Model leaderboard

Arena scores (LMArena)

196 models in multi-turn ranked by LMArena score · updated Nov 19, 2026

#ModelScore
196PaLM 2. Closed weights: ranked by its LMArena score, with no size or downloads to show.994
195GPT-3.5 Turbo (1106). Closed weights: ranked by its LMArena score, with no size or downloads to show.1078
194GPT-3.5 Turbo (0125). Closed weights: ranked by its LMArena score, with no size or downloads to show.1117
193Gemini Pro (Dev API). Closed weights: ranked by its LMArena score, with no size or downloads to show.1124
192Gemini Pro. Closed weights: ranked by its LMArena score, with no size or downloads to show.1139
191Reka Flash 21B (20240226). Closed weights: ranked by its LMArena score, with no size or downloads to show.1141
190Mistral Medium. Closed weights: ranked by its LMArena score, with no size or downloads to show.1147
189Reka Flash 21B (Online, 20240226). Closed weights: ranked by its LMArena score, with no size or downloads to show.1151
188Mistral Large (2402). Closed weights: ranked by its LMArena score, with no size or downloads to show.1172
187Hunyuan Standard 256K. Closed weights: ranked by its LMArena score, with no size or downloads to show.1175
186Amazon Nova Micro 1.0. Closed weights: ranked by its LMArena score, with no size or downloads to show.1178
185GPT-4 (0613). Closed weights: ranked by its LMArena score, with no size or downloads to show.1185
184Gemini 1.5 Flash-8B (001). Closed weights: ranked by its LMArena score, with no size or downloads to show.1185
183Reka Flash (20240904). Closed weights: ranked by its LMArena score, with no size or downloads to show.1189
182Claude 3 Haiku (20240307). Closed weights: ranked by its LMArena score, with no size or downloads to show.1190
181Amazon Nova Lite 1.0. Closed weights: ranked by its LMArena score, with no size or downloads to show.1199
180GPT-4 (0314). Closed weights: ranked by its LMArena score, with no size or downloads to show.1206
179GLM-4 (0520). Closed weights: ranked by its LMArena score, with no size or downloads to show.1218
178Reka Core (20240904). Closed weights: ranked by its LMArena score, with no size or downloads to show.1227
177Claude 3 Sonnet (20240229). Closed weights: ranked by its LMArena score, with no size or downloads to show.1227
176Gemini 1.5 Flash (001). Closed weights: ranked by its LMArena score, with no size or downloads to show.1227
175Amazon Nova Pro 1.0. Closed weights: ranked by its LMArena score, with no size or downloads to show.1245
174GPT-4 Turbo Preview (0125). Closed weights: ranked by its LMArena score, with no size or downloads to show.1250
173Gemini 1.5 Flash (002). Closed weights: ranked by its LMArena score, with no size or downloads to show.1253
172Hunyuan Large Vision. Closed weights: ranked by its LMArena score, with no size or downloads to show.1253
171GPT-4 Turbo Preview (1106). Closed weights: ranked by its LMArena score, with no size or downloads to show.1257
170Claude 3.5 Haiku (20241022). Closed weights: ranked by its LMArena score, with no size or downloads to show.1265
169Grok 2 mini (2024-08-13). Closed weights: ranked by its LMArena score, with no size or downloads to show.1265
168GPT-4 Turbo (2024-04-09). Closed weights: ranked by its LMArena score, with no size or downloads to show.1267
167Gemini 1.5 Pro (001). Closed weights: ranked by its LMArena score, with no size or downloads to show.1268
166Gemini Advanced (0514). Closed weights: ranked by its LMArena score, with no size or downloads to show.1269
165Magistral Medium (2506). Closed weights: ranked by its LMArena score, with no size or downloads to show.1275
164Hunyuan Standard (2025-02-10). Closed weights: ranked by its LMArena score, with no size or downloads to show.1275
163Claude 3 Opus (20240229). Closed weights: ranked by its LMArena score, with no size or downloads to show.1275
162GPT-4.1 nano (2025-04-14). Closed weights: ranked by its LMArena score, with no size or downloads to show.1277
161GPT-4o (2024-08-06). Closed weights: ranked by its LMArena score, with no size or downloads to show.1279
160Mercury. Closed weights: ranked by its LMArena score, with no size or downloads to show.1282
159Hunyuan Large (2025-02-10). Closed weights: ranked by its LMArena score, with no size or downloads to show.1284
158GPT-4o mini (2024-07-18). Closed weights: ranked by its LMArena score, with no size or downloads to show.1285
157GLM-4-Plus. Closed weights: ranked by its LMArena score, with no size or downloads to show.1289
156Grok 2 (2024-08-13). Closed weights: ranked by its LMArena score, with no size or downloads to show.1290
155Step-2 16K Exp (202412). Closed weights: ranked by its LMArena score, with no size or downloads to show.1292
154Gemini 1.5 Pro (002). Closed weights: ranked by its LMArena score, with no size or downloads to show.1296
153Claude 3.5 Sonnet (20240620). Closed weights: ranked by its LMArena score, with no size or downloads to show.1299
152Qwen2.5-Plus (1127). Closed weights: ranked by its LMArena score, with no size or downloads to show.1299
151GPT-4o (2024-05-13). Closed weights: ranked by its LMArena score, with no size or downloads to show.1302
150Hunyuan Turbo (0110). Closed weights: ranked by its LMArena score, with no size or downloads to show.1303
149Gemini 2.0 Flash-Lite Preview (02-05). Closed weights: ranked by its LMArena score, with no size or downloads to show.1307
148Yi Lightning. Closed weights: ranked by its LMArena score, with no size or downloads to show.1311
147GPT-5 nano (High). Closed weights: ranked by its LMArena score, with no size or downloads to show.1312
146o3-mini. Closed weights: ranked by its LMArena score, with no size or downloads to show.1313
145o1-mini. Closed weights: ranked by its LMArena score, with no size or downloads to show.1314
144Hunyuan TurboS (20250226). Closed weights: ranked by its LMArena score, with no size or downloads to show.1320
143o3-mini (High). Closed weights: ranked by its LMArena score, with no size or downloads to show.1320
142GLM-4-Plus (0111). Closed weights: ranked by its LMArena score, with no size or downloads to show.1324
141Claude 3.5 Sonnet (20241022). Closed weights: ranked by its LMArena score, with no size or downloads to show.1326
140Qwen-Plus (0125). Closed weights: ranked by its LMArena score, with no size or downloads to show.1336
139Claude 3.7 Sonnet (Thinking 32K, 20250219). Closed weights: ranked by its LMArena score, with no size or downloads to show.1338
138Amazon Nova 2 Lite. Closed weights: ranked by its LMArena score, with no size or downloads to show.1338
137Claude 3.7 Sonnet (20250219). Closed weights: ranked by its LMArena score, with no size or downloads to show.1339
136Step-1o Turbo (202506). Closed weights: ranked by its LMArena score, with no size or downloads to show.1341
135Gemini 2.0 Flash (001). Closed weights: ranked by its LMArena score, with no size or downloads to show.1349
134o4-mini (2025-04-16). Closed weights: ranked by its LMArena score, with no size or downloads to show.1350
133Grok 3 Mini Beta. Closed weights: ranked by its LMArena score, with no size or downloads to show.1351
132GPT-4.1 mini (2025-04-14). Closed weights: ranked by its LMArena score, with no size or downloads to show.1354
131amazon-nova-experimental-chat (10-09). Closed weights: ranked by its LMArena score, with no size or downloads to show.1355
130o1 (2024-12-17). Closed weights: ranked by its LMArena score, with no size or downloads to show.1355
129Grok 3 Mini (High). Closed weights: ranked by its LMArena score, with no size or downloads to show.1355
128Mercury 2. Closed weights: ranked by its LMArena score, with no size or downloads to show.1356
127Gemini 2.5 Flash-Lite Preview (Thinking, 06-17). Closed weights: ranked by its LMArena score, with no size or downloads to show.1359
126GPT-5 mini (High). Closed weights: ranked by its LMArena score, with no size or downloads to show.1363
125amazon-nova-experimental-chat (10-20). Closed weights: ranked by its LMArena score, with no size or downloads to show.1364
124Qwen2.5-Max. Closed weights: ranked by its LMArena score, with no size or downloads to show.1364
123Claude Sonnet 4 (20250514). Closed weights: ranked by its LMArena score, with no size or downloads to show.1365
122Gemini 2.5 Flash-Lite Preview (Non-Thinking, 09-2025). Closed weights: ranked by its LMArena score, with no size or downloads to show.1366
121o1-preview. Closed weights: ranked by its LMArena score, with no size or downloads to show.1369
120Claude Sonnet 4 (Thinking 32K, 20250514). Closed weights: ranked by its LMArena score, with no size or downloads to show.1376
119amazon-nova-experimental-chat (26-01-10). Closed weights: ranked by its LMArena score, with no size or downloads to show.1379
118amazon-nova-experimental-chat (11-10). Closed weights: ranked by its LMArena score, with no size or downloads to show.1380
117GPT-5.4 nano (High). Closed weights: ranked by its LMArena score, with no size or downloads to show.1382
116Mistral Medium 3 (2505). Closed weights: ranked by its LMArena score, with no size or downloads to show.1383
115Hunyuan TurboS (20250416). Closed weights: ranked by its LMArena score, with no size or downloads to show.1387
114Claude Haiku 5.5 (High). Closed weights: ranked by its LMArena score, with no size or downloads to show.1387
113Claude Opus 4 (20250514). Closed weights: ranked by its LMArena score, with no size or downloads to show.1388
112Solar Pro 4. Closed weights: ranked by its LMArena score, with no size or downloads to show.1389
111Grok 4.1 Fast (Reasoning). Closed weights: ranked by its LMArena score, with no size or downloads to show.1389
110Qwen3.5-Flash. Closed weights: ranked by its LMArena score, with no size or downloads to show.1393
109Hunyuan T1 (20250711). Closed weights: ranked by its LMArena score, with no size or downloads to show.1394
108Grok 4.7 (xHigh). Closed weights: ranked by its LMArena score, with no size or downloads to show.1394
107GPT-6 Luna (Max). Closed weights: ranked by its LMArena score, with no size or downloads to show.1395
106Claude Opus 4 (Thinking 16K, 20250514). Closed weights: ranked by its LMArena score, with no size or downloads to show.1396
105Gemini 2.5 Flash Preview (09-2025). Closed weights: ranked by its LMArena score, with no size or downloads to show.1397
104GPT-4.1 (2025-04-14). Closed weights: ranked by its LMArena score, with no size or downloads to show.1398
103GPT-5 (High). Closed weights: ranked by its LMArena score, with no size or downloads to show.1399
102Grok 4 Fast (Reasoning). Closed weights: ranked by its LMArena score, with no size or downloads to show.1404
101o3 (2025-04-16). Closed weights: ranked by its LMArena score, with no size or downloads to show.1405
100Grok 4.3. Closed weights: ranked by its LMArena score, with no size or downloads to show.1406
99Gemini 2.5 Flash. Closed weights: ranked by its LMArena score, with no size or downloads to show.1408
98amazon-nova-experimental-chat (12-10). Closed weights: ranked by its LMArena score, with no size or downloads to show.1408
97ERNIE-5.0-Preview (1203). Closed weights: ranked by its LMArena score, with no size or downloads to show.1409
96Claude Haiku 4.5 (20251001). Closed weights: ranked by its LMArena score, with no size or downloads to show.1409
95GPT-5.3 Chat. Closed weights: ranked by its LMArena score, with no size or downloads to show.1412
94GPT-6 Sol (Max). Closed weights: ranked by its LMArena score, with no size or downloads to show.1413
93Grok 4 Fast (Non-Reasoning). Closed weights: ranked by its LMArena score, with no size or downloads to show.1414
92Grok 4 (0709). Closed weights: ranked by its LMArena score, with no size or downloads to show.1416
91LongCat-Flash-Chat Exp (2602). Closed weights: ranked by its LMArena score, with no size or downloads to show.1417
90ERNIE-5.0-Preview (1022). Closed weights: ranked by its LMArena score, with no size or downloads to show.1418
89Gemini 3.1 Flash-Lite Preview. Closed weights: ranked by its LMArena score, with no size or downloads to show.1418
88Mistral Medium 3.1 (2508). Closed weights: ranked by its LMArena score, with no size or downloads to show.1418
87GPT-5.2. Closed weights: ranked by its LMArena score, with no size or downloads to show.1418
86GPT-5.2 (High). Closed weights: ranked by its LMArena score, with no size or downloads to show.1419
85GPT-6.2 Sol (Max). Closed weights: ranked by its LMArena score, with no size or downloads to show.1420
84Hunyuan Vision 1.5 Thinking. Closed weights: ranked by its LMArena score, with no size or downloads to show.1422
83Grok 3 Preview (02-24). Closed weights: ranked by its LMArena score, with no size or downloads to show.1424
82GPT-6.2 Astra (Max). Closed weights: ranked by its LMArena score, with no size or downloads to show.1425
81GPT-5 Chat. Closed weights: ranked by its LMArena score, with no size or downloads to show.1426
80Grok 4.6 (High). Closed weights: ranked by its LMArena score, with no size or downloads to show.1427
79GPT-5.4 mini (High). Closed weights: ranked by its LMArena score, with no size or downloads to show.1429
78Grok 4.1 (Thinking). Closed weights: ranked by its LMArena score, with no size or downloads to show.1430
77GPT-6.1 Terra (Max). Closed weights: ranked by its LMArena score, with no size or downloads to show.1432
76GPT-5.1. Closed weights: ranked by its LMArena score, with no size or downloads to show.1433
75ERNIE 5.0 (0110). Closed weights: ranked by its LMArena score, with no size or downloads to show.1433
74Qwen3-Max (2025-09-23). Closed weights: ranked by its LMArena score, with no size or downloads to show.1433
73GPT-5.5 Instant. Closed weights: ranked by its LMArena score, with no size or downloads to show.1434
72GPT-5.6 Luna (xHigh). Closed weights: ranked by its LMArena score, with no size or downloads to show.1435
71Grok 4.1. Closed weights: ranked by its LMArena score, with no size or downloads to show.1438
70Qwen3.6-Plus. Closed weights: ranked by its LMArena score, with no size or downloads to show.1438
69Step 5 Preview. Closed weights: ranked by its LMArena score, with no size or downloads to show.1439
68Dola Seed 2.0 Pro. Closed weights: ranked by its LMArena score, with no size or downloads to show.1441
67amazon-nova-experimental-chat (26-02-10). Closed weights: ranked by its LMArena score, with no size or downloads to show.1442
66Claude Opus 4.1 (20250805). Closed weights: ranked by its LMArena score, with no size or downloads to show.1443
65Claude Opus 4.1 (Thinking 16K, 20250805). Closed weights: ranked by its LMArena score, with no size or downloads to show.1444
64GPT-4.5 Preview (2025-02-27). Closed weights: ranked by its LMArena score, with no size or downloads to show.1444
63MiMo-V2-Omni. Closed weights: ranked by its LMArena score, with no size or downloads to show.1445
62GPT-6 Astra (Max). Closed weights: ranked by its LMArena score, with no size or downloads to show.1446
61Gemini 3.5 Flash-Lite. Closed weights: ranked by its LMArena score, with no size or downloads to show.1446
60Qwen3-Max-Preview. Closed weights: ranked by its LMArena score, with no size or downloads to show.1446
59GPT-5.1 (High). Closed weights: ranked by its LMArena score, with no size or downloads to show.1450
58GPT-6.1 Sol (Max). Closed weights: ranked by its LMArena score, with no size or downloads to show.1450
57Grok 4.20 Beta 1. Closed weights: ranked by its LMArena score, with no size or downloads to show.1450
56Grok 4.20 Multi-Agent Beta (0309). Closed weights: ranked by its LMArena score, with no size or downloads to show.1452
55Gemini 2.5 Pro. Closed weights: ranked by its LMArena score, with no size or downloads to show.1452
54Claude Sonnet 4.5 (High, 32K, 20250929). Closed weights: ranked by its LMArena score, with no size or downloads to show.1453
53Claude Sonnet 5 (High). Closed weights: ranked by its LMArena score, with no size or downloads to show.1454
52Qwen3.6-Max-Preview. Closed weights: ranked by its LMArena score, with no size or downloads to show.1454
51ChatGPT-4o Latest (20250326). Closed weights: ranked by its LMArena score, with no size or downloads to show.1454
50GPT-5.6 Terra (xHigh). Closed weights: ranked by its LMArena score, with no size or downloads to show.1455
49Grok 4.5. Closed weights: ranked by its LMArena score, with no size or downloads to show.1455
48Gemini 3 Flash (Minimal). Closed weights: ranked by its LMArena score, with no size or downloads to show.1455
47Grok 4.20 Beta (Reasoning, 0309). Closed weights: ranked by its LMArena score, with no size or downloads to show.1456
46MiMo-V2-Pro. Closed weights: ranked by its LMArena score, with no size or downloads to show.1456
45Claude Fable 5.2 (Max). Closed weights: ranked by its LMArena score, with no size or downloads to show.1458
44GPT-5.2 Chat (20260210). Closed weights: ranked by its LMArena score, with no size or downloads to show.1458
43Qwen3.7-Plus. Closed weights: ranked by its LMArena score, with no size or downloads to show.1460
42Claude Opus 4.5 (High, 32K, 20251101). Closed weights: ranked by its LMArena score, with no size or downloads to show.1460
41GPT-5.6 Sol (xHigh). Closed weights: ranked by its LMArena score, with no size or downloads to show.1462
40Claude Sonnet 5.5 (xHigh). Closed weights: ranked by its LMArena score, with no size or downloads to show.1462
39Claude Sonnet 4.6. Closed weights: ranked by its LMArena score, with no size or downloads to show.1463
38GPT-5.4. Closed weights: ranked by its LMArena score, with no size or downloads to show.1463
37Claude Sonnet 4.5 (20250929). Closed weights: ranked by its LMArena score, with no size or downloads to show.1465
36Claude Opus 4.5 (20251101). Closed weights: ranked by its LMArena score, with no size or downloads to show.1466
35ERNIE 5.1. Closed weights: ranked by its LMArena score, with no size or downloads to show.1471
34Claude Opus 4.8. Closed weights: ranked by its LMArena score, with no size or downloads to show.1471
33Gemini 3 Flash. Closed weights: ranked by its LMArena score, with no size or downloads to show.1472
32GPT-5.5. Closed weights: ranked by its LMArena score, with no size or downloads to show.1473
31Claude Opus 4.8 (High). Closed weights: ranked by its LMArena score, with no size or downloads to show.1476
30GPT-5.5 (High). Closed weights: ranked by its LMArena score, with no size or downloads to show.1477
29Muse Spark. Closed weights: ranked by its LMArena score, with no size or downloads to show.1477
28Gemini 3.5 Flash (Medium). Closed weights: ranked by its LMArena score, with no size or downloads to show.1478
27Qwen3.5-Max-Preview. Closed weights: ranked by its LMArena score, with no size or downloads to show.1478
26Qwen3.7-Max-Preview. Closed weights: ranked by its LMArena score, with no size or downloads to show.1478
25Gemini 3.5 Flash (High). Closed weights: ranked by its LMArena score, with no size or downloads to show.1481
24GPT-5.4 (High). Closed weights: ranked by its LMArena score, with no size or downloads to show.1482
23Gemini 3.6 Flash (High). Closed weights: ranked by its LMArena score, with no size or downloads to show.1483
22Gemini 3 Pro. Closed weights: ranked by its LMArena score, with no size or downloads to show.1484
21Muse Spark 1.1. Closed weights: ranked by its LMArena score, with no size or downloads to show.1485
20Gemini 3.1 Pro Preview. Closed weights: ranked by its LMArena score, with no size or downloads to show.1486
19Gemini 3.7 Flash (High). Closed weights: ranked by its LMArena score, with no size or downloads to show.1487
18Muse Spark 1.3 (Max). Closed weights: ranked by its LMArena score, with no size or downloads to show.1488
17Gemini 4 Hydrogen (High). Closed weights: ranked by its LMArena score, with no size or downloads to show.1489
16Claude Fable 5.1 (Max). Closed weights: ranked by its LMArena score, with no size or downloads to show.1490
15Qwen3.8-Max. Closed weights: ranked by its LMArena score, with no size or downloads to show.1492
14Claude Opus 5 (High). Closed weights: ranked by its LMArena score, with no size or downloads to show.1494
13Muse Spark 1.2 (xHigh). Closed weights: ranked by its LMArena score, with no size or downloads to show.1495
12Claude Opus 5 (Max). Closed weights: ranked by its LMArena score, with no size or downloads to show.1499
11Claude Opus 5.5 (High). Closed weights: ranked by its LMArena score, with no size or downloads to show.1502
10Gemini 3.8 Flash (High). Closed weights: ranked by its LMArena score, with no size or downloads to show.1502
9Claude Fable 5 (High). Closed weights: ranked by its LMArena score, with no size or downloads to show.1504
8Claude Opus 4.7. Closed weights: ranked by its LMArena score, with no size or downloads to show.1504
7Claude Opus 4.6. Closed weights: ranked by its LMArena score, with no size or downloads to show.1505
6Claude Opus 4.7 (High). Closed weights: ranked by its LMArena score, with no size or downloads to show.1506
5Muse Wonder (Max). Closed weights: ranked by its LMArena score, with no size or downloads to show.1512
4Claude Opus 4.6 (High). Closed weights: ranked by its LMArena score, with no size or downloads to show.1512
3Gemini 4 Neon (High). Closed weights: ranked by its LMArena score, with no size or downloads to show.1525
2Gemini 4 Argon (High). Closed weights: ranked by its LMArena score, with no size or downloads to show.1545
1Gemini 4 Carbon (High). Closed weights: ranked by its LMArena score, with no size or downloads to show.1570
Show the top 20

Scores: LMArena, CC BY 4.0. Measured on served versions, not local builds. A model with several served variants shows its best.