TestsBenchmarks · Human preference
LMArena Text - Instruction Following
Crowd-voted, style-controlled Elo on prompts with explicit constraints/instructions.
Elo ratingHigher is betterCounts toward:Weights: Writing & creativity ×0.6The test's websiteOfficial page ↗
Measured by independent testersIndependent Reported by the makerVendor-reported
| Thinking levelSetting | |||||||
|---|---|---|---|---|---|---|---|
| 1 | Gemini 4 Argon | Google (Gemini / DeepMind) | 1529 | Highgemini-4-argon-high | Independent testIndependentLMArena ↗ | — | 30 Sep 2026 |
| 2 | Claude Opus 5.5 | Anthropic | 1514 | Highclaude-opus-5.5-high | Independent testIndependentLMArena ↗ | — | 30 Sep 2026 |
| 3 | Claude Opus 4.6 | Anthropic | 1514 | Highclaude-opus-4-6-high | Independent testIndependentLMArena ↗ | — | 30 Sep 2026 |
| 4 | Claude Fable 5 | Anthropic | 1510 | Highclaude-fable-5-high | Independent testIndependentLMArena ↗ | — | 30 Sep 2026 |
| 5 | Claude Opus 4.7 | Anthropic | 1503 | Highclaude-opus-4-7-high | Independent testIndependentLMArena ↗ | — | 30 Sep 2026 |
| 6 | Claude Fable 5.1 | Anthropic | 1498 | Maxclaude-fable-5.1-max | Independent testIndependentLMArena ↗ | — | 30 Sep 2026 |
| 7 | Claude Opus 5 | Anthropic | 1497 | Highclaude-opus-5-high | Independent testIndependentLMArena ↗ | — | 30 Sep 2026 |
| 8 | GPT-5.6 Sol | OpenAI | 1491 | Extra highgpt-5.6-sol-xhigh | Independent testIndependentLMArena ↗ | — | 30 Sep 2026 |
| 9 | Claude Opus 4.8 | Anthropic | 1490 | Highclaude-opus-4-8-high | Independent testIndependentLMArena ↗ | — | 30 Sep 2026 |
| 10 | Kimi K3 | Moonshot AI (Kimi) | 1487 | Maxkimi-k3-max | Independent testIndependentLMArena ↗ | — | 30 Sep 2026 |
| 11 | Gemini 3.8 Flash | Google (Gemini / DeepMind) | 1487 | Highgemini-3.8-flash-high | Independent testIndependentLMArena ↗ | — | 30 Sep 2026 |
| 12 | Muse Spark 1.3 | Meta (Meta Superintelligence Labs, Muse) | 1486 | Maxmuse-spark-1.3-max | Independent testIndependentLMArena ↗ | — | 30 Sep 2026 |
| 13 | Gemini 3.7 Flash | Google (Gemini / DeepMind) | 1486 | Highgemini-3.7-flash-high | Independent testIndependentLMArena ↗ | — | 30 Sep 2026 |
| 14 | Claude Opus 4.5 | Anthropic | 1483 | Highclaude-opus-4-5-20251101-high-32k | Independent testIndependentLMArena ↗ | — | 30 Sep 2026 |
| 15 | Gemini 3.1 Pro (Preview) | Google (Gemini / DeepMind) | 1479 | Defaultgemini-3.1-pro-preview | Independent testIndependentLMArena ↗ | — | 30 Sep 2026 |
| 16 | DeepSeek V4.1 Flash | DeepSeek | 1478 | Maxdeepseek-v4.1-flash-max | Independent testIndependentLMArena ↗ | — | 30 Sep 2026 |
| 17 | GLM-5.3 | Z.ai (Zhipu) | 1478 | Maxglm-5.3-max | Independent testIndependentLMArena ↗ | — | 30 Sep 2026 |
| 18 | MiMo-V2.6-Pro | Xiaomi MiMo | 1473 | Defaultmimo-v2.6-pro | Independent testIndependentLMArena ↗ | — | 30 Sep 2026 |
| 19 | GPT-6 Astra | OpenAI | 1473 | Maxgpt-6-astra-max | Independent testIndependentLMArena ↗ | — | 30 Sep 2026 |
| 20 | Qwen3.8 Max (0803) | Qwen (Alibaba) | 1473 | Defaultqwen3.8-max | Independent testIndependentLMArena ↗ | — | 30 Sep 2026 |
| 21 | Claude Sonnet 5 | Anthropic | 1467 | Highclaude-sonnet-5-high | Independent testIndependentLMArena ↗ | — | 30 Sep 2026 |
| 22 | DeepSeek V4 Pro (0813) | DeepSeek | 1461 | Highdeepseek-v4-pro-high-20260813 | Independent testIndependentLMArena ↗ | — | 30 Sep 2026 |
| 23 | GPT-6 Sol | OpenAI | 1453 | Maxgpt-6-sol-max | Independent testIndependentLMArena ↗ | — | 30 Sep 2026 |
| 24 | GPT-6 Luna | OpenAI | 1449 | Maxgpt-6-luna-max | Independent testIndependentLMArena ↗ | — | 30 Sep 2026 |
| 25 | Grok 4.7 | SpaceXAI (formerly xAI) | 1442 | Extra highgrok-4.7-xhigh | Independent testIndependentLMArena ↗ | — | 30 Sep 2026 |