TestsBenchmarks · Human preference
LMArena Text (overall)
Crowd-voted Elo (style-controlled) from blind head-to-head chats across all text prompts.
Elo ratingHigher is betterCounts toward:Weights: Writing & creativity ×0.5The test's websiteOfficial page ↗
Measured by independent testersIndependent Reported by the makerVendor-reported
| Thinking levelSetting | |||||||
|---|---|---|---|---|---|---|---|
| 1 | Gemini 4 Argon | Google (Gemini / DeepMind) | 1525 | Highgemini-4-argon-high | Independent testIndependentLMArena ↗ | — | 30 Sep 2026 |
| 2 | Claude Opus 4.6 | Anthropic | 1506 | Highclaude-opus-4-6-high | Independent testIndependentLMArena ↗ | — | 30 Sep 2026 |
| 3 | Claude Fable 5 | Anthropic | 1505 | Highclaude-fable-5-high | Independent testIndependentLMArena ↗ | — | 30 Sep 2026 |
| 4 | Claude Opus 5.5 | Anthropic | 1504 | Highclaude-opus-5.5-high | Independent testIndependentLMArena ↗ | — | 30 Sep 2026 |
| 5 | Claude Opus 4.7 | Anthropic | 1502 | Highclaude-opus-4-7-high | Independent testIndependentLMArena ↗ | — | 30 Sep 2026 |
| 6 | Claude Fable 5.1 | Anthropic | 1501 | Maxclaude-fable-5.1-max | Independent testIndependentLMArena ↗ | — | 30 Sep 2026 |
| 7 | Muse Spark 1.3 | Meta (Meta Superintelligence Labs, Muse) | 1495 | Maxmuse-spark-1.3-max | Independent testIndependentLMArena ↗ | — | 30 Sep 2026 |
| 8 | Muse Spark 1.2 | Meta (Meta Superintelligence Labs, Muse) | 1494 | Extra highmuse-spark-1.2 (xHigh) | Independent testIndependentLMArena ↗ | — | 30 Sep 2026 |
| 9 | Gemini 3.8 Flash | Google (Gemini / DeepMind) | 1494 | Highgemini-3.8-flash-high | Independent testIndependentLMArena ↗ | — | 30 Sep 2026 |
| 10 | Muse Spark 1.1 | Meta (Meta Superintelligence Labs, Muse) | 1492 | Defaultmuse-spark-1.1 | Independent testIndependentLMArena ↗ | — | 30 Sep 2026 |
| 11 | Claude Opus 5 | Anthropic | 1491 | Highclaude-opus-5-high | Independent testIndependentLMArena ↗ | — | 30 Sep 2026 |
| 12 | Muse Spark | Meta (Meta Superintelligence Labs, Muse) | 1489 | Defaultmuse-spark | Independent testIndependentLMArena ↗ | — | 30 Sep 2026 |
| 13 | Gemini 3.7 Flash | Google (Gemini / DeepMind) | 1488 | Highgemini-3.7-flash-high | Independent testIndependentLMArena ↗ | — | 30 Sep 2026 |
| 14 | Kimi K3 | Moonshot AI (Kimi) | 1488 | Maxkimi-k3-max | Independent testIndependentLMArena ↗ | — | 30 Sep 2026 |
| 15 | Gemini 3.1 Pro (Preview) | Google (Gemini / DeepMind) | 1487 | Defaultgemini-3.1-pro-preview | Independent testIndependentLMArena ↗ | — | 30 Sep 2026 |
| 16 | Gemini 3 Pro | Google (Gemini / DeepMind) | 1486 | Defaultgemini-3-pro | Independent testIndependentLMArena ↗ | — | 30 Sep 2026 |
| 17 | GPT-5.6 Sol | OpenAI | 1484 | Extra highgpt-5.6-sol-xhigh | Independent testIndependentLMArena ↗ | — | 30 Sep 2026 |
| 18 | Gemini 3.6 Flash | Google (Gemini / DeepMind) | 1483 | Highgemini-3.6-flash-high | Independent testIndependentLMArena ↗ | — | 30 Sep 2026 |
| 19 | GPT-5.5 | OpenAI | 1481 | Highgpt-5.5-high | Independent testIndependentLMArena ↗ | — | 30 Sep 2026 |
| 20 | Claude Opus 4.8 | Anthropic | 1481 | Highclaude-opus-4-8-high | Independent testIndependentLMArena ↗ | — | 30 Sep 2026 |
| 21 | Qwen3.8 Max (0803) | Qwen (Alibaba) | 1481 | Defaultqwen3.8-max | Independent testIndependentLMArena ↗ | — | 30 Sep 2026 |
| 22 | MiMo-V2.6-Pro | Xiaomi MiMo | 1480 | Defaultmimo-v2.6-pro | Independent testIndependentLMArena ↗ | — | 30 Sep 2026 |
| 23 | GLM-5.3 | Z.ai (Zhipu) | 1479 | Maxglm-5.3-max | Independent testIndependentLMArena ↗ | — | 30 Sep 2026 |
| 24 | Gemini 3.5 Flash | Google (Gemini / DeepMind) | 1477 | Highgemini-3.5-flash-high | Independent testIndependentLMArena ↗ | — | 30 Sep 2026 |
| 25 | Gemma 4 31B IT | Google (Gemini / DeepMind) | 1452 | DefaultThinking | Maker's own figureVendor-reportedGoogle ↗ | — | 2 Apr 2026 |
| 26 | Gemma 4 26B A4B IT | Google (Gemini / DeepMind) | 1441 | DefaultThinking | Maker's own figureVendor-reportedGoogle ↗ | — | 2 Apr 2026 |