Pass IndexThe State of AISign in

LMArena · Text

LMArena · Text is run by LMArena. It has ranked 402 models, of which the catalogue holds 150, scoring from 975 to 1506 on Score (Elo, style control).

measured by LMArena · the board itself

PlaceModelMetricScore
1stof 402Claude Fable 5Score (Elo)1506
2ndof 402Claude Opus 4.6Score (Elo) (high)1505
3rdof 402Claude Opus 4.7Score (Elo) (high)1502
4thof 402Muse Spark 1.2Score (Elo)1500
5thof 402Claude Fable 5.1Score (Elo) (max)1498
8thof 402Muse Spark 1.3Score (Elo) (max)1493
9thof 402Gemini 3.8 FlashScore (Elo) (high)1493
10thof 402Claude Opus 5Score (Elo) (high)1493
11thof 402Muse Spark 1.1Score (Elo)1493
12thof 402Gemini 3.7 FlashScore (Elo) (high)1490
15thof 402Gemini 3.1 Pro PreviewScore (Elo)1487
16thof 402gemini-3-pro-previewScore (Elo)1485
18thof 402GPT-5.6 SolScore (Elo) (xhigh)1483
19thof 402GLM-5.3Score (Elo) (max)1483
20thof 402GPT-5.5Score (Elo) (high)1482
21stof 402Claude Opus 4.8Score (Elo) (high)1481
22ndof 402Qwen 3.8 MaxScore (Elo) (max)1481
23rdof 402Gemini 3.6 FlashScore (Elo) (high)1480
24thof 402GPT 6 AstraScore (Elo) (max)1480
25thof 402Gemini 3.5 FlashScore (Elo) (high)1478
26thof 402GPT-5.4Score (Elo) (high)1476
27thof 402GPT-5.2 ChatScore (Elo)1476
29thof 402GLM 5.3 FlashScore (Elo)1475
30thof 402Grok 4.20Score (Elo)1475
32ndof 402GPT-5.5 InstantScore (Elo)1474
33rdof 402Gemini 3 FlashScore (Elo)1474
34thof 402Qwen3.7 MaxScore (Elo) (max)1473
36thof 402Claude Opus 4.5Score (Elo) (high)1473
37thof 402Claude Sonnet 4.6Score (Elo)1473
38thof 402GLM 5.2Score (Elo) (max)1472
40thof 402Grok 4.20 Multi-AgentScore (Elo)1470
42ndof 402Grok 4.5Score (Elo)1468
43rdof 402ERNIE-5.1Score (Elo)1468
44thof 402MiMo-V2.5-ProScore (Elo)1467
45thof 402GPT-5.6 TerraScore (Elo) (xhigh)1466
47thof 402GLM 5.1Score (Elo)1466
49thof 402GPT-5Score (Elo) (max)1465
50thof 402DeepSeek V4 ProScore (Elo) (high)1463
51stof 402Claude Sonnet 5Score (Elo) (high)1461
53rdof 402Qwen3.6 Max PreviewScore (Elo) (max)1460
54thof 402Grok 4.1Score (Elo)1459
56thof 402GLM-5Score (Elo)1458
58thof 402Claude Sonnet 4.5Score (Elo) (high)1456
59thof 402Gemini 3.5 Flash-LiteScore (Elo)1456
62ndof 402Qwen 3.7 PlusScore (Elo)1456
63rdof 402Grok 4.6Score (Elo) (high)1456
64thof 402GPT-5.1Score (Elo) (high)1455
67thof 402GPT-5.6 LunaScore (Elo) (xhigh)1452
71stof 402GPT-5.3 ChatScore (Elo)1449
73rdof 402MiMo-V2-ProScore (Elo)1448
74thof 402GPT-5.4 miniScore (Elo) (high)1448
75thof 402Claude Opus 4.1Score (Elo)1448
77thof 402Gemini 2.5 ProScore (Elo)1445
79thof 402Qwen3.6 PlusScore (Elo)1443
80thof 402OpenAI ChatGPT-4oScore (Elo)1443
81stof 402Grok 4.3Score (Elo)1443
83rdof 402GLM-4.7Score (Elo)1442
87thof 402DeepSeek V4 FlashScore (Elo) (high)1438
89thof 402GPT-5.2Score (Elo) (high)1438
96thof 402MiMo-V2.5Score (Elo)1434
97thof 402GLM-5V-TurboScore (Elo)1433
98thof 402Gemini 3.1 Flash-LiteScore (Elo)1432
99thof 402o3Score (Elo)1432
101stof 402Grok 4.1 Fast ReasoningScore (Elo)1430
103rdof 402MiMo V2 OmniScore (Elo)1430
105thof 402GPT-5 ChatScore (Elo)1427
107thof 402Claude Opus 4Score (Elo)1426
109thof 402Nemotron 3 UltraScore (Elo)1426
111thof 402DeepSeek v3.2Score (Elo)1425
112thof 402GLM-4.6Score (Elo)1425
115thof 402DeepSeek V3.2 ThinkingScore (Elo)1422
116thof 402DeepSeek V3.2 ExpScore (Elo)1422
117thof 402DeepSeek-R1 (0528)Score (Elo)1421
123rdof 402DeepSeek-V3.1Score (Elo)1417
127thof 402DeepSeek V3.1 TerminusScore (Elo)1415
129thof 402Claude Haiku 4.5Score (Elo)1415
130thof 402GPT-4.1 fine-tunedScore (Elo)1414
135thof 402Grok 3Score (Elo)1412
136thof 402GLM-4.5Score (Elo)1411
138thof 402Gemini 2.5 FlashScore (Elo)1410
145thof 402o1Score (Elo)1402
146thof 402GPT-5.4 nanoScore (Elo) (high)1402
147thof 402LongCat-Flash-ChatScore (Elo)1401
148thof 402Claude Sonnet 4Score (Elo)1401
151stof 402DeepSeek-R1Score (Elo)1398
152ndof 402Qwen3.5-FlashScore (Elo)1397
153rdof 402DeepSeek-V3 0324Score (Elo)1396
159thof 402MiMo-V2-FlashScore (Elo)1392
160thof 402o4-miniScore (Elo)1391
163rdof 402GPT-5 miniScore (Elo) (high)1390
168thof 402Mistral Medium 2505Score (Elo)1387
170thof 402MiniMax M2.1Score (Elo)1384
172ndof 402GPT-4.1 miniScore (Elo)1383
174thof 402Gemini 2.5 Flash-Lite PreviewScore (Elo) (no-thinking)1380
175thof 402GLM-4.6VScore (Elo)1378
177thof 402Solar Pro 4Score (Elo)1376
180thof 402Claude 3.5 SonnetScore (Elo)1374
182ndof 402GLM-4.5-AirScore (Elo)1373
183rdof 402Claude 3.7 SonnetScore (Elo)1372
186thof 402GLM-4.7 FlashScore (Elo)1366
187thof 402Gemma 3 27BScore (Elo)1365
190thof 402Grok 3 MiniScore (Elo) (high)1364
191stof 402o3 Mini HighScore (Elo) (high)1363
193rdof 402gemini-2.0-flash-001Score (Elo)1360
194thof 402DeepSeek-V3Score (Elo)1358
198thof 402Command A 03-2025Score (Elo)1354
199thof 402Gemini 2.0 Flash-LiteScore (Elo)1353
200thof 402GLM-4.5VScore (Elo)1353
207thof 402o3-miniScore (Elo)1348
211thof 402Mercury 2Score (Elo)1346
212thof 402GPT-4o (2024-05-13)Score (Elo)1346
215thof 402Ling-flash-2.0Score (Elo)1344
220thof 402Gemma 3 12BScore (Elo)1342
222ndof 402GPT-5 nanoScore (Elo) (high)1337
223rdof 402o1-miniScore (Elo)1337
224thof 402Nova 2 LiteScore (Elo)1336
228thof 402GPT-4o (2024-08-06)Score (Elo)1335
238thof 402Tencent-Hunyuan-LargeScore (Elo)1326
239thof 402Claude Haiku 3.5Score (Elo)1324
240thof 402GPT-4 TurboScore (Elo)1324
242ndof 402DeepSeek-V2.5-1210Score (Elo)1323
243rdof 402GPT-4.1 nanoScore (Elo)1322
244thof 402Claude 3 OpusScore (Elo)1322
250thof 402Llama 3.3 70B InstructScore (Elo)1318
251stof 402GPT-4o-mini (2024-07-18)Score (Elo)1318
253rdof 402Gemma 3n 4BScore (Elo)1317
264thof 402DeepSeek-V2.5Score (Elo)1307
270thof 402Gemma 3 4BScore (Elo)1303
272ndof 402Qwen2.5 72B InstructScore (Elo)1303
277thof 402Nova ProScore (Elo)1290
288thof 402Claude 3 SonnetScore (Elo)1281
292ndof 402Command R+ (08-2024)Score (Elo)1276
293rdof 402GPT-4 (0613)Score (Elo)1276
298thof 402Aya Expanse 32BScore (Elo)1267
303rdof 402Claude 3 HaikuScore (Elo)1261
304thof 402Nova LiteScore (Elo)1260
306thof 402Phi-4Score (Elo)1256
307thof 402Olmo-2-0325-32B-InstructScore (Elo)1251
308thof 402Command R (08-2024)Score (Elo)1250
309thof 402Mistral Large (24.02)Score (Elo)1242
310thof 402Nova MicroScore (Elo)1241
321stof 402GPT-3.5 TurboScore (Elo)1225
325thof 402Mistral Medium 3.1Score (Elo) (medium)1222
331stof 402GPT-3.5 Turbo (1106)Score (Elo)1204
334thof 402Phi-3-medium-4k-instructScore (Elo)1198
352ndof 402Phi-3-small-8k-instructScore (Elo)1171
364thof 402Mistral-7B-Instruct-v0.2Score (Elo)1149
375thof 402Phi-3-mini-128k-instructScore (Elo)1129
376thof 402Phi-3-mini-4k-instructScore (Elo)1128
401stof 402llama-13bScore (Elo)975

Read from the board on 2026-09-16