TestsBenchmarks · Human preference
LMArena Code Arena (WebDev)
Crowd-voted Elo from head-to-head comparisons of models building web apps agentically in Code Arena.
Measured by independent testersIndependent Reported by the makerVendor-reported
| Thinking levelSetting | |||||||
|---|---|---|---|---|---|---|---|
| 1 | Claude Opus 5.5 | Anthropic | 1818 | Maxclaude-opus-5.5-max | Independent testIndependentLMArena ↗ | — | 30 Sep 2026 |
| 2 | GPT-6 Astra | OpenAI | 1789 | Maxgpt-6-astra-max | Independent testIndependentLMArena ↗ | — | 30 Sep 2026 |
| 3 | GPT-6.1 Sol | OpenAI | 1759 | Maxgpt-6.1-sol-max | Independent testIndependentLMArena ↗ | — | 30 Sep 2026 |
| 4 | Claude Fable 5.1 | Anthropic | 1751 | Maxclaude-fable-5.1-max | Independent testIndependentLMArena ↗ | — | 30 Sep 2026 |
| 5 | Claude Sonnet 5.5 | Anthropic | 1709 | Highclaude-sonnet-5.5-high | Independent testIndependentLMArena ↗ | — | 30 Sep 2026 |
| 6 | Claude Opus 5 | Anthropic | 1694 | Maxclaude-opus-5-max | Independent testIndependentLMArena ↗ | — | 30 Sep 2026 |
| 7 | GPT-6 Sol | OpenAI | 1689 | Maxgpt-6-sol-max | Independent testIndependentLMArena ↗ | — | 30 Sep 2026 |
| 8 | Gemini 4 Argon | Google (Gemini / DeepMind) | 1679 | Highgemini-4-argon-high | Independent testIndependentLMArena ↗ | — | 30 Sep 2026 |
| 9 | Qwen3.8 Max (0803) | Qwen (Alibaba) | 1671 | Defaultqwen3.8-max | Independent testIndependentLMArena ↗ | — | 30 Sep 2026 |
| 10 | Qwen3.8 Max (0902) | Qwen (Alibaba) | 1670 | Defaultqwen3.8-max-0902 | Independent testIndependentLMArena ↗ | — | 30 Sep 2026 |
| 11 | Kimi K3 | Moonshot AI (Kimi) | 1658 | Maxkimi-k3-max | Independent testIndependentLMArena ↗ | — | 30 Sep 2026 |
| 12 | Muse Spark 1.3 | Meta (Meta Superintelligence Labs, Muse) | 1655 | Maxmuse-spark-1.3-max | Independent testIndependentLMArena ↗ | — | 30 Sep 2026 |
| 13 | Qwen3.8-Flash-Next | Qwen (Alibaba) | 1638 | Defaultqwen3.8-flash-next | Independent testIndependentLMArena ↗ | — | 30 Sep 2026 |
| 14 | Grok 4.7 | SpaceXAI (formerly xAI) | 1636 | Extra highgrok-4.7-xhigh | Independent testIndependentLMArena ↗ | — | 30 Sep 2026 |
| 15 | Hy4 preview | Tencent Hunyuan | 1633 | Defaulthy4-preview | Independent testIndependentLMArena ↗ | — | 30 Sep 2026 |
| 16 | Claude Fable 5 | Anthropic | 1626 | Highclaude-fable-5-high | Independent testIndependentLMArena ↗ | — | 30 Sep 2026 |
| 17 | GLM-5.3 | Z.ai (Zhipu) | 1622 | Maxglm-5.3-max | Independent testIndependentLMArena ↗ | — | 30 Sep 2026 |
| 18 | Grok 4.6 | SpaceXAI (formerly xAI) | 1620 | Highgrok-4.6-high | Independent testIndependentLMArena ↗ | — | 30 Sep 2026 |
| 19 | DeepSeek V4.1 Flash | DeepSeek | 1620 | Maxdeepseek-v4.1-flash-max | Independent testIndependentLMArena ↗ | — | 30 Sep 2026 |
| 20 | GPT-5.6 Sol | OpenAI | 1619 | Extra highgpt-5.6-sol-xhigh | Independent testIndependentLMArena ↗ | Codex | 30 Sep 2026 |
| 21 | MiMo-V2.6-Pro | Xiaomi MiMo | 1619 | Defaultmimo-v2.6-pro | Independent testIndependentLMArena ↗ | — | 30 Sep 2026 |
| 22 | GLM-5.3-Flash | Z.ai (Zhipu) | 1615 | Defaultglm-5.3-flash | Independent testIndependentLMArena ↗ | — | 30 Sep 2026 |
| 23 | GLM-5.2 | Z.ai (Zhipu) | 1605 | Maxglm-5.2-max | Independent testIndependentLMArena ↗ | — | 30 Sep 2026 |
| 24 | Gemini 3.7 Flash | Google (Gemini / DeepMind) | 1592 | Highgemini-3.7-flash-high | Independent testIndependentLMArena ↗ | — | 30 Sep 2026 |
| 25 | Qwen3.8 27B | Qwen (Alibaba) | 1590 | Defaultqwen3.8-27b | Independent testIndependentLMArena ↗ | — | 30 Sep 2026 |
| 26 | Gemini 3.8 Flash | Google (Gemini / DeepMind) | 1583 | Highgemini-3.8-flash-high | Independent testIndependentLMArena ↗ | — | 30 Sep 2026 |
| 27 | Gemini 3.6 Flash | Google (Gemini / DeepMind) | 1538 | Defaultdefault settings (API default thinking_level=medium) | Maker's own figureVendor-reportedGoogle ↗ | — | 13 Aug 2026 |