TestsBenchmarks · Human preference
LMArena Text - Expert
Crowd-voted, style-controlled Elo on expert-level prompts (deep domain knowledge questions).
Elo ratingHigher is betterCounts toward:Weights: Research & analysis ×0.6The test's websiteOfficial page ↗
Measured by independent testersIndependent Reported by the makerVendor-reported
| Thinking levelSetting | |||||||
|---|---|---|---|---|---|---|---|
| 1 | Claude Fable 5 | Anthropic | 1549 | Highclaude-fable-5-high | Independent testIndependentLMArena ↗ | — | 30 Sep 2026 |
| 2 | Claude Opus 4.6 | Anthropic | 1547 | Highclaude-opus-4-6-high | Independent testIndependentLMArena ↗ | — | 30 Sep 2026 |
| 3 | Claude Opus 5 | Anthropic | 1542 | Highclaude-opus-5-high | Independent testIndependentLMArena ↗ | — | 30 Sep 2026 |
| 4 | Claude Opus 5.5 | Anthropic | 1539 | Highclaude-opus-5.5-high | Independent testIndependentLMArena ↗ | — | 30 Sep 2026 |
| 5 | Gemini 4 Argon | Google (Gemini / DeepMind) | 1538 | Highgemini-4-argon-high | Independent testIndependentLMArena ↗ | — | 30 Sep 2026 |
| 6 | GPT-5.6 Sol | OpenAI | 1535 | Extra highgpt-5.6-sol-xhigh | Independent testIndependentLMArena ↗ | — | 30 Sep 2026 |
| 7 | Claude Opus 4.7 | Anthropic | 1534 | Defaultclaude-opus-4-7 | Independent testIndependentLMArena ↗ | — | 30 Sep 2026 |
| 8 | Kimi K3 | Moonshot AI (Kimi) | 1533 | Maxkimi-k3-max | Independent testIndependentLMArena ↗ | — | 30 Sep 2026 |
| 9 | MiMo-V2.6-Pro | Xiaomi MiMo | 1532 | Defaultmimo-v2.6-pro | Independent testIndependentLMArena ↗ | — | 30 Sep 2026 |
| 10 | Muse Spark 1.3 | Meta (Meta Superintelligence Labs, Muse) | 1528 | Maxmuse-spark-1.3-max | Independent testIndependentLMArena ↗ | — | 30 Sep 2026 |
| 11 | Claude Opus 4.8 | Anthropic | 1525 | Highclaude-opus-4-8-high | Independent testIndependentLMArena ↗ | — | 30 Sep 2026 |
| 12 | Gemini 3.8 Flash | Google (Gemini / DeepMind) | 1525 | Highgemini-3.8-flash-high | Independent testIndependentLMArena ↗ | — | 30 Sep 2026 |
| 13 | Claude Fable 5.1 | Anthropic | 1519 | Maxclaude-fable-5.1-max | Independent testIndependentLMArena ↗ | — | 30 Sep 2026 |
| 14 | GLM-5.3 | Z.ai (Zhipu) | 1519 | Maxglm-5.3-max | Independent testIndependentLMArena ↗ | — | 30 Sep 2026 |
| 15 | GPT-5.4 | OpenAI | 1515 | Highgpt-5.4-high | Independent testIndependentLMArena ↗ | — | 30 Sep 2026 |
| 16 | MiMo-V2.6-Flash | Xiaomi MiMo | 1514 | Defaultmimo-v2.6-flash | Independent testIndependentLMArena ↗ | — | 30 Sep 2026 |
| 17 | GPT-6 Astra | OpenAI | 1513 | Maxgpt-6-astra-max | Independent testIndependentLMArena ↗ | — | 30 Sep 2026 |
| 18 | Claude Sonnet 5 | Anthropic | 1512 | Highclaude-sonnet-5-high | Independent testIndependentLMArena ↗ | — | 30 Sep 2026 |
| 19 | Qwen3.8 Max (0803) | Qwen (Alibaba) | 1512 | Defaultqwen3.8-max | Independent testIndependentLMArena ↗ | — | 30 Sep 2026 |
| 20 | DeepSeek V4.1 Flash | DeepSeek | 1511 | Maxdeepseek-v4.1-flash-max | Independent testIndependentLMArena ↗ | — | 30 Sep 2026 |
| 21 | GPT-6 Sol | OpenAI | 1498 | Maxgpt-6-sol-max | Independent testIndependentLMArena ↗ | — | 30 Sep 2026 |
| 22 | GPT-6 Luna | OpenAI | 1498 | Maxgpt-6-luna-max | Independent testIndependentLMArena ↗ | — | 30 Sep 2026 |
| 23 | DeepSeek V4 Pro (0813) | DeepSeek | 1484 | Highdeepseek-v4-pro-high-20260813 | Independent testIndependentLMArena ↗ | — | 30 Sep 2026 |
| 24 | Grok 4.7 | SpaceXAI (formerly xAI) | 1459 | Extra highgrok-4.7-xhigh | Independent testIndependentLMArena ↗ | — | 30 Sep 2026 |