Skip to content

Model rank

Arena text preference

378 models ranked by arena text style controlled rating.
Recorded Jul 21, 2026Source: LMArenaHow this board is measuredCSV / JSON

1,507.3 arena_score

claude-fable-5 ranks first

Arena text style controlled rating

378

Models ranked

Jul 21

Snapshot recorded

2026

Follow changes

All 378 models by arena text style controlled rating

claude-fable-5 leads at 1,507.3 arena_score; the middle of the board sits at 1,347.

Ahead of second place
2.5
Held by the top three
1%
Middle of the board
1,347
Highest 1,507.3 arena_scoreMiddle 1,347
1. claude-fable-5: 1,507.3 arena_score2. claude-opus-4-6-thinking: 1,504.837 arena_score3. claude-opus-4-7-thinking: 1,502.043 arena_score4. claude-opus-4-6: 1,497.759 arena_score5. muse-spark-1.1: 1,495.059 arena_score6. claude-opus-4-7: 1,493.665 arena_score7. muse-spark: 1,487.549 arena_score8. gemini-3.1-pro-preview: 1,485.814 arena_score9. gemini-3-pro: 1,485.737 arena_score10. kimi-k3: 1,485.657 arena_score11. gpt-5.6-sol-xhigh: 1,485.073 arena_score12. gemini-3.6-flash: 1,485.03 arena_score13. claude-opus-4-8-thinking: 1,483.583 arena_score14. gpt-5.5-high: 1,481.726 arena_score15. gpt-5.4-high: 1,477.787 arena_score16. gpt-5.5: 1,476.323 arena_score17. gemini-3.5-flash-high: 1,476.261 arena_score18. gpt-5.2-chat-latest-20260210: 1,475.702 arena_score19. qwen3.7-max-preview: 1,475.151 arena_score20. grok-4.20-beta1: 1,474.331 arena_score21. gemini-3.5-flash-medium: 1,474.327 arena_score22. claude-opus-4-8: 1,473.432 arena_score23. gpt-5.5-instant: 1,473.321 arena_score24. grok-4.20-beta-0309-reasoning: 1,473.176 arena_score25. gemini-3-flash: 1,473.136 arena_score26. claude-opus-4-5-20251101-thinking-32k: 1,472.872 arena_score27. claude-sonnet-4-6: 1,472.544 arena_score28. grok-4.20-multi-agent-beta-0309: 1,470.927 arena_score29. glm-5.1: 1,469.645 arena_score30. glm-5.2 (max): 1,469.199 arena_score31. claude-opus-4-5-20251101: 1,469.122 arena_score32. ernie-5.1: 1,467.724 arena_score33. grok-4.5: 1,467.72 arena_score34. mimo-v2.5-pro: 1,466.835 arena_score35. gpt-5.4: 1,466.259 arena_score36. grok-4.1-thinking: 1,465.901 arena_score37. qwen3.5-max-preview: 1,464.799 arena_score38. claude-sonnet-5-high: 1,461.148 arena_score39. kimi-k2.6: 1,460.911 arena_score40. qwen3.6-max-preview: 1,460.103 arena_score41. qwen3.7-plus: 1,459.81 arena_score42. grok-4.1: 1,459.455 arena_score43. gemini-3.5-flash-lite: 1,459.103 arena_score44. gemini-3-flash (thinking-minimal): 1,458.629 arena_score45. glm-5: 1,456.662 arena_score46. deepseek-v4-pro: 1,456.612 arena_score47. claude-sonnet-4-5-20250929-thinking-32k: 1,455.577 arena_score48. dola-seed-2.0-pro: 1,455.414 arena_score49. deepseek-v4-pro-thinking: 1,455.205 arena_score50. claude-sonnet-4-5-20250929: 1,455.123 arena_score51. gpt-5.1-high: 1,454.631 arena_score52. gemma-4-31b: 1,450.846 arena_score53. kimi-k2.5-thinking: 1,449.686 arena_score54. gpt-5.4-mini-high: 1,449.179 arena_score55. claude-opus-4-1-20250805-thinking-16k: 1,449.066 arena_score56. ernie-5.0-preview-1203: 1,448.864 arena_score57. gpt-5.3-chat-latest: 1,448.83 arena_score58. mimo-v2-pro: 1,448.339 arena_score59. claude-opus-4-1-20250805: 1,447.034 arena_score60. ernie-5.0-0110: 1,446.887 arena_score61. gemini-2.5-pro: 1,445.566 arena_score62. inkling: 1,444.914 arena_score63. gpt-4.5-preview-2025-02-27: 1,444.691 arena_score64. minimax-m3: 1,444.192 arena_score65. qwen3.6-plus: 1,443.823 arena_score66. chatgpt-4o-latest-20250326: 1,443.152 arena_score67. qwen3.5-397b-a17b: 1,442.154 arena_score68. glm-4.7: 1,442.027 arena_score69. grok-4.3: 1,442.019 arena_score70. deepseek-v4-flash-thinking: 1,438.855 arena_score71. gpt-5.1: 1,438.631 arena_score72. gemma-4-26b-a4b: 1,438.097 arena_score73. gpt-5.2-high: 1,437.401 arena_score74. glm-5v-turbo: 1,436.741 arena_score75. longcat-flash-chat-2602-exp: 1,435.748 arena_score76. deepseek-v4-flash: 1,435.503 arena_score77. qwen3-max-preview: 1,434.779 arena_score78. gpt-5.2: 1,434.405 arena_score79. gpt-5-high: 1,433.804 arena_score80. mimo-v2.5: 1,432.992 arena_score81. gemini-3.1-flash-lite-preview: 1,431.896 arena_score82. kimi-k2.5-instant: 1,431.44 arena_score83. grok-4-1-fast-reasoning: 1,430.989 arena_score84. o3-2025-04-16: 1,430.803 arena_score85. mimo-v2-omni: 1,429.864 arena_score86. kimi-k2-thinking-turbo: 1,429.74 arena_score87. mistral-medium-3.5: 1,427.421 arena_score88. amazon-nova-experimental-chat-26-02-10: 1,426.884 arena_score89. gpt-5-chat: 1,426.753 arena_score90. nvidia-nemotron-3-ultra-550b-a55b-nvfp4: 1,425.247 arena_score91. glm-4.6: 1,425.154 arena_score92. deepseek-v3.2: 1,424.923 arena_score93. deepseek-v3.2-exp-thinking: 1,424.721 arena_score94. claude-opus-4-20250514-thinking-16k: 1,424.496 arena_score95. qwen3-max-2025-09-23: 1,424.099 arena_score96. qwen3-235b-a22b-instruct-2507: 1,423.168 arena_score97. deepseek-v3.2-thinking: 1,422.937 arena_score98. deepseek-v3.2-exp: 1,422.677 arena_score99. deepseek-r1-0528: 1,422.061 arena_score100. grok-4-fast-chat: 1,420.772 arena_score101. ernie-5.0-preview-1022: 1,418.52 arena_score102. kimi-k2-0905-preview: 1,417.887 arena_score103. deepseek-v3.1: 1,417.486 arena_score104. kimi-k2-0711-preview: 1,417.465 arena_score105. qwen3.5-122b-a10b: 1,417.303 arena_score106. deepseek-v3.1-terminus-thinking: 1,417.244 arena_score107. deepseek-v3.1-thinking: 1,417.04 arena_score108. minimax-m2.7: 1,416.749 arena_score109. amazon-nova-experimental-chat-26-01-10: 1,415.479 arena_score110. mistral-large-3: 1,415.386 arena_score111. deepseek-v3.1-terminus: 1,415.28 arena_score112. qwen3-vl-235b-a22b-instruct: 1,415.268 arena_score113. gpt-4.1-2025-04-14: 1,413.698 arena_score114. claude-opus-4-20250514: 1,412.502 arena_score115. claude-haiku-4-5-20251001: 1,412.202 arena_score116. hunyuan-hy3-preview: 1,412.115 arena_score117. grok-3-preview-02-24: 1,411.544 arena_score118. glm-4.5: 1,410.925 arena_score119. gemini-2.5-flash: 1,410.159 arena_score120. mistral-medium-2508: 1,409.574 arena_score121. grok-4-0709: 1,409.508 arena_score122. qwen3.5-27b: 1,408.63 arena_score123. gemini-2.5-flash-preview-09-2025: 1,404.152 arena_score124. grok-4-fast-reasoning: 1,404.112 arena_score125. gpt-5.4-nano-high: 1,403.64 arena_score126. qwen3-235b-a22b-no-thinking: 1,403.009 arena_score127. o1-2024-12-17: 1,402.053 arena_score128. qwen3-next-80b-a3b-instruct: 1,401.192 arena_score129. longcat-flash-chat: 1,401.142 arena_score130. claude-sonnet-4-20250514-thinking-32k: 1,399.182 arena_score131. qwen3-235b-a22b-thinking-2507: 1,399.125 arena_score132. deepseek-r1: 1,398.137 arena_score133. qwen3.5-flash: 1,397.094 arena_score134. qwen3.5-35b-a3b: 1,395.748 arena_score135. deepseek-v3-0324: 1,395.598 arena_score136. qwen3-vl-235b-a22b-thinking: 1,395.205 arena_score137. hunyuan-vision-1.5-thinking: 1,395.18 arena_score138. step-3.5-flash: 1,395.122 arena_score139. amazon-nova-experimental-chat-12-10: 1,394.098 arena_score140. mimo-v2-flash (non-thinking): 1,392.824 arena_score141. minimax-m2.5: 1,390.474 arena_score142. gpt-5-mini-high: 1,389.979 arena_score143. o4-mini-2025-04-16: 1,389.894 arena_score144. claude-sonnet-4-20250514: 1,389.046 arena_score145. o1-preview: 1,388.394 arena_score146. qwen3-coder-480b-a35b-instruct: 1,387.523 arena_score147. claude-3-7-sonnet-20250219-thinking-32k: 1,387.348 arena_score148. mimo-v2-flash (thinking): 1,387.092 arena_score149. mistral-medium-2505: 1,386.869 arena_score150. hunyuan-t1-20250711: 1,386.77 arena_score151. minimax-m2.1-preview: 1,384.059 arena_score152. qwen3-30b-a3b-instruct-2507: 1,383.109 arena_score153. gpt-4.1-mini-2025-04-14: 1,382.761 arena_score154. hunyuan-turbos-20250416: 1,382.241 arena_score155. gemini-2.5-flash-lite-preview-09-2025-no-thinking: 1,379.68 arena_score156. trinity-large-preview: 1,378.504 arena_score157. glm-4.6v: 1,377.245 arena_score158. qwen3-235b-a22b: 1,374.818 arena_score159. gemini-2.5-flash-lite-preview-06-17-thinking: 1,374.313 arena_score160. qwen2.5-max: 1,374.154 arena_score161. claude-3-5-sonnet-20241022: 1,373.133 arena_score162. glm-4.5-air: 1,372.919 arena_score163. claude-3-7-sonnet-20250219: 1,371.383 arena_score164. qwen3-next-80b-a3b-thinking: 1,369.523 arena_score165. trinity-large-thinking: 1,369.39 arena_score166. glm-4.7-flash: 1,368.08 arena_score167. amazon-nova-experimental-chat-11-10: 1,366.279 arena_score168. gemma-3-27b-it: 1,365.74 arena_score169. minimax-m1: 1,363.757 arena_score170. o3-mini-high: 1,363.468 arena_score171. grok-3-mini-high: 1,361.947 arena_score172. nvidia-nemotron-3-super-120b-a12b: 1,361.561 arena_score173. gemini-2.0-flash-001: 1,360.338 arena_score174. deepseek-v3: 1,358.503 arena_score175. mistral-small-2506: 1,357.508 arena_score176. grok-3-mini-beta: 1,356.718 arena_score177. intellect-3: 1,356.202 arena_score178. command-a-03-2025: 1,353.93 arena_score179. gemini-2.0-flash-lite-preview-02-05: 1,353.469 arena_score180. glm-4.5v: 1,353.431 arena_score181. gpt-oss-120b: 1,352.484 arena_score182. gemini-1.5-pro-002: 1,351.073 arena_score183. amazon-nova-experimental-chat-10-20: 1,349.681 arena_score184. hunyuan-turbos-20250226: 1,348.887 arena_score185. step-3: 1,348.31 arena_score186. o3-mini: 1,347.722 arena_score187. amazon-nova-experimental-chat-10-09: 1,347.687 arena_score188. llama-3.1-nemotron-ultra-253b-v1: 1,347.487 arena_score189. qwen3-32b: 1,347.204 arena_score190. mercury-2: 1,346.728 arena_score191. ling-flash-2.0: 1,346.248 arena_score192. qwen-plus-0125: 1,346.128 arena_score193. minimax-m2: 1,345.944 arena_score194. gpt-4o-2024-05-13: 1,345.799 arena_score195. nvidia-llama-3.3-nemotron-super-49b-v1.5: 1,343.17 arena_score196. glm-4-plus-0111: 1,342.873 arena_score197. claude-3-5-sonnet-20240620: 1,342.487 arena_score198. gemma-3-12b-it: 1,341.887 arena_score199. hunyuan-turbo-0110: 1,340.719 arena_score200. gpt-5-nano-high: 1,337.246 arena_score201. o1-mini: 1,337.068 arena_score202. nova-2-lite: 1,336.816 arena_score203. qwq-32b: 1,336.121 arena_score204. grok-2-2024-08-13: 1,335.639 arena_score205. gemini-advanced-0514: 1,335.399 arena_score206. gpt-4o-2024-08-06: 1,335.127 arena_score207. llama-3.1-405b-instruct-bf16: 1,334.824 arena_score208. step-2-16k-exp-202412: 1,333.9 arena_score209. llama-3.1-405b-instruct-fp8: 1,332.995 arena_score210. olmo-3.1-32b-instruct: 1,330.034 arena_score211. molmo-2-8b: 1,328.434 arena_score212. yi-lightning: 1,328.315 arena_score213. llama-3.3-nemotron-49b-super-v1: 1,328.009 arena_score214. qwen3-30b-a3b: 1,327.216 arena_score215. llama-4-maverick-17b-128e-instruct: 1,327.079 arena_score216. hunyuan-large-2025-02-10: 1,326.222 arena_score217. gpt-4-turbo-2024-04-09: 1,324.011 arena_score218. claude-3-5-haiku-20241022: 1,323.779 arena_score219. gemini-1.5-pro-001: 1,323.672 arena_score220. deepseek-v2.5-1210: 1,323.458 arena_score221. llama-4-scout-17b-16e-instruct: 1,322.71 arena_score222. gpt-4.1-nano-2025-04-14: 1,322.102 arena_score223. claude-3-opus-20240229: 1,321.454 arena_score224. ring-flash-2.0: 1,320.643 arena_score225. step-1o-turbo-202506: 1,320.272 arena_score226. glm-4-plus: 1,319.392 arena_score227. llama-3.3-70b-instruct: 1,318.155 arena_score228. gemma-3n-e4b-it: 1,318.039 arena_score229. qwen-max-0919: 1,317.987 arena_score230. gpt-4o-mini-2024-07-18: 1,317.709 arena_score231. gpt-oss-20b: 1,317.244 arena_score232. nvidia-nemotron-3-nano-30b-a3b-bf16: 1,315.647 arena_score233. qwen2.5-plus-1127: 1,314.886 arena_score234. athene-v2-chat: 1,314.298 arena_score235. mistral-large-2407: 1,314.04 arena_score236. gpt-4-0125-preview: 1,312.737 arena_score237. gpt-4-1106-preview: 1,312.308 arena_score238. hunyuan-standard-2025-02-10: 1,311.178 arena_score239. gemini-1.5-flash-002: 1,309.197 arena_score240. grok-2-mini-2024-08-13: 1,308.459 arena_score241. deepseek-v2.5: 1,307.12 arena_score242. granite-4.1-8b: 1,307.006 arena_score243. athene-70b-0725: 1,306.353 arena_score244. mercury: 1,306.264 arena_score245. olmo-3-32b-think: 1,305.599 arena_score246. mistral-large-2411: 1,305.297 arena_score247. magistral-medium-2506: 1,304.197 arena_score248. gemma-3-4b-it: 1,303.301 arena_score249. mistral-small-3.1-24b-instruct-2503: 1,303.297 arena_score250. qwen2.5-72b-instruct: 1,302.831 arena_score251. llama-3.1-nemotron-70b-instruct: 1,298.975 arena_score252. hunyuan-large-vision: 1,293.921 arena_score253. llama-3.1-70b-instruct: 1,293.181 arena_score254. amazon-nova-pro-v1.0: 1,290.033 arena_score255. jamba-1.5-large: 1,289.086 arena_score256. gemma-2-27b-it: 1,288.981 arena_score257. reka-core-20240904: 1,287.759 arena_score258. ibm-granite-h-small: 1,287.209 arena_score259. gpt-4-0314: 1,286.776 arena_score260. gemini-1.5-flash-001: 1,286.221 arena_score261. llama-3.1-nemotron-51b-instruct: 1,285.957 arena_score262. llama-3.1-tulu-3-70b: 1,285.938 arena_score263. olmo-3.1-32b-think: 1,284.99 arena_score264. claude-3-sonnet-20240229: 1,280.586 arena_score265. gemma-2-9b-it-simpo: 1,279.95 arena_score266. nemotron-4-340b-instruct: 1,276.537 arena_score267. llama-3-70b-instruct: 1,275.976 arena_score268. command-r-plus-08-2024: 1,275.821 arena_score269. gpt-4-0613: 1,275.046 arena_score270. mistral-small-24b-instruct-2501: 1,274.113 arena_score271. glm-4-0520: 1,272.987 arena_score272. reka-flash-20240904: 1,271.826 arena_score273. qwen2.5-coder-32b-instruct: 1,270.399 arena_score274. c4ai-aya-expanse-32b: 1,266.92 arena_score275. gemma-2-9b-it: 1,266.499 arena_score276. deepseek-coder-v2: 1,264.583 arena_score277. qwen2-72b-instruct: 1,261.142 arena_score278. command-r-plus: 1,261.087 arena_score279. claude-3-haiku-20240307: 1,260.867 arena_score280. amazon-nova-lite-v1.0: 1,260.352 arena_score281. gemini-1.5-flash-8b-001: 1,258.597 arena_score282. phi-4: 1,256.043 arena_score283. olmo-2-0325-32b-instruct: 1,251.331 arena_score284. command-r-08-2024: 1,249.7 arena_score285. mistral-large-2402: 1,241.728 arena_score286. amazon-nova-micro-v1.0: 1,240.599 arena_score287. jamba-1.5-mini: 1,239.39 arena_score288. ministral-8b-2410: 1,237.325 arena_score289. gemini-pro-dev-api: 1,235.808 arena_score290. qwen1.5-110b-chat: 1,233.51 arena_score291. hunyuan-standard-256k: 1,233.24 arena_score292. reka-flash-21b-20240226-online: 1,232.808 arena_score293. qwen1.5-72b-chat: 1,232.722 arena_score294. mixtral-8x22b-instruct-v0.1: 1,228.745 arena_score295. reka-flash-21b-20240226: 1,226.093 arena_score296. command-r: 1,226.085 arena_score297. gpt-3.5-turbo-0125: 1,224.276 arena_score298. llama-3-8b-instruct: 1,223.016 arena_score299. c4ai-aya-expanse-8b: 1,222.847 arena_score300. gemini-pro: 1,222.505 arena_score301. mistral-medium: 1,222.006 arena_score302. llama-3.1-tulu-3-8b: 1,220.425 arena_score303. yi-1.5-34b-chat: 1,212.497 arena_score304. zephyr-orpo-141b-A35b-v0.1: 1,212.176 arena_score305. llama-3.1-8b-instruct: 1,211.289 arena_score306. granite-3.1-8b-instruct: 1,207.842 arena_score307. qwen1.5-32b-chat: 1,203.177 arena_score308. gpt-3.5-turbo-1106: 1,202.777 arena_score309. gemma-2-2b-it: 1,199.868 arena_score310. phi-3-medium-4k-instruct: 1,197.198 arena_score311. mixtral-8x7b-instruct-v0.1: 1,196.355 arena_score312. dbrx-instruct-preview: 1,194.554 arena_score313. internlm2_5-20b-chat: 1,190.536 arena_score314. qwen1.5-14b-chat: 1,190.333 arena_score315. wizardlm-70b: 1,183.955 arena_score316. deepseek-llm-67b-chat: 1,183.923 arena_score317. yi-34b-chat: 1,183.133 arena_score318. granite-3.0-8b-instruct: 1,182.076 arena_score319. openchat-3.5: 1,181.96 arena_score320. openchat-3.5-0106: 1,181.796 arena_score321. gemma-1.1-7b-it: 1,181.647 arena_score322. snowflake-arctic-instruct: 1,179.057 arena_score323. granite-3.1-2b-instruct: 1,178.334 arena_score324. tulu-2-dpo-70b: 1,176.985 arena_score325. openhermes-2.5-mistral-7b: 1,174.906 arena_score326. vicuna-33b: 1,172.108 arena_score327. starling-lm-7b-beta: 1,170.576 arena_score328. phi-3-small-8k-instruct: 1,170.368 arena_score329. llama-2-70b-chat: 1,170.009 arena_score330. starling-lm-7b-alpha: 1,166.705 arena_score331. llama-3.2-3b-instruct: 1,166.207 arena_score332. nous-hermes-2-mixtral-8x7b-dpo: 1,163.81 arena_score333. granite-3.0-2b-instruct: 1,155.738 arena_score334. qwq-32b-preview: 1,154.586 arena_score335. llama2-70b-steerlm-chat: 1,153.999 arena_score336. solar-10.7b-instruct-v1.0: 1,151.565 arena_score337. dolphin-2.2.1-mistral-7b: 1,151.401 arena_score338. mpt-30b-chat: 1,149.731 arena_score339. mistral-7b-instruct-v0.2: 1,148.675 arena_score340. wizardlm-13b: 1,148.634 arena_score341. falcon-180b-chat: 1,146.93 arena_score342. qwen1.5-7b-chat: 1,143.158 arena_score343. phi-3-mini-4k-instruct-june-2024: 1,142.398 arena_score344. llama-2-13b-chat: 1,140.781 arena_score345. vicuna-13b: 1,140.51 arena_score346. qwen-14b-chat: 1,138.233 arena_score347. palm-2: 1,137.741 arena_score348. gemma-7b-it: 1,136.874 arena_score349. codellama-34b-instruct: 1,135.998 arena_score350. zephyr-7b-beta: 1,130.069 arena_score351. phi-3-mini-128k-instruct: 1,128.862 arena_score352. phi-3-mini-4k-instruct: 1,127.493 arena_score353. guanaco-33b: 1,126.581 arena_score354. zephyr-7b-alpha: 1,126.099 arena_score355. stripedhyena-nous-7b: 1,120.573 arena_score356. codellama-70b-instruct: 1,118.489 arena_score357. gemma-1.1-2b-it: 1,115.646 arena_score358. vicuna-7b: 1,114.261 arena_score359. smollm2-1.7b-instruct: 1,113.859 arena_score360. llama-3.2-1b-instruct: 1,110.561 arena_score361. mistral-7b-instruct: 1,109.271 arena_score362. llama-2-7b-chat: 1,107.318 arena_score363. gemma-2b-it: 1,092.658 arena_score364. qwen1.5-4b-chat: 1,089.938 arena_score365. olmo-7b-instruct: 1,073.176 arena_score366. koala-13b: 1,069.941 arena_score367. alpaca-13b: 1,068.446 arena_score368. gpt4all-13b-snoozy: 1,066.293 arena_score369. mpt-7b-chat: 1,062.077 arena_score370. chatglm3-6b: 1,055.518 arena_score371. RWKV-4-Raven-14B: 1,041.183 arena_score372. chatglm2-6b: 1,023.708 arena_score373. oasst-pythia-12b: 1,022.185 arena_score374. chatglm-6b: 994.904 arena_score375. fastchat-t5-3b: 991.382 arena_score376. dolly-v2-12b: 980.827 arena_score377. llama-13b: 973.398 arena_score378. stablelm-tuned-alpha-7b: 952.185 arena_score
Rank 1One bar per published rowRank 378

Official Arena release: 2026-07-21 · 100% confidence across rows.

Arena text preference current rankings
RankNameArena text style controlled ratingArena text rating lower boundArena text rating upper boundArena text rating varianceWhy
01claude-fable-51,507.3 arena_score1,500.91,513.710.6This rank
02claude-opus-4-6-thinking1,504.837 arena_score1,501.11,508.63.6This rank
03claude-opus-4-7-thinking1,502.043 arena_score1,497.81,506.24.6This rank
04claude-opus-4-61,497.759 arena_score1,494.11,501.43.4This rank
05muse-spark-1.11,495.059 arena_score1,487.81,502.313.6This rank
06claude-opus-4-71,493.665 arena_score1,489.51,497.94.6This rank
07muse-spark1,487.549 arena_score1,481.71,493.49This rank
08gemini-3.1-pro-preview1,485.814 arena_score1,482.31,489.33.2This rank
09gemini-3-pro1,485.737 arena_score1,481.91,489.63.8This rank
10kimi-k31,485.657 arena_score1,475.71,495.625.8This rank
11gpt-5.6-sol-xhigh1,485.073 arena_score1,477.21,49316.2This rank
12gemini-3.6-flash1,485.03 arena_score1,476.21,493.920.4This rank
13claude-opus-4-8-thinking1,483.583 arena_score1,478.51,488.76.8This rank
14gpt-5.5-high1,481.726 arena_score1,477.31,486.15This rank
15gpt-5.4-high1,477.787 arena_score1,473.81,481.74.1This rank
16gpt-5.51,476.323 arena_score1,4721,480.75This rank
17gemini-3.5-flash-high1,476.261 arena_score1,469.71,482.811.1This rank
18gpt-5.2-chat-latest-202602101,475.702 arena_score1,471.61,479.84.5This rank
19qwen3.7-max-preview1,475.151 arena_score1,465.11,485.226.2This rank
20grok-4.20-beta11,474.331 arena_score1,469.71,4795.7This rank
21gemini-3.5-flash-medium1,474.327 arena_score1,468.21,480.49.6This rank
22claude-opus-4-81,473.432 arena_score1,468.31,478.56.8This rank
23gpt-5.5-instant1,473.321 arena_score1,468.21,478.56.9This rank
24grok-4.20-beta-0309-reasoning1,473.176 arena_score1,469.31,4773.8This rank
25gemini-3-flash1,473.136 arena_score1,468.71,477.55.1This rank
26claude-opus-4-5-20251101-thinking-32k1,472.872 arena_score1,4691,476.83.9This rank
27claude-sonnet-4-61,472.544 arena_score1,468.71,476.43.9This rank
28grok-4.20-multi-agent-beta-03091,470.927 arena_score1,467.11,474.83.9This rank
29glm-5.11,469.645 arena_score1,465.11,474.25.5This rank
30glm-5.2 (max)1,469.199 arena_score1,463.41,4758.9This rank
31claude-opus-4-5-202511011,469.122 arena_score1,465.91,472.32.7This rank
32ernie-5.11,467.724 arena_score1,463.11,472.45.7This rank
33grok-4.51,467.72 arena_score1,460.41,47513.8This rank
34mimo-v2.5-pro1,466.835 arena_score1,462.41,471.35.2This rank
35gpt-5.41,466.259 arena_score1,462.41,470.13.9This rank
36grok-4.1-thinking1,465.901 arena_score1,462.71,469.12.7This rank
37qwen3.5-max-preview1,464.799 arena_score1,459.81,469.86.5This rank
38claude-sonnet-5-high1,461.148 arena_score1,454.91,467.410.2This rank
39kimi-k2.61,460.911 arena_score1,456.41,465.55.4This rank
40qwen3.6-max-preview1,460.103 arena_score1,451.71,468.518.3This rank
41qwen3.7-plus1,459.81 arena_score1,454.21,465.48.1This rank
42grok-4.11,459.455 arena_score1,456.21,462.72.7This rank
43gemini-3.5-flash-lite1,459.103 arena_score1,450.31,467.920This rank
44gemini-3-flash (thinking-minimal)1,458.629 arena_score1,455.51,461.82.6This rank
45glm-51,456.662 arena_score1,452.31,4614.9This rank
46deepseek-v4-pro1,456.612 arena_score1,452.21,4615This rank
47claude-sonnet-4-5-20250929-thinking-32k1,455.577 arena_score1,452.81,458.42.1This rank
48dola-seed-2.0-pro1,455.414 arena_score1,451.81,459.13.5This rank
49deepseek-v4-pro-thinking1,455.205 arena_score1,450.81,459.75.1This rank
50claude-sonnet-4-5-202509291,455.123 arena_score1,452.21,4582.2This rank
51gpt-5.1-high1,454.631 arena_score1,450.91,458.43.7This rank
52gemma-4-31b1,450.846 arena_score1,443.21,458.415.1This rank
53kimi-k2.5-thinking1,449.686 arena_score1,446.11,453.23.3This rank
54gpt-5.4-mini-high1,449.179 arena_score1,445.31,453.14This rank
55claude-opus-4-1-20250805-thinking-16k1,449.066 arena_score1,445.61,452.53.1This rank
56ernie-5.0-preview-12031,448.864 arena_score1,442.31,455.411.1This rank
57gpt-5.3-chat-latest1,448.83 arena_score1,444.51,453.24.9This rank
58mimo-v2-pro1,448.339 arena_score1,443.61,453.15.9This rank
59claude-opus-4-1-202508051,447.034 arena_score1,4441,4502.3This rank
60ernie-5.0-01101,446.887 arena_score1,442.91,450.94.1This rank
61gemini-2.5-pro1,445.566 arena_score1,443.11,448.11.6This rank
62inkling1,444.914 arena_score1,436.71,453.117.5This rank
63gpt-4.5-preview-2025-02-271,444.691 arena_score1,4391,450.48.5This rank
64minimax-m31,444.192 arena_score1,438.91,449.57.3This rank
65qwen3.6-plus1,443.823 arena_score1,439.51,448.14.9This rank
66chatgpt-4o-latest-202503261,443.152 arena_score1,440.31,4462.1This rank
67qwen3.5-397b-a17b1,442.154 arena_score1,438.41,445.93.6This rank
68glm-4.71,442.027 arena_score1,435.91,448.19.7This rank
69grok-4.31,442.019 arena_score1,437.71,446.34.9This rank
70deepseek-v4-flash-thinking1,438.855 arena_score1,434.51,443.25This rank
71gpt-5.11,438.631 arena_score1,4351,442.33.5This rank
72gemma-4-26b-a4b1,438.097 arena_score1,430.51,445.715.2This rank
73gpt-5.2-high1,437.401 arena_score1,433.81,4413.4This rank
74glm-5v-turbo1,436.741 arena_score1,429.41,444.113.9This rank
75longcat-flash-chat-2602-exp1,435.748 arena_score1,431.11,440.45.6This rank
76deepseek-v4-flash1,435.503 arena_score1,431.21,439.84.9This rank
77qwen3-max-preview1,434.779 arena_score1,430.31,439.35.3This rank
78gpt-5.21,434.405 arena_score1,431.11,437.72.8This rank
79gpt-5-high1,433.804 arena_score1,429.31,438.35.3This rank
80mimo-v2.51,432.992 arena_score1,428.61,437.45.1This rank
81gemini-3.1-flash-lite-preview1,431.896 arena_score1,428.11,435.73.7This rank
82kimi-k2.5-instant1,431.44 arena_score1,424.91,43811.3This rank
83grok-4-1-fast-reasoning1,430.989 arena_score1,427.71,434.22.8This rank
84o3-2025-04-161,430.803 arena_score1,427.21,434.43.4This rank
85mimo-v2-omni1,429.864 arena_score1,424.11,435.68.5This rank
86kimi-k2-thinking-turbo1,429.74 arena_score1,426.61,432.92.6This rank
87mistral-medium-3.51,427.421 arena_score1,420.81,43411.3This rank
88amazon-nova-experimental-chat-26-02-101,426.884 arena_score1,4171,436.725.2This rank
89gpt-5-chat1,426.753 arena_score1,422.51,4314.8This rank
90nvidia-nemotron-3-ultra-550b-a55b-nvfp41,425.247 arena_score1,418.21,432.313.1This rank
91glm-4.61,425.154 arena_score1,421.21,429.14This rank
92deepseek-v3.21,424.923 arena_score1,421.41,428.53.3This rank
93deepseek-v3.2-exp-thinking1,424.721 arena_score1,418.21,431.311.2This rank
94claude-opus-4-20250514-thinking-16k1,424.496 arena_score1,420.11,428.84.9This rank
95qwen3-max-2025-09-231,424.099 arena_score1,417.61,430.610.8This rank
96qwen3-235b-a22b-instruct-25071,423.168 arena_score1,420.61,425.81.7This rank
97deepseek-v3.2-thinking1,422.937 arena_score1,419.31,426.63.5This rank
98deepseek-v3.2-exp1,422.677 arena_score1,416.31,429.110.7This rank
99deepseek-r1-05281,422.061 arena_score1,416.41,427.78.3This rank
100grok-4-fast-chat1,420.772 arena_score1,413.11,428.415.1This rank
101ernie-5.0-preview-10221,418.52 arena_score1,409.71,427.320.2This rank
102kimi-k2-0905-preview1,417.887 arena_score1,411.41,424.411This rank
103deepseek-v3.11,417.486 arena_score1,411.51,423.59.4This rank
104kimi-k2-0711-preview1,417.465 arena_score1,412.61,422.36.2This rank
105qwen3.5-122b-a10b1,417.303 arena_score1,412.91,421.75This rank
106deepseek-v3.1-terminus-thinking1,417.244 arena_score1,407.31,427.225.9This rank
107deepseek-v3.1-thinking1,417.04 arena_score1,410.41,423.711.4This rank
108minimax-m2.71,416.749 arena_score1,412.61,420.94.5This rank
109amazon-nova-experimental-chat-26-01-101,415.479 arena_score1,405.61,425.425.4This rank
110mistral-large-31,415.386 arena_score1,4121,418.83This rank
111deepseek-v3.1-terminus1,415.28 arena_score1,405.71,424.924.1This rank
112qwen3-vl-235b-a22b-instruct1,415.268 arena_score1,408.81,421.810.9This rank
113gpt-4.1-2025-04-141,413.698 arena_score1,4101,417.43.6This rank
114claude-opus-4-202505141,412.502 arena_score1,408.21,416.84.8This rank
115claude-haiku-4-5-202510011,412.202 arena_score1,409.51,414.91.9Showing
116hunyuan-hy3-preview1,412.115 arena_score1,404.61,419.714.8This rank
117grok-3-preview-02-241,411.544 arena_score1,407.21,415.94.9This rank
118glm-4.51,410.925 arena_score1,4061,415.86.2This rank
119gemini-2.5-flash1,410.159 arena_score1,407.71,412.61.6This rank
120mistral-medium-25081,409.574 arena_score1,406.91,412.21.8This rank
121grok-4-07091,409.508 arena_score1,405.61,413.44This rank
122qwen3.5-27b1,408.63 arena_score1,404.21,413.15.1This rank
123gemini-2.5-flash-preview-09-20251,404.152 arena_score1,400.11,408.24.3This rank
124grok-4-fast-reasoning1,404.112 arena_score1,399.11,409.16.5This rank
125gpt-5.4-nano-high1,403.64 arena_score1,399.71,407.64.1This rank
126qwen3-235b-a22b-no-thinking1,403.009 arena_score1,398.51,407.55.3This rank
127o1-2024-12-171,402.053 arena_score1,397.61,406.55.2This rank
128qwen3-next-80b-a3b-instruct1,401.192 arena_score1,396.41,4065.9This rank
129longcat-flash-chat1,401.142 arena_score1,394.81,407.510.5This rank
130claude-sonnet-4-20250514-thinking-32k1,399.182 arena_score1,394.81,403.65.1This rank
131qwen3-235b-a22b-thinking-25071,399.125 arena_score1,392.61,405.711.1This rank
132deepseek-r11,398.137 arena_score1,393.31,4036.2This rank
133qwen3.5-flash1,397.094 arena_score1,393.31,400.93.8This rank
134qwen3.5-35b-a3b1,395.748 arena_score1,391.41,400.14.9This rank
135deepseek-v3-03241,395.598 arena_score1,391.71,399.53.9This rank
136qwen3-vl-235b-a22b-thinking1,395.205 arena_score1,388.41,40212This rank
137hunyuan-vision-1.5-thinking1,395.18 arena_score1,382.91,407.439This rank
138step-3.5-flash1,395.122 arena_score1,391.41,398.83.5This rank
139amazon-nova-experimental-chat-12-101,394.098 arena_score1,384.51,403.723.8This rank
140mimo-v2-flash (non-thinking)1,392.824 arena_score1,389.31,396.43.3This rank
141minimax-m2.51,390.474 arena_score1,386.51,394.54.2This rank
142gpt-5-mini-high1,389.979 arena_score1,385.31,394.65.6This rank
143o4-mini-2025-04-161,389.894 arena_score1,385.91,393.94.1This rank
144claude-sonnet-4-202505141,389.046 arena_score1,384.71,393.45This rank
145o1-preview1,388.394 arena_score1,383.41,393.46.5This rank
146qwen3-coder-480b-a35b-instruct1,387.523 arena_score1,382.61,392.56.4This rank
147claude-3-7-sonnet-20250219-thinking-32k1,387.348 arena_score1,383.21,391.54.5This rank
148mimo-v2-flash (thinking)1,387.092 arena_score1,380.81,393.310.2This rank
149mistral-medium-25051,386.869 arena_score1,382.21,391.65.8This rank
150hunyuan-t1-202507111,386.77 arena_score1,378.11,395.419.4This rank
151minimax-m2.1-preview1,384.059 arena_score1,378.81,389.37.1This rank
152qwen3-30b-a3b-instruct-25071,383.109 arena_score1,378.21,3886.2This rank
153gpt-4.1-mini-2025-04-141,382.761 arena_score1,378.51,387.14.8This rank
154hunyuan-turbos-202504161,382.241 arena_score1,375.81,388.710.9This rank
155gemini-2.5-flash-lite-preview-09-2025-no-thinking1,379.68 arena_score1,376.21,383.13.1This rank
156trinity-large-preview1,378.504 arena_score1,374.11,382.94.9This rank
157glm-4.6v1,377.245 arena_score1,3661,388.533This rank
158qwen3-235b-a22b1,374.818 arena_score1,370.11,379.55.7This rank
159gemini-2.5-flash-lite-preview-06-17-thinking1,374.313 arena_score1,369.81,378.85.3This rank
160qwen2.5-max1,374.154 arena_score1,370.11,378.34.4This rank
161claude-3-5-sonnet-202410221,373.133 arena_score1,3701,376.32.6This rank
162glm-4.5-air1,372.919 arena_score1,368.71,377.24.7This rank
163claude-3-7-sonnet-202502191,371.383 arena_score1,367.41,375.34This rank
164qwen3-next-80b-a3b-thinking1,369.523 arena_score1,363.71,375.48.9This rank
165trinity-large-thinking1,369.39 arena_score1,364.71,374.15.7This rank
166glm-4.7-flash1,368.08 arena_score1,362.31,373.98.7This rank
167amazon-nova-experimental-chat-11-101,366.279 arena_score1,361.91,370.65This rank
168gemma-3-27b-it1,365.74 arena_score1,362.11,369.43.5This rank
169minimax-m11,363.757 arena_score1,359.51,3684.8This rank
170o3-mini-high1,363.468 arena_score1,358.21,368.77.2This rank
171grok-3-mini-high1,361.947 arena_score1,356.61,367.37.4This rank
172nvidia-nemotron-3-super-120b-a12b1,361.561 arena_score1,354.31,368.813.7This rank
173gemini-2.0-flash-0011,360.338 arena_score1,356.61,364.13.7This rank
174deepseek-v31,358.503 arena_score1,353.81,363.25.9This rank
175mistral-small-25061,357.508 arena_score1,352.31,362.77This rank
176grok-3-mini-beta1,356.718 arena_score1,351.71,361.76.5This rank
177intellect-31,356.202 arena_score1,347.91,364.518.1This rank
178command-a-03-20251,353.93 arena_score1,350.51,357.43.1This rank
179gemini-2.0-flash-lite-preview-02-051,353.469 arena_score1,349.21,357.84.8This rank
180glm-4.5v1,353.431 arena_score1,345.11,361.818.1This rank
181gpt-oss-120b1,352.484 arena_score1,348.11,356.84.9This rank
182gemini-1.5-pro-0021,351.073 arena_score1,347.71,354.53This rank
183amazon-nova-experimental-chat-10-201,349.681 arena_score1,343.51,355.910This rank
184hunyuan-turbos-202502261,348.887 arena_score1,337.21,360.635.8This rank
185step-31,348.31 arena_score1,340.91,355.714.3This rank
186o3-mini1,347.722 arena_score1,344.21,351.33.2This rank
187amazon-nova-experimental-chat-10-091,347.687 arena_score1,336.81,358.530.7This rank
188llama-3.1-nemotron-ultra-253b-v11,347.487 arena_score1,335.81,359.235.5This rank
189qwen3-32b1,347.204 arena_score1,337.71,356.723.3This rank
190mercury-21,346.728 arena_score1,336.11,357.329.2This rank
191ling-flash-2.01,346.248 arena_score1,3391,353.513.7This rank
192qwen-plus-01251,346.128 arena_score1,337.81,354.518.1This rank
193minimax-m21,345.944 arena_score1,338.21,353.715.6This rank
194gpt-4o-2024-05-131,345.799 arena_score1,342.31,349.33.1This rank
195nvidia-llama-3.3-nemotron-super-49b-v1.51,343.17 arena_score1,333.21,353.125.9This rank
196glm-4-plus-01111,342.873 arena_score1,334.51,351.318.4This rank
197claude-3-5-sonnet-202406201,342.487 arena_score1,3391,345.93.1This rank
198gemma-3-12b-it1,341.887 arena_score1,332.41,351.423.5This rank
199hunyuan-turbo-01101,340.719 arena_score1,329.21,352.334.6This rank
200gpt-5-nano-high1,337.246 arena_score1,330.41,344.112.3This rank
201o1-mini1,337.068 arena_score1,333.41,340.73.5This rank
202nova-2-lite1,336.816 arena_score1,330.71,342.99.8This rank
203qwq-32b1,336.121 arena_score1,331.71,340.65.1This rank
204grok-2-2024-08-131,335.639 arena_score1,3321,339.33.5This rank
205gemini-advanced-05141,335.399 arena_score1,330.21,340.66.9This rank
206gpt-4o-2024-08-061,335.127 arena_score1,330.91,339.34.6This rank
207llama-3.1-405b-instruct-bf161,334.824 arena_score1,331.11,338.53.6This rank
208step-2-16k-exp-2024121,333.9 arena_score1,325.31,342.519.2This rank
209llama-3.1-405b-instruct-fp81,332.995 arena_score1,329.41,336.63.4This rank
210olmo-3.1-32b-instruct1,330.034 arena_score1,3241,336.19.6This rank
211molmo-2-8b1,328.434 arena_score1,307.11,349.8118.3This rank
212yi-lightning1,328.315 arena_score1,323.41,333.36.4This rank
213llama-3.3-nemotron-49b-super-v11,328.009 arena_score1,315.91,340.238.4This rank
214qwen3-30b-a3b1,327.216 arena_score1,322.51,331.95.8This rank
215llama-4-maverick-17b-128e-instruct1,327.079 arena_score1,322.81,331.34.7This rank
216hunyuan-large-2025-02-101,326.222 arena_score1,316.51,33624.7This rank
217gpt-4-turbo-2024-04-091,324.011 arena_score1,320.11,327.94This rank
218claude-3-5-haiku-202410221,323.779 arena_score1,320.51,3272.7This rank
219gemini-1.5-pro-0011,323.672 arena_score1,319.71,327.74.1This rank
220deepseek-v2.5-12101,323.458 arena_score1,315.21,331.717.8This rank
221llama-4-scout-17b-16e-instruct1,322.71 arena_score1,3181,327.45.8This rank
222gpt-4.1-nano-2025-04-141,322.102 arena_score1,314.41,329.815.5This rank
223claude-3-opus-202402291,321.454 arena_score1,318.41,324.52.5This rank
224ring-flash-2.01,320.643 arena_score1,313.41,327.913.6This rank
225step-1o-turbo-2025061,320.272 arena_score1,313.41,327.112.1This rank
226glm-4-plus1,319.392 arena_score1,314.51,324.36.3This rank
227llama-3.3-70b-instruct1,318.155 arena_score1,314.71,321.63.1This rank
228gemma-3n-e4b-it1,318.039 arena_score1,312.91,323.26.9This rank
229qwen-max-09191,317.987 arena_score1,312.31,323.78.5This rank
230gpt-4o-mini-2024-07-181,317.709 arena_score1,314.21,321.23.2This rank
231gpt-oss-20b1,317.244 arena_score1,310.91,323.610.6This rank
232nvidia-nemotron-3-nano-30b-a3b-bf161,315.647 arena_score1,310.11,321.28This rank
233qwen2.5-plus-11271,314.886 arena_score1,308.51,321.210.5This rank
234athene-v2-chat1,314.298 arena_score1,309.71,318.95.4This rank
235mistral-large-24071,314.04 arena_score1,310.11,3184This rank
236gpt-4-0125-preview1,312.737 arena_score1,308.71,316.84.3This rank
237gpt-4-1106-preview1,312.308 arena_score1,308.41,316.23.9This rank
238hunyuan-standard-2025-02-101,311.178 arena_score1,301.51,320.924.4This rank
239gemini-1.5-flash-0021,309.197 arena_score1,3051,313.44.6This rank
240grok-2-mini-2024-08-131,308.459 arena_score1,304.71,312.23.6This rank
241deepseek-v2.51,307.12 arena_score1,302.41,311.85.8This rank
242granite-4.1-8b1,307.006 arena_score1,296.91,317.126.7This rank
243athene-70b-07251,306.353 arena_score1,300.71,3128.4This rank
244mercury1,306.264 arena_score1,292.51,320.149.7This rank
245olmo-3-32b-think1,305.599 arena_score1,297.41,313.817.4This rank
246mistral-large-24111,305.297 arena_score1,300.91,309.75.1This rank
247magistral-medium-25061,304.197 arena_score1,297.81,310.610.8This rank
248gemma-3-4b-it1,303.301 arena_score1,2941,312.622.6This rank
249mistral-small-3.1-24b-instruct-25031,303.297 arena_score1,298.81,307.85.3This rank
250qwen2.5-72b-instruct1,302.831 arena_score1,298.81,306.94.3This rank
251llama-3.1-nemotron-70b-instruct1,298.975 arena_score1,291.21,306.715.7This rank
252hunyuan-large-vision1,293.921 arena_score1,284.81,30321.5This rank
253llama-3.1-70b-instruct1,293.181 arena_score1,289.41,296.93.6This rank
254amazon-nova-pro-v1.01,290.033 arena_score1,285.51,294.65.4This rank
255jamba-1.5-large1,289.086 arena_score1,281.81,296.413.9This rank
256gemma-2-27b-it1,288.981 arena_score1,285.61,292.43This rank
257reka-core-202409041,287.759 arena_score1,280.61,294.913.4This rank
258ibm-granite-h-small1,287.209 arena_score1,278.81,295.618.3This rank
259gpt-4-03141,286.776 arena_score1,2821,291.55.9This rank
260gemini-1.5-flash-0011,286.221 arena_score1,281.71,290.75.3This rank
261llama-3.1-nemotron-51b-instruct1,285.957 arena_score1,2761,295.925.9This rank
262llama-3.1-tulu-3-70b1,285.938 arena_score1,275.51,296.428.5This rank
263olmo-3.1-32b-think1,284.99 arena_score1,277.81,292.213.5This rank
264claude-3-sonnet-202402291,280.586 arena_score1,276.61,284.64.2This rank
265gemma-2-9b-it-simpo1,279.95 arena_score1,273.11,286.812.3This rank
266nemotron-4-340b-instruct1,276.537 arena_score1,271.21,281.97.4This rank
267llama-3-70b-instruct1,275.976 arena_score1,272.41,279.63.4This rank
268command-r-plus-08-20241,275.821 arena_score1,269.21,282.411.3This rank
269gpt-4-06131,275.046 arena_score1,2711,279.14.3This rank
270mistral-small-24b-instruct-25011,274.113 arena_score1,268.21,2809.1This rank
271glm-4-05201,272.987 arena_score1,2661,28012.7This rank
272reka-flash-202409041,271.826 arena_score1,264.81,278.812.8This rank
273qwen2.5-coder-32b-instruct1,270.399 arena_score1,262.31,278.517.2This rank
274c4ai-aya-expanse-32b1,266.92 arena_score1,2621,271.86.2This rank
275gemma-2-9b-it1,266.499 arena_score1,262.71,270.33.8This rank
276deepseek-coder-v21,264.583 arena_score1,258.31,270.910.3This rank
277qwen2-72b-instruct1,261.142 arena_score1,256.21,266.16.4This rank
278command-r-plus1,261.087 arena_score1,256.81,265.44.9This rank
279claude-3-haiku-202403071,260.867 arena_score1,257.11,264.63.7This rank
280amazon-nova-lite-v1.01,260.352 arena_score1,255.21,265.57This rank
281gemini-1.5-flash-8b-0011,258.597 arena_score1,254.31,262.94.8This rank
282phi-41,256.043 arena_score1,251.41,260.65.5This rank
283olmo-2-0325-32b-instruct1,251.331 arena_score1,240.51,262.130.3This rank
284command-r-08-20241,249.7 arena_score1,243.11,256.311.4This rank
285mistral-large-24021,241.728 arena_score1,2371,246.45.8This rank
286amazon-nova-micro-v1.01,240.599 arena_score1,235.41,245.86.9This rank
287jamba-1.5-mini1,239.39 arena_score1,232.21,246.613.6This rank
288ministral-8b-24101,237.325 arena_score1,228.21,246.421.5This rank
289gemini-pro-dev-api1,235.808 arena_score1,228.51,243.113.9This rank
290qwen1.5-110b-chat1,233.51 arena_score1,2281,239.18This rank
291hunyuan-standard-256k1,233.24 arena_score1,221.51,24535.9This rank
292reka-flash-21b-20240226-online1,232.808 arena_score1,225.41,240.214.3This rank
293qwen1.5-72b-chat1,232.722 arena_score1,227.41,2387.2This rank
294mixtral-8x22b-instruct-v0.11,228.745 arena_score1,224.21,233.35.4This rank
295reka-flash-21b-202402261,226.093 arena_score1,220.11,2329.2This rank
296command-r1,226.085 arena_score1,221.31,230.96This rank
297gpt-3.5-turbo-01251,224.276 arena_score1,219.61,2295.8This rank
298llama-3-8b-instruct1,223.016 arena_score1,219.31,226.83.6This rank
299c4ai-aya-expanse-8b1,222.847 arena_score1,215.91,229.812.7This rank
300gemini-pro1,222.505 arena_score1,210.81,234.235.9This rank
301mistral-medium1,222.006 arena_score1,216.51,227.57.9This rank
302llama-3.1-tulu-3-8b1,220.425 arena_score1,209.71,231.129.7This rank
303yi-1.5-34b-chat1,212.497 arena_score1,207.51,217.56.6This rank
304zephyr-orpo-141b-A35b-v0.11,212.176 arena_score1,201.41,22330.3This rank
305llama-3.1-8b-instruct1,211.289 arena_score1,207.11,215.44.5This rank
306granite-3.1-8b-instruct1,207.842 arena_score1,196.71,218.932.1This rank
307qwen1.5-32b-chat1,203.177 arena_score1,197.11,209.39.7This rank
308gpt-3.5-turbo-11061,202.777 arena_score1,1941,211.519.9This rank
309gemma-2-2b-it1,199.868 arena_score1,195.81,2044.4This rank
310phi-3-medium-4k-instruct1,197.198 arena_score1,1921,202.46.9This rank
311mixtral-8x7b-instruct-v0.11,196.355 arena_score1,192.11,200.64.7This rank
312dbrx-instruct-preview1,194.554 arena_score1,188.41,200.79.7This rank
313internlm2_5-20b-chat1,190.536 arena_score1,183.41,197.713.4This rank
314qwen1.5-14b-chat1,190.333 arena_score1,183.21,197.513.2This rank
315wizardlm-70b1,183.955 arena_score1,174.51,193.423.2This rank
316deepseek-llm-67b-chat1,183.923 arena_score1,172.41,195.434.3This rank
317yi-34b-chat1,183.133 arena_score1,176.31,19012.1This rank
318granite-3.0-8b-instruct1,182.076 arena_score1,173.41,190.819.6This rank
319openchat-3.51,181.96 arena_score1,172.31,191.624.3This rank
320openchat-3.5-01061,181.796 arena_score1,173.81,189.816.6This rank
321gemma-1.1-7b-it1,181.647 arena_score1,175.61,187.79.6This rank
322snowflake-arctic-instruct1,179.057 arena_score1,173.11,1859.1This rank
323granite-3.1-2b-instruct1,178.334 arena_score1,167.11,189.532.6This rank
324tulu-2-dpo-70b1,176.985 arena_score1,167.21,186.825This rank
325openhermes-2.5-mistral-7b1,174.906 arena_score1,164.51,185.328.2This rank
326vicuna-33b1,172.108 arena_score1,165.91,178.310This rank
327starling-lm-7b-beta1,170.576 arena_score1,163.21,17814.3This rank
328phi-3-small-8k-instruct1,170.368 arena_score1,164.41,176.39.1This rank
329llama-2-70b-chat1,170.009 arena_score1,164.51,175.57.9This rank
330starling-lm-7b-alpha1,166.705 arena_score1,158.61,174.816.9This rank
331llama-3.2-3b-instruct1,166.207 arena_score1,158.51,173.915.5This rank
332nous-hermes-2-mixtral-8x7b-dpo1,163.81 arena_score1,151.91,175.736.9This rank
333granite-3.0-2b-instruct1,155.738 arena_score1,147.31,164.118.3This rank
334qwq-32b-preview1,154.586 arena_score1,143.11,166.134.4This rank
335llama2-70b-steerlm-chat1,153.999 arena_score1,141.41,166.641.3This rank
336solar-10.7b-instruct-v1.01,151.565 arena_score1,138.41,164.745.1This rank
337dolphin-2.2.1-mistral-7b1,151.401 arena_score1,136.11,166.761.2This rank
338mpt-30b-chat1,149.731 arena_score1,137.51,16239.1This rank
339mistral-7b-instruct-v0.21,148.675 arena_score1,1421,155.311.5This rank
340wizardlm-13b1,148.634 arena_score1,139.41,157.922.2This rank
341falcon-180b-chat1,146.93 arena_score1,129.91,16475.8This rank
342qwen1.5-7b-chat1,143.158 arena_score1,133.31,15325.4This rank
343phi-3-mini-4k-instruct-june-20241,142.398 arena_score1,1361,148.810.8This rank
344llama-2-13b-chat1,140.781 arena_score1,134.11,147.511.8This rank
345vicuna-13b1,140.51 arena_score1,133.81,147.211.7This rank
346qwen-14b-chat1,138.233 arena_score1,127.31,149.231.2This rank
347palm-21,137.741 arena_score1,128.41,147.122.8This rank
348gemma-7b-it1,136.874 arena_score1,127.41,146.423.4This rank
349codellama-34b-instruct1,135.998 arena_score1,127.11,144.920.6This rank
350zephyr-7b-beta1,130.069 arena_score1,121.21,138.920.3This rank
351phi-3-mini-128k-instruct1,128.862 arena_score1,121.41,136.314.3This rank
352phi-3-mini-4k-instruct1,127.493 arena_score1,121.11,133.910.7This rank
353guanaco-33b1,126.581 arena_score1,114.51,138.738.1This rank
354zephyr-7b-alpha1,126.099 arena_score1,110.51,141.763.4This rank
355stripedhyena-nous-7b1,120.573 arena_score1,109.61,131.631.4This rank
356codellama-70b-instruct1,118.489 arena_score1,100.41,136.685.6This rank
357gemma-1.1-2b-it1,115.646 arena_score1,107.91,123.415.6This rank
358vicuna-7b1,114.261 arena_score1,105.11,123.421.7This rank
359smollm2-1.7b-instruct1,113.859 arena_score1,099.51,128.253.8This rank
360llama-3.2-1b-instruct1,110.561 arena_score1,102.71,118.416.2This rank
361mistral-7b-instruct1,109.271 arena_score1,1001,118.622.4This rank
362llama-2-7b-chat1,107.318 arena_score1,100.31,114.412.9This rank
363gemma-2b-it1,092.658 arena_score1,081.21,104.134.3This rank
364qwen1.5-4b-chat1,089.938 arena_score1,080.61,099.322.7This rank
365olmo-7b-instruct1,073.176 arena_score1,0621,084.332.4This rank
366koala-13b1,069.941 arena_score1,060.11,079.825.4This rank
367alpaca-13b1,068.446 arena_score1,0571,079.934.1This rank
368gpt4all-13b-snoozy1,066.293 arena_score1,051.11,081.560.2This rank
369mpt-7b-chat1,062.077 arena_score1,050.11,07437.3This rank
370chatglm3-6b1,055.518 arena_score1,043.91,067.235.4This rank
371RWKV-4-Raven-14B1,041.183 arena_score1,029.81,052.633.7This rank
372chatglm2-6b1,023.708 arena_score1,010.11,037.348This rank
373oasst-pythia-12b1,022.185 arena_score1,011.31,03330.7This rank
374chatglm-6b994.904 arena_score982.41,007.541This rank
375fastchat-t5-3b991.382 arena_score9791,003.739.8This rank
376dolly-v2-12b980.827 arena_score967.3994.347.5This rank
377llama-13b973.398 arena_score957.6989.264.8This rank
378stablelm-tuned-alpha-7b952.185 arena_score939.5964.942This rank

Why this rank

claude-haiku-4-5-20251001 on Arena Text Preference

Some explanation inputs are unavailable. Not published: the evidence frozen with this snapshot, comparable prior ranking.

Ranks official Arena model identifiers by the published style-controlled text overall rating.

115

Rank on this board

1,412.202

Score

108,518

Inputs behind the score

100% confidence · 1 of 1 components evidenced

What the score is built from

1 of 1 evidenced

Every component evidenced · 1 evidence record each

Components of claude-haiku-4-5-20251001's score
ComponentContribution
Arena text style controlled rating1,412.202

New in this snapshot

No change in rank

no_prior_published_snapshot

No component moved since the previous snapshot.

Where each number comes from

5 public records
  • Arena rating lower confidence boundArena text rating lower bound · observed Jul 21, 2026, 11:59 PM UTC1,409.516 arena_score100% confidence
    Source
    Arena official leaderboard dataset
    Grade
    A
    Freshness
    fresh
    Locator
    {"filter":"category = overall","datasetCard":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/blob/fb100fd1a48607efb93e28ba6610b641a7ac1bce/README.md","methodology":"https://github.com/lmarena/arena-rank","datasetSplit":"latest","datasetConfig":"text_style_control","datasetRevision":"fb100fd1a48607efb93e28ba6610b641a7ac1bce"}
    Open the source
  • Arena rating upper confidence boundArena text rating upper bound · observed Jul 21, 2026, 11:59 PM UTC1,414.888 arena_score100% confidence
    Source
    Arena official leaderboard dataset
    Grade
    A
    Freshness
    fresh
    Locator
    {"filter":"category = overall","datasetCard":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/blob/fb100fd1a48607efb93e28ba6610b641a7ac1bce/README.md","methodology":"https://github.com/lmarena/arena-rank","datasetSplit":"latest","datasetConfig":"text_style_control","datasetRevision":"fb100fd1a48607efb93e28ba6610b641a7ac1bce"}
    Open the source
  • Arena rating varianceArena text rating variance · observed Jul 21, 2026, 11:59 PM UTC1.878 arena_score_squared100% confidence
    Source
    Arena official leaderboard dataset
    Grade
    A
    Freshness
    fresh
    Locator
    {"filter":"category = overall","datasetCard":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/blob/fb100fd1a48607efb93e28ba6610b641a7ac1bce/README.md","methodology":"https://github.com/lmarena/arena-rank","datasetSplit":"latest","datasetConfig":"text_style_control","datasetRevision":"fb100fd1a48607efb93e28ba6610b641a7ac1bce"}
    Open the source
  • Arena text style-controlled ratingArena text style controlled rating · observed Jul 21, 2026, 11:59 PM UTC1,412.202 arena_score100% confidence
    Source
    Arena official leaderboard dataset
    Grade
    A
    Freshness
    fresh
    Locator
    {"filter":"category = overall","datasetCard":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/blob/fb100fd1a48607efb93e28ba6610b641a7ac1bce/README.md","methodology":"https://github.com/lmarena/arena-rank","datasetSplit":"latest","datasetConfig":"text_style_control","datasetRevision":"fb100fd1a48607efb93e28ba6610b641a7ac1bce"}
    Open the source
  • Arena vote countArena text vote · observed Jul 21, 2026, 11:59 PM UTC108,518 votes100% confidence
    Source
    Arena official leaderboard dataset
    Grade
    A
    Freshness
    fresh
    Locator
    {"filter":"category = overall","datasetCard":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset/blob/fb100fd1a48607efb93e28ba6610b641a7ac1bce/README.md","methodology":"https://github.com/lmarena/arena-rank","datasetSplit":"latest","datasetConfig":"text_style_control","datasetRevision":"fb100fd1a48607efb93e28ba6610b641a7ac1bce"}
    Open the source
Arena text style-controlled human-preference ranking published 2026-07-21, version arena-text-style-control-2026-07-21-fb100fd1a486-v11,890 observations · 1 source · quality passed
Snapshot
c5974e74-cce6-4258-bc51-ed2b27360bff
Data hash
dd2036b84fb51c58660a32e440acf003115f9197a850807f8da5983ceb649772
Method hash
0ae70a23e0117c0b4413d6bc1080037cc5cea4034f41c8eef849e92d66e5e7d9

More in Model rank

Capability-first rankings across frontier and open models.

3 boards

Enter your website. In about two minutes, Rank.ai asks ChatGPT, Claude and Gemini 12 questions your customers ask and grades how often they name you.

  • Your grade out of 100How often AI names you, cites your site, and how high it ranks you.
  • Who gets namedEvery competitor in the answers, most named first.
  • The pages AI readsThe sources behind each answer.
  • Three fixesWhat to fix first, with a brief for the first article.