Model Tracker
Text Arena leaderboard
The models in the Model Tracker that Arena has measured on Text Arena, ranked by the highest score of each: the name Arena gives it, the setting it ran and the day.
Auf Englisch
The models in the Model Tracker that Arena has measured on Text Arena, 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. Gemini 4 Argon: 1,520 (1,515–1,525) — Gemini 4 Argon (High), High, 19 November 2026
- 2. Muse Wonder: 1,511 (1,506–1,517) — Muse Wonder (Max), Max, 19 November 2026
- 3. Claude Opus 5.5: 1,506 (1,500–1,512) — Claude Opus 5.5 (High), High, 19 November 2026
- 4. Claude Fable 5: 1,504 (1,500–1,508) — Claude Fable 5 (High), High, 19 November 2026
- 5. Claude Fable 5.2: 1,503 (1,494–1,512) — Claude Fable 5.2 (Max), Max, 19 November 2026
- 6. Claude Opus 4.6: 1,503 (1,500–1,506) — Claude Opus 4.6 (High), High, 19 November 2026
- 7. Claude Fable 5.1: 1,503 (1,497–1,508) — Claude Fable 5.1 (Max), Max, 19 November 2026
- 8. Claude Opus 4.7: 1,501 (1,497–1,505) — Claude Opus 4.7 (High), High, 19 November 2026
- 9. Gemini 3.8 Flash: 1,497 (1,493–1,501) — Gemini 3.8 Flash (High), High, 19 November 2026
- 10. Gemini 3.7 Flash: 1,490 (1,485–1,495) — Gemini 3.7 Flash (High), High, 19 November 2026
- 11. Claude Opus 5: 1,490 (1,486–1,493) — Claude Opus 5 (High), High, 19 November 2026
- 12. Muse Spark: 1,489 (1,484–1,495) — Muse Spark, 19 November 2026
- 13. Gemini 3 Pro: 1,486 (1,482–1,489) — Gemini 3 Pro, 19 November 2026
- 14. GPT-5.6 Sol: 1,485 (1,481–1,489) — GPT-5.6 Sol (xHigh), xHigh, 19 November 2026
- 15. Qwen3.8-Max: 1,484 (1,480–1,488) — Qwen3.8-Max, 19 November 2026
- 16. Gemini 3.6 Flash: 1,483 (1,478–1,487) — Gemini 3.6 Flash (High), High, 19 November 2026
- 17. GPT-6.1 Sol: 1,483 (1,477–1,489) — GPT-6.1 Sol (Max), Max, 19 November 2026
- 18. Claude Opus 4.8: 1,482 (1,478–1,486) — Claude Opus 4.8 (High), High, 19 November 2026
- 19. GPT-5.5: 1,481 (1,477–1,485) — GPT-5.5 (High), High, 19 November 2026
- 20. Gemini 3.5 Flash: 1,479 (1,475–1,482) — Gemini 3.5 Flash (High), High, 19 November 2026
- 21. GPT-6 Astra: 1,475 (1,470–1,481) — GPT-6 Astra (Max), Max, 19 November 2026
- 22. GPT-5.4: 1,475 (1,471–1,479) — GPT-5.4 (High), High, 19 November 2026
- 23. Claude Sonnet 5.5: 1,473 (1,468–1,479) — Claude Sonnet 5.5 (xHigh), xHigh, 19 November 2026
- 24. Gemini 3 Flash: 1,473 (1,469–1,477) — Gemini 3 Flash, 19 November 2026
- 25. Claude Sonnet 4.6: 1,472 (1,468–1,475) — Claude Sonnet 4.6, 19 November 2026
- 26. GPT-5.6 Terra: 1,468 (1,464–1,472) — GPT-5.6 Terra (xHigh), xHigh, 19 November 2026
- 27. Grok 4.5: 1,466 (1,461–1,470) — Grok 4.5, 19 November 2026
- 28. Grok 4.1: 1,465 (1,462–1,469) — Grok 4.1 (Thinking), Thinking, 19 November 2026
- 29. Claude Sonnet 5: 1,461 (1,457–1,465) — Claude Sonnet 5 (High), High, 19 November 2026
- 30. GPT-6 Sol: 1,458 (1,453–1,463) — GPT-6 Sol (Max), Max, 19 November 2026
- 31. DeepSeek V4 Pro: 1,458 (1,454–1,462) — DeepSeek-V4-Pro, 19 November 2026
- 32. Grok 4.6: 1,457 (1,452–1,461) — Grok 4.6 (High), High, 19 November 2026
- 33. GPT-5.1: 1,456 (1,452–1,459) — GPT-5.1 (High), High, 19 November 2026
- 34. Gemini 3.5 Flash-Lite: 1,455 (1,451–1,460) — Gemini 3.5 Flash-Lite, 19 November 2026
- 35. GPT-5.6 Luna: 1,453 (1,449–1,457) — GPT-5.6 Luna (xHigh), xHigh, 19 November 2026
- 36. GPT-5.3 Chat: 1,450 (1,446–1,455) — GPT-5.3 Chat, 19 November 2026
- 37. GPT-5.4 Mini: 1,447 (1,443–1,451) — GPT-5.4 mini (High), High, 19 November 2026
- 38. Gemini 2.5 Pro: 1,445 (1,443–1,448) — Gemini 2.5 Pro, 19 November 2026
- 39. Grok 4.7: 1,443 (1,438–1,448) — Grok 4.7 (xHigh), xHigh, 19 November 2026
- 40. GPT-6 Luna: 1,443 (1,439–1,447) — GPT-6 Luna (Max), Max, 19 November 2026
- 41. Grok 4.3: 1,442 (1,438–1,445) — Grok 4.3, 19 November 2026
- 42. GPT-5.2: 1,437 (1,434–1,441) — GPT-5.2 (High), High, 19 November 2026
- 43. DeepSeek-V4-Flash: 1,436 (1,432–1,440) — DeepSeek-V4-Flash, 19 November 2026
- 44. GPT-5: 1,435 (1,431–1,440) — GPT-5 (High), High, 19 November 2026
- 45. Qwen3.8-27B: 1,435 (1,430–1,439) — Qwen3.8-27B, 19 November 2026
- 46. Grok 4.1 Fast: 1,431 (1,427–1,434) — Grok 4.1 Fast (Reasoning), Reasoning, 19 November 2026
- 47. GPT-5 Chat: 1,427 (1,422–1,431) — GPT-5 Chat, 19 November 2026
- 48. Mistral Medium 3.5: 1,426 (1,420–1,433) — Mistral Medium 3.5, 19 November 2026
- 49. DeepSeek-V3.2-Exp: 1,425 (1,418–1,432) — DeepSeek-V3.2-Exp (Thinking), Thinking, 19 November 2026
- 50. Mistral Large 4: 1,423 (1,415–1,430) — Mistral Large 4, 19 November 2026
- 51. Claude Haiku 5.5: 1,421 (1,415–1,427) — Claude Haiku 5.5 (High), High, 19 November 2026
- 52. Grok 4 Fast: 1,418 (1,411–1,426) — Grok 4 Fast (Non-Reasoning), Non-Reasoning, 19 November 2026
- 53. DeepSeek-V3.1: 1,417 (1,411–1,423) — DeepSeek-V3.1, 19 November 2026
- 54. Qwen3.5-122B-A10B: 1,416 (1,412–1,421) — Qwen3.5-122B-A10B, 19 November 2026
- 55. DeepSeek-V3.1-Terminus: 1,416 (1,406–1,426) — DeepSeek-V3.1-Terminus (Thinking), Thinking, 19 November 2026
- 56. Mistral Large 3: 1,415 (1,412–1,417) — Mistral Large 3, 19 November 2026
- 57. Gemini 2.5 Flash: 1,409 (1,407–1,412) — Gemini 2.5 Flash, 19 November 2026
- 58. Qwen3.5-27B: 1,408 (1,404–1,413) — Qwen3.5-27B, 19 November 2026
- 59. GPT-5.4 nano: 1,401 (1,397–1,405) — GPT-5.4 nano (High), High, 19 November 2026
- 60. DeepSeek-R1: 1,398 (1,393–1,403) — DeepSeek-R1, 19 November 2026
- 61. Qwen3.5-35B-A3B: 1,394 (1,390–1,398) — Qwen3.5-35B-A3B, 19 November 2026
- 62. GPT-5 Mini: 1,390 (1,386–1,395) — GPT-5 mini (High), High, 19 November 2026
- 63. o1-preview: 1,389 (1,384–1,394) — o1-preview, 19 November 2026
- 64. Qwen3-235B-A22B: 1,375 (1,370–1,380) — Qwen3-235B-A22B, 19 November 2026
- 65. Grok 3 mini: 1,364 (1,358–1,369) — Grok 3 Mini (High), High, 19 November 2026
- 66. o3-mini: 1,364 (1,358–1,369) — o3-mini (High), High, 19 November 2026
- 67. DeepSeek-V3: 1,358 (1,354–1,363) — DeepSeek-V3, 19 November 2026
- 68. gpt-oss-120b: 1,352 (1,347–1,356) — gpt-oss-120b, 19 November 2026
- 69. Qwen3-32B: 1,347 (1,337–1,356) — Qwen3-32B, 19 November 2026
- 70. GPT-5 nano: 1,338 (1,331–1,345) — GPT-5 nano (High), High, 19 November 2026
- 71. o1-mini: 1,337 (1,333–1,340) — o1-mini, 19 November 2026
- 72. Qwen3-30B-A3B: 1,326 (1,322–1,331) — Qwen3-30B-A3B, 19 November 2026
- 73. gpt-oss-20b: 1,317 (1,311–1,324) — gpt-oss-20b, 19 November 2026
- 74. DeepSeek-V2.5: 1,307 (1,302–1,312) — DeepSeek-V2.5, 19 November 2026
- 75. Aya Expanse 32B: 1,267 (1,262–1,272) — Aya Expanse 32B, 19 November 2026
- 76. DeepSeek-Coder-V2: 1,266 (1,259–1,272) — DeepSeek-Coder-V2, 19 November 2026
- 77. Command R: 1,227 (1,222–1,232) — Command R, 19 November 2026
- 78. Aya Expanse 8B: 1,223 (1,216–1,230) — Aya Expanse 8B, 19 November 2026
- 79. Phi-3-small-8k-instruct: 1,171 (1,165–1,177) — Phi-3 Small 8K Instruct, 19 November 2026
- 80. Phi-3-mini-4k-instruct: 1,143 (1,137–1,150) — Phi-3 Mini 4K Instruct (June 2024), 19 November 2026
Arena: the benchmark and its data · CC BY 4.0