Model Tracker
Code Arena (WebDev) leaderboard
The models in the Model Tracker that Arena has measured on Code Arena (WebDev), ranked by the highest score of each: the name Arena gives it, the setting it ran and the day.
Em inglês
The models in the Model Tracker that Arena has measured on Code Arena (WebDev), ranked by the highest score of each: the name Arena gives it, the setting it ran and the day. Arena’s leaderboard dataset (lmarena-ai/leaderboard-dataset on Hugging Face), CC BY 4.0: ratings from people’s votes between two anonymous models, as Arena publishes them.
- 1. Claude Fable 5.2: 1,823 (1,807–1,839) — Claude Fable 5.2 (xHigh), xHigh, 19 November 2026
- 2. Claude Opus 5.5: 1,818 (1,807–1,829) — Claude Opus 5.5 (Max), Max, 19 November 2026
- 3. Claude Sonnet 5.5: 1,771 (1,762–1,781) — Claude Sonnet 5.5 (xHigh), xHigh, 19 November 2026
- 4. GPT-6 Astra: 1,763 (1,755–1,771) — GPT-6 Astra (Max), Max, 19 November 2026
- 5. Qwen4-Max: 1,750 (1,734–1,765) — Qwen4-Max (xHigh), xHigh, 19 November 2026
- 6. GPT-6.1 Sol: 1,744 (1,734–1,753) — GPT-6.1 Sol (Max), Max, 19 November 2026
- 7. Claude Fable 5.1: 1,741 (1,734–1,749) — Claude Fable 5.1 (Max), Max, 19 November 2026
- 8. Muse Wonder Full: 1,723 (1,709–1,738) — Muse Wonder Full (Max), Max, 19 November 2026
- 9. Claude Opus 5: 1,692 (1,686–1,698) — Claude Opus 5 (Max), Max, 19 November 2026
- 10. Gemini 4 Argon: 1,681 (1,672–1,690) — Gemini 4 Argon (High), High, 19 November 2026
- 11. GPT-6 Sol: 1,674 (1,666–1,682) — GPT-6 Sol (Max), Max, 19 November 2026
- 12. Qwen3.8-Max: 1,671 (1,659–1,683) — Qwen3.8-Max, 19 November 2026
- 13. Muse Wonder: 1,648 (1,639–1,656) — Muse Wonder (Max), Max, 19 November 2026
- 14. Grok 4.7: 1,638 (1,630–1,645) — Grok 4.7 (xHigh), xHigh, 19 November 2026
- 15. Qwen3.8-Flash-Next: 1,626 (1,619–1,633) — Qwen3.8-Flash-Next, 19 November 2026
- 16. Claude Fable 5: 1,626 (1,620–1,632) — Claude Fable 5 (High), High, 19 November 2026
- 17. Grok 4.6: 1,618 (1,611–1,625) — Grok 4.6 (High), High, 19 November 2026
- 18. Claude Haiku 5.5: 1,596 (1,588–1,604) — Claude Haiku 5.5 (High), High, 19 November 2026
- 19. Qwen3.8-27B: 1,589 (1,583–1,595) — Qwen3.8-27B, 19 November 2026
- 20. Gemini 3.7 Flash: 1,589 (1,582–1,595) — Gemini 3.7 Flash (High), High, 19 November 2026
- 21. Gemini 3.8 Flash: 1,584 (1,577–1,590) — Gemini 3.8 Flash (High), High, 19 November 2026
- 22. DeepSeek-V4-Flash: 1,582 (1,572–1,591) — DeepSeek-V4-Flash (High), High, 19 November 2026
- 23. GPT-6 Luna: 1,579 (1,573–1,585) — GPT-6 Luna (Max), Max, 19 November 2026
- 24. Mistral Large 4: 1,570 (1,557–1,582) — Mistral Large 4, 19 November 2026
- 25. Claude Opus 4.7: 1,557 (1,551–1,563) — Claude Opus 4.7 (High), High, 19 November 2026
- 26. Claude Opus 4.8: 1,555 (1,550–1,561) — Claude Opus 4.8 (High), High, 19 November 2026
- 27. Grok 4.5: 1,552 (1,546–1,559) — Grok 4.5, 19 November 2026
- 28. Claude Opus 4.6: 1,546 (1,541–1,552) — Claude Opus 4.6 (High), High, 19 November 2026
- 29. Claude Sonnet 5: 1,539 (1,534–1,545) — Claude Sonnet 5 (High), High, 19 November 2026
- 30. Gemini 3.6 Flash: 1,538 (1,530–1,545) — Gemini 3.6 Flash (High), High, 19 November 2026
- 31. Claude Sonnet 4.6: 1,522 (1,517–1,527) — Claude Sonnet 4.6, 19 November 2026
- 32. Gemini 3.5 Flash: 1,500 (1,492–1,507) — Gemini 3.5 Flash (High), High, 19 November 2026
- 33. DeepSeek V4 Pro: 1,448 (1,442–1,455) — DeepSeek-V4-Pro, 19 November 2026
- 34. Gemini 3 Pro: 1,441 (1,433–1,450) — Gemini 3 Pro, 19 November 2026
- 35. Gemini 3 Flash: 1,440 (1,431–1,449) — Gemini 3 Flash, 19 November 2026
- 36. Gemini 3.5 Flash-Lite: 1,432 (1,390–1,473) — Gemini 3.5 Flash-Lite, 19 November 2026
- 37. GPT-5.2: 1,419 (1,396–1,442) — GPT-5.2, 19 November 2026
- 38. GPT-5: 1,418 (1,402–1,433) — GPT-5 (Medium), Medium, 19 November 2026
- 39. GPT-5.4: 1,400 (1,390–1,410) — GPT-5.4, 19 November 2026
- 40. GPT-5.4 Mini: 1,398 (1,391–1,405) — GPT-5.4 mini (High), High, 19 November 2026
- 41. GPT-5.1: 1,397 (1,386–1,409) — GPT-5.1 (Medium), Medium, 19 November 2026
- 42. Qwen3.5-122B-A10B: 1,360 (1,352–1,368) — Qwen3.5-122B-A10B, 19 November 2026
- 43. Grok 4.3: 1,357 (1,351–1,364) — Grok 4.3, 19 November 2026
- 44. Qwen3.5-27B: 1,357 (1,349–1,365) — Qwen3.5-27B, 19 November 2026
- 45. GPT-5.2-Codex: 1,339 (1,330–1,348) — GPT-5.2-Codex, 19 November 2026
- 46. GPT-5.1-Codex: 1,338 (1,326–1,350) — GPT-5.1-Codex, 19 November 2026
- 47. DeepSeek-V3.2-Exp: 1,271 (1,258–1,285) — DeepSeek-V3.2-Exp, 19 November 2026
- 48. Mistral Medium 3.5: 1,263 (1,248–1,278) — Mistral Medium 3.5, 19 November 2026
- 49. Qwen3.5-35B-A3B: 1,253 (1,236–1,271) — Qwen3.5-35B-A3B, 19 November 2026
- 50. GPT-5.1-Codex Mini: 1,244 (1,221–1,266) — GPT-5.1-Codex-Mini, 19 November 2026
- 51. Grok 4.1 Fast: 1,242 (1,231–1,253) — Grok 4.1 Fast (Reasoning), Reasoning, 19 November 2026
- 52. Mistral Large 3: 1,233 (1,207–1,258) — Mistral Large 3, 19 November 2026
- 53. Gemini 2.5 Pro: 1,227 (1,211–1,242) — Gemini 2.5 Pro, 19 November 2026
- 54. Grok 4.1: 1,216 (1,191–1,241) — Grok 4.1 (Thinking), Thinking, 19 November 2026
- 55. Devstral 2: 1,196 (1,175–1,216) — Devstral 2, 19 November 2026
- 56. Grok Code Fast 1: 1,166 (1,137–1,194) — Grok Code Fast 1, 19 November 2026
- 57. Grok 4 Fast: 1,159 (1,132–1,186) — Grok 4 Fast (Reasoning), Reasoning, 19 November 2026
Arena: the benchmark and its data · CC BY 4.0