Qwen3.7-Max-Preview: Vibe Code Bench, GPQA Diamond, MMLU-Pro).