WebDev Leaderboard: Qwen4-Max (xHigh) enters the top 10, ranking at position 6 (new entry)

LMArena WebDev Leaderboard update for 2026-11-15: Qwen4-Max (xHigh) (Alibaba) ranks at position 6, was not on the previous list, with a score of 1749.8 and 1814 votes.

LMArena WebDev Leaderboard update for 2026-11-15: Qwen4-Max (xHigh) (Alibaba) ranks at position 6, was not on the previous list, with a score of 1749.8 and 1814 votes.

LMArena WebDev Leaderboard Rank 6 (not on previous list) · Score 1749.8 · 1814 votes

Leaderboard date: 2026-11-15 (previous period 2026-11-11)

Current Top 10

  1. Claude Fable 5.2 (xHigh) (Anthropic) 1826
  2. Claude Opus 5.5 (Max) (Anthropic) 1815.6
  3. Claude Sonnet 5.5 (xHigh) (Anthropic) 1772.2
  4. Gemini 4 Carbon (High) (Google) 1768.3
  5. GPT-6 Astra (Max) (OpenAI) 1762.9
  6. Qwen4-Max (xHigh) (Alibaba) 1749.8 ←
  7. Claude Fable 5.1 (Max) (Anthropic) 1742.9
  8. GPT-6.1 Sol (Max) (OpenAI) 1742.3
  9. Muse Wonder Full (Max) (Meta) 1723.9
  10. Claude Sonnet 5.5 (High) (Anthropic) 1715.8

Reasoning

  • New entries in the top 10, changes in rankings for domestic models (comparing datasets from releases on 2026-11-11 and 2026-11-15).

Risks

  • LMArena rankings are derived from user blind-test votes, reflecting only preferences for this type of conversational/generative task.

Open

LMArena 排行榜数据集

Explore the latest AI Radar updates