Pass IndexThe State of AISign in

LMArena · Text

LMArena · Text is run by LMArena. It has ranked 414 models, of which the catalogue holds 161, scoring from 975 to 1507 on Score (Elo, style control).

measured by LMArena · the board itself

PlaceModelMetricScore
2ndof 414Claude Opus 5.5Score (Elo) (high)1507
3rdof 414Claude Opus 4.6Score (Elo) (high)1504
4thof 414Claude Fable 5Score (Elo) (high)1504
5thof 414Claude Opus 4.7Score (Elo) (high)1501
6thof 414Claude Fable 5.1Score (Elo) (max)1501
8thof 414Gemini 3.8 FlashScore (Elo) (high)1497
9thof 414Muse Spark 1.3Score (Elo) (max)1494
11thof 414Muse Spark 1.2Score (Elo)1492
12thof 414Muse Spark 1.1Score (Elo)1491
13thof 414Claude Opus 5Score (Elo) (high)1490
17thof 414Gemini 3.1 Pro PreviewScore (Elo)1487
18thof 414Gemini 3.7 FlashScore (Elo) (high)1486
19thof 414gemini-3-pro-previewScore (Elo)1485
20thof 414GPT-5.6 SolScore (Elo) (xhigh)1485
21stof 414GPT 6.1 SolScore (Elo) (max)1484
22ndof 414Qwen 3.8 MaxScore (Elo) (max)1483
23rdof 414Gemini 3.6 FlashScore (Elo) (high)1482
24thof 414GPT-5.5Score (Elo) (high)1482
25thof 414Claude Opus 4.8Score (Elo) (high)1481
26thof 414MiMo V2.6 ProScore (Elo)1480
27thof 414GLM-5.3Score (Elo) (max)1478
28thof 414Gemini 3.5 FlashScore (Elo) (high)1478
31stof 414GPT-5.2 ChatScore (Elo)1476
32ndof 414Claude Sonnet 5.5Score (Elo) (xhigh)1476
33rdof 414GLM 5.2Score (Elo) (max)1475
34thof 414GPT-5.4Score (Elo) (high)1475
35thof 414GPT 6 AstraScore (Elo) (max)1475
36thof 414Qwen3.7 MaxScore (Elo) (max)1475
37thof 414Grok 4.20Score (Elo)1475
38thof 414GLM 5.3 FlashScore (Elo)1475
39thof 414DeepSeek V4.1 FlashScore (Elo) (max)1475
41stof 414Claude Opus 4.5Score (Elo) (high)1474
42ndof 414GPT-5.5 InstantScore (Elo)1473
43rdof 414Gemini 3 FlashScore (Elo)1473
44thof 414Claude Sonnet 4.6Score (Elo)1472
46thof 414Grok 4.20 Multi-AgentScore (Elo)1470
48thof 414MiMo-V2.5-ProScore (Elo)1468
49thof 414ERNIE-5.1Score (Elo)1467
50thof 414GPT-5.6 TerraScore (Elo) (xhigh)1466
51stof 414Grok 4.5Score (Elo)1466
54thof 414GPT-5Score (Elo) (max)1465
55thof 414DeepSeek V4 ProScore (Elo) (high)1465
56thof 414GLM 5.1Score (Elo)1464
57thof 414Claude Sonnet 5Score (Elo) (high)1461
59thof 414Qwen3.6 Max PreviewScore (Elo) (max)1460
60thof 414Grok 4.1Score (Elo)1459
63rdof 414GLM-5Score (Elo)1458
64thof 414Claude Sonnet 4.5Score (Elo) (high)1456
66thof 414Qwen 3.7 PlusScore (Elo)1456
67thof 414GPT 6 SolScore (Elo) (max)1456
68thof 414GPT-5.1Score (Elo) (high)1456
70thof 414Gemini 3.5 Flash-LiteScore (Elo)1455
72ndof 414Grok 4.6Score (Elo) (high)1454
74thof 414GPT-5.6 LunaScore (Elo) (xhigh)1452
76thof 414MiMo V2.6 FlashScore (Elo)1451
77thof 414GPT-5.3 ChatScore (Elo)1450
81stof 414Claude Opus 4.1Score (Elo)1448
82ndof 414MiMo-V2-ProScore (Elo)1448
83rdof 414Step 5Score (Elo)1447
84thof 414GPT-5.4 miniScore (Elo) (high)1447
86thof 414Gemini 2.5 ProScore (Elo)1445
88thof 414Qwen3.6 PlusScore (Elo)1443
89thof 414OpenAI ChatGPT-4oScore (Elo)1443
90thof 414Grok 4.7Score (Elo) (xhigh)1443
91stof 414GPT 6 LunaScore (Elo) (max)1443
93rdof 414Grok 4.3Score (Elo)1442
94thof 414GLM-4.7Score (Elo)1441
97thof 414DeepSeek V4 FlashScore (Elo) (high)1439
101stof 414GPT-5.2Score (Elo) (high)1437
107thof 414MiMo-V2.5Score (Elo)1434
108thof 414GLM-5V-TurboScore (Elo)1433
109thof 414Gemini 3.1 Flash-LiteScore (Elo)1433
110thof 414o3Score (Elo)1432
111thof 414MiMo V2 OmniScore (Elo)1431
112thof 414Grok 4.1 Fast ReasoningScore (Elo)1430
115thof 414Mistral Large 4Score (Elo)1429
118thof 414GPT-5 ChatScore (Elo)1426
119thof 414Claude Opus 4Score (Elo)1426
120thof 414Nemotron 3 UltraScore (Elo)1426
122ndof 414DeepSeek v3.2Score (Elo)1425
124thof 414GLM-4.6Score (Elo)1424
126thof 414DeepSeek V3.2 ThinkingScore (Elo)1423
128thof 414DeepSeek V3.2 ExpScore (Elo)1421
129thof 414DeepSeek-R1 (0528)Score (Elo)1421
134thof 414DeepSeek-V3.1Score (Elo)1417
139thof 414DeepSeek V3.1 TerminusScore (Elo)1415
140thof 414GPT-4.1 fine-tunedScore (Elo)1415
142ndof 414Claude Haiku 4.5Score (Elo)1414
146thof 414Grok 3Score (Elo)1411
148thof 414GLM-4.5Score (Elo)1411
149thof 414Gemini 2.5 FlashScore (Elo)1409
156thof 414o1Score (Elo)1402
158thof 414Claude Sonnet 4Score (Elo)1402
159thof 414GPT-5.4 nanoScore (Elo) (high)1401
160thof 414LongCat-Flash-ChatScore (Elo)1401
163rdof 414DeepSeek-R1Score (Elo)1398
164thof 414Qwen3.5-FlashScore (Elo)1396
165thof 414DeepSeek-V3 0324Score (Elo)1395
171stof 414MiMo-V2-FlashScore (Elo)1392
172ndof 414o4-miniScore (Elo)1391
175thof 414GPT-5 miniScore (Elo) (high)1390
179thof 414Mistral Medium 2505Score (Elo)1387
182ndof 414Solar Pro 4Score (Elo)1386
183rdof 414MiniMax M2.1Score (Elo)1385
185thof 414GPT-4.1 miniScore (Elo)1383
187thof 414Gemini 2.5 Flash-Lite PreviewScore (Elo) (no-thinking)1379
188thof 414GLM-4.6VScore (Elo)1379
192ndof 414Claude 3.5 SonnetScore (Elo)1374
194thof 414GLM-4.5-AirScore (Elo)1373
195thof 414Claude 3.7 SonnetScore (Elo)1372
198thof 414Gemma 3 27BScore (Elo)1365
199thof 414GLM-4.7 FlashScore (Elo)1365
201stof 414Grok 3 MiniScore (Elo) (high)1364
203rdof 414o3 Mini HighScore (Elo) (high)1364
205thof 414gemini-2.0-flash-001Score (Elo)1360
206thof 414DeepSeek-V3Score (Elo)1358
210thof 414Command A 03-2025Score (Elo)1354
211thof 414Gemini 2.0 Flash-LiteScore (Elo)1354
212thof 414GLM-4.5VScore (Elo)1352
218thof 414o3-miniScore (Elo)1348
223rdof 414GPT-4o (2024-05-13)Score (Elo)1346
225thof 414Mercury 2Score (Elo)1344
226thof 414Ling-flash-2.0Score (Elo)1344
231stof 414Gemma 3 12BScore (Elo)1342
234thof 414GPT-5 nanoScore (Elo) (high)1337
235thof 414o1-miniScore (Elo)1337
239thof 414GPT-4o (2024-08-06)Score (Elo)1336
241stof 414Nova 2 LiteScore (Elo)1335
249thof 414Tencent-Hunyuan-LargeScore (Elo)1326
250thof 414Claude Haiku 3.5Score (Elo)1325
251stof 414GPT-4 TurboScore (Elo)1324
253rdof 414DeepSeek-V2.5-1210Score (Elo)1323
255thof 414GPT-4.1 nanoScore (Elo)1322
256thof 414Claude 3 OpusScore (Elo)1322
262ndof 414Llama 3.3 70B InstructScore (Elo)1318
263rdof 414GPT-4o-mini (2024-07-18)Score (Elo)1318
264thof 414Gemma 3n 4BScore (Elo)1318
275thof 414DeepSeek-V2.5Score (Elo)1307
282ndof 414Gemma 3 4BScore (Elo)1303
283rdof 414Qwen2.5 72B InstructScore (Elo)1303
289thof 414Nova ProScore (Elo)1290
300thof 414Claude 3 SonnetScore (Elo)1281
304thof 414Command R+ (08-2024)Score (Elo)1276
305thof 414GPT-4 (0613)Score (Elo)1276
310thof 414Aya Expanse 32BScore (Elo)1267
315thof 414Claude 3 HaikuScore (Elo)1262
316thof 414Nova LiteScore (Elo)1260
318thof 414Phi-4Score (Elo)1256
319thof 414Olmo-2-0325-32B-InstructScore (Elo)1252
320thof 414Command R (08-2024)Score (Elo)1250
321stof 414Mistral Large (24.02)Score (Elo)1243
322ndof 414Nova MicroScore (Elo)1241
333rdof 414GPT-3.5 TurboScore (Elo)1226
337thof 414Mistral Medium 3.1Score (Elo) (medium)1223
343rdof 414GPT-3.5 Turbo (1106)Score (Elo)1204
346thof 414Phi-3-medium-4k-instructScore (Elo)1198
363rdof 414Phi-3-small-8k-instructScore (Elo)1171
376thof 414Mistral-7B-Instruct-v0.2Score (Elo)1149
387thof 414Phi-3-mini-128k-instructScore (Elo)1130
388thof 414Phi-3-mini-4k-instructScore (Elo)1128
413thof 414llama-13bScore (Elo)975

Read from the board on 2026-10-12