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 PreviewClaude Opus 5.5 vs Muse Spark
- Claude Opus 5.5 rates higher on LMArena’s text leaderboard: 1516 against 1474.
- On the 2 Vals AI benchmarks both have taken, Claude Opus 5.5 wins 1 and Muse Spark wins 1 (Claude Opus 5.5: Vibe Code Bench).
LatestMuse Spark 1474
Side by side
Models (2/6)
- Claude Opus 5.5
- Muse Spark
| Benchmark | Claude Opus 5.5 | Muse Spark |
|---|---|---|
| The model | ||
| Lab | Anthropic | Meta |
| Released | 2026-09-22 | — |
| Weights | Proprietary | Proprietary |
| Context window | 1M | — |
| Input, per 1M tokens | $4 | — |
| Output, per 1M tokens | $20 | — |
| LMArena, people’s votes | ||
| LMArena TextMillions of people compare two anonymous models side by side and vote for the better answer | 1516#2 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 | 1807#1 of 124 | — |
| LMArena VisionSide-by-side votes on prompts that include an image | 1321#2 of 146 | 1306#15 of 146 |
| LMArena CodingLMArena’s text votes on prompts that ask for code | 1545#1 of 346 | 1481#56 of 346 |
| LMArena MathLMArena’s text votes on math prompts | 1518#6 of 339 | 1456#65 of 339 |
| LMArena Creative writingLMArena’s text votes on stories, poems and other creative writing | 1534#1 of 349 | 1459#26 of 349 |
| LMArena Hard promptsLMArena’s text votes on the hardest prompts | 1536#2 of 351 | 1474#41 of 351 |
| LMArena Instruction followingLMArena’s text votes on prompts with specific instructions to follow | 1539#1 of 351 | 1443#58 of 351 |
| Vals AI, overall | ||
| Vals IndexVals AI’s headline score | 70.18%#2 of 27 | — |
| Vals AI, coding | ||
| Terminal-Bench 4.0Frontier-difficulty tasks an agent completes in a real terminal | 65.15%#1 of 55 | — |
| SWE-benchReal GitHub issues from open-source projects | — | 74.40%#45 of 85 |
| Vibe Code BenchBuilding complete web apps from a plain-language brief, graded on whether the app works | 90.29%#5 of 115 | 19.67%#84 of 115 |
| Code MigrationRewriting working programs in a new language, graded on whether the new program still passes its tests | 81.01%#2 of 28 | — |
| Vals AI, finance | ||
| Finance AgentThe core tasks of a financial analyst, done as an agent with research tools | 67.85%#1 of 31 | — |
| Finance IndexVals AI’s composite of finance tasks | 65.59%#1 of 31 | — |
| Tax Agent BenchAgentic research into US corporate tax questions | 45.57%#3 of 76 | — |
| Vals AI, law | ||
| Legal IndexVals AI’s composite of legal tasks | 72.33%#7 of 28 | — |
| Legal Research BenchAgentic US legal research | 50.48%#7 of 85 | — |
| Vals AI, medicine | ||
| MedCodeAssigning the right medical billing codes from clinical notes | 49.80%#19 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 | — | 89.65%#28 of 138 |
| MMLU-ProHarder, reasoning-focused multiple choice across 14 subjects, from law to engineering | — | 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 |
| Terminal-Bench ScienceExpert-written scientific research workflows, run by an agent in a terminal | 47.14%#3 of 42 | — |
Add models in the compare tool.
Questions
Which is better, Claude Opus 5.5 or Muse Spark?
Claude Opus 5.5 rates higher on LMArena’s text leaderboard: 1516 against 1474. On the 2 Vals AI benchmarks both have taken, Claude Opus 5.5 wins 1 and Muse Spark wins 1 (Claude Opus 5.5: Vibe Code Bench).