Model leaderboard

Arena scores (LMArena)

196 models in instructions ranked by LMArena score · updated Nov 19, 2026

#ModelScore
1Gemini 4 Carbon (High). Closed weights: ranked by its LMArena score, with no size or downloads to show.1539
2Gemini 4 Neon (High). Closed weights: ranked by its LMArena score, with no size or downloads to show.1535
3Gemini 4 Argon (High). Closed weights: ranked by its LMArena score, with no size or downloads to show.1535
4Claude Opus 5.5 (High). Closed weights: ranked by its LMArena score, with no size or downloads to show.1533
5Claude Fable 5.1 (Max). Closed weights: ranked by its LMArena score, with no size or downloads to show.1522
6Claude Opus 4.6 (High). Closed weights: ranked by its LMArena score, with no size or downloads to show.1521
7Claude Opus 5 (Max). Closed weights: ranked by its LMArena score, with no size or downloads to show.1517
8Gemini 4 Hydrogen (High). Closed weights: ranked by its LMArena score, with no size or downloads to show.1515
9Claude Opus 5 (High). Closed weights: ranked by its LMArena score, with no size or downloads to show.1515
10Claude Opus 4.6. Closed weights: ranked by its LMArena score, with no size or downloads to show.1510
11Claude Fable 5 (High). Closed weights: ranked by its LMArena score, with no size or downloads to show.1503
12Claude Opus 4.7 (High). Closed weights: ranked by its LMArena score, with no size or downloads to show.1498
13Gemini 3.8 Flash (High). Closed weights: ranked by its LMArena score, with no size or downloads to show.1494
14Muse Wonder (Max). Closed weights: ranked by its LMArena score, with no size or downloads to show.1492
15Claude Fable 5.2 (Max). Closed weights: ranked by its LMArena score, with no size or downloads to show.1490
16Claude Opus 4.7. Closed weights: ranked by its LMArena score, with no size or downloads to show.1489
17Gemini 3.7 Flash (High). Closed weights: ranked by its LMArena score, with no size or downloads to show.1485
18Claude Sonnet 5.5 (xHigh). Closed weights: ranked by its LMArena score, with no size or downloads to show.1485
19Qwen3.8-Max. Closed weights: ranked by its LMArena score, with no size or downloads to show.1484
20GPT-5.6 Sol (xHigh). Closed weights: ranked by its LMArena score, with no size or downloads to show.1482
21Muse Spark 1.3 (Max). Closed weights: ranked by its LMArena score, with no size or downloads to show.1480
22GPT-5.5 (High). Closed weights: ranked by its LMArena score, with no size or downloads to show.1478
23Claude Opus 4.5 (High, 32K, 20251101). Closed weights: ranked by its LMArena score, with no size or downloads to show.1478
24Claude Opus 4.8 (High). Closed weights: ranked by its LMArena score, with no size or downloads to show.1477
25Claude Sonnet 4.6. Closed weights: ranked by its LMArena score, with no size or downloads to show.1476
26GPT-5.5. Closed weights: ranked by its LMArena score, with no size or downloads to show.1475
27Claude Opus 4.5 (20251101). Closed weights: ranked by its LMArena score, with no size or downloads to show.1472
28GPT-5.4 (High). Closed weights: ranked by its LMArena score, with no size or downloads to show.1469
29Qwen3.5-Max-Preview. Closed weights: ranked by its LMArena score, with no size or downloads to show.1468
30Gemini 3.5 Flash (High). Closed weights: ranked by its LMArena score, with no size or downloads to show.1468
31Gemini 3.6 Flash (High). Closed weights: ranked by its LMArena score, with no size or downloads to show.1467
32Muse Spark 1.2 (xHigh). Closed weights: ranked by its LMArena score, with no size or downloads to show.1467
33GPT-6.1 Sol (Max). Closed weights: ranked by its LMArena score, with no size or downloads to show.1466
34Gemini 3.1 Pro Preview. Closed weights: ranked by its LMArena score, with no size or downloads to show.1465
35Gemini 3.5 Flash (Medium). Closed weights: ranked by its LMArena score, with no size or downloads to show.1465
36Claude Opus 4.8. Closed weights: ranked by its LMArena score, with no size or downloads to show.1463
37ERNIE 5.1. Closed weights: ranked by its LMArena score, with no size or downloads to show.1462
38Qwen3.7-Max-Preview. Closed weights: ranked by its LMArena score, with no size or downloads to show.1460
39Claude Sonnet 4.5 (20250929). Closed weights: ranked by its LMArena score, with no size or downloads to show.1459
40Gemini 3 Pro. Closed weights: ranked by its LMArena score, with no size or downloads to show.1458
41Claude Sonnet 4.5 (High, 32K, 20250929). Closed weights: ranked by its LMArena score, with no size or downloads to show.1458
42Muse Spark 1.1. Closed weights: ranked by its LMArena score, with no size or downloads to show.1457
43GPT-5.6 Terra (xHigh). Closed weights: ranked by its LMArena score, with no size or downloads to show.1455
44GPT-5.4. Closed weights: ranked by its LMArena score, with no size or downloads to show.1455
45GPT-6 Astra (Max). Closed weights: ranked by its LMArena score, with no size or downloads to show.1455
46Claude Sonnet 5 (High). Closed weights: ranked by its LMArena score, with no size or downloads to show.1453
47Step 5 Preview. Closed weights: ranked by its LMArena score, with no size or downloads to show.1446
48Grok 4.5. Closed weights: ranked by its LMArena score, with no size or downloads to show.1446
49MiMo-V2-Pro. Closed weights: ranked by its LMArena score, with no size or downloads to show.1446
50Muse Spark. Closed weights: ranked by its LMArena score, with no size or downloads to show.1443
51GPT-5.1 (High). Closed weights: ranked by its LMArena score, with no size or downloads to show.1442
52GPT-6.1 Terra (Max). Closed weights: ranked by its LMArena score, with no size or downloads to show.1442
53Qwen3.7-Plus. Closed weights: ranked by its LMArena score, with no size or downloads to show.1439
54Qwen3.6-Max-Preview. Closed weights: ranked by its LMArena score, with no size or downloads to show.1439
55Gemini 2.5 Pro. Closed weights: ranked by its LMArena score, with no size or downloads to show.1437
56GPT-5.6 Luna (xHigh). Closed weights: ranked by its LMArena score, with no size or downloads to show.1437
57Gemini 3 Flash. Closed weights: ranked by its LMArena score, with no size or downloads to show.1436
58Claude Opus 4.1 (Thinking 16K, 20250805). Closed weights: ranked by its LMArena score, with no size or downloads to show.1435
59GPT-6.2 Sol (Max). Closed weights: ranked by its LMArena score, with no size or downloads to show.1434
60Claude Opus 4.1 (20250805). Closed weights: ranked by its LMArena score, with no size or downloads to show.1433
61Grok 4.6 (High). Closed weights: ranked by its LMArena score, with no size or downloads to show.1431
62MiMo-V2-Omni. Closed weights: ranked by its LMArena score, with no size or downloads to show.1428
63amazon-nova-experimental-chat (26-02-10). Closed weights: ranked by its LMArena score, with no size or downloads to show.1427
64Qwen3.6-Plus. Closed weights: ranked by its LMArena score, with no size or downloads to show.1424
65GPT-6.2 Astra (Max). Closed weights: ranked by its LMArena score, with no size or downloads to show.1423
66Grok 4.20 Beta (Reasoning, 0309). Closed weights: ranked by its LMArena score, with no size or downloads to show.1421
67Grok 4.20 Multi-Agent Beta (0309). Closed weights: ranked by its LMArena score, with no size or downloads to show.1421
68Gemini 3.5 Flash-Lite. Closed weights: ranked by its LMArena score, with no size or downloads to show.1420
69Qwen3-Max-Preview. Closed weights: ranked by its LMArena score, with no size or downloads to show.1420
70GPT-5.1. Closed weights: ranked by its LMArena score, with no size or downloads to show.1418
71GPT-5.2 Chat (20260210). Closed weights: ranked by its LMArena score, with no size or downloads to show.1416
72Grok 4.20 Beta 1. Closed weights: ranked by its LMArena score, with no size or downloads to show.1415
73Gemini 3 Flash (Minimal). Closed weights: ranked by its LMArena score, with no size or downloads to show.1415
74Dola Seed 2.0 Pro. Closed weights: ranked by its LMArena score, with no size or downloads to show.1414
75Claude Haiku 4.5 (20251001). Closed weights: ranked by its LMArena score, with no size or downloads to show.1414
76ERNIE 5.0 (0110). Closed weights: ranked by its LMArena score, with no size or downloads to show.1413
77LongCat-Flash-Chat Exp (2602). Closed weights: ranked by its LMArena score, with no size or downloads to show.1411
78GPT-6 Sol (Max). Closed weights: ranked by its LMArena score, with no size or downloads to show.1411
79GPT-5.2 (High). Closed weights: ranked by its LMArena score, with no size or downloads to show.1409
80Grok 3 Preview (02-24). Closed weights: ranked by its LMArena score, with no size or downloads to show.1408
81Claude Haiku 5.5 (High). Closed weights: ranked by its LMArena score, with no size or downloads to show.1407
82GPT-5.5 Instant. Closed weights: ranked by its LMArena score, with no size or downloads to show.1407
83Claude Opus 4 (Thinking 16K, 20250514). Closed weights: ranked by its LMArena score, with no size or downloads to show.1406
84GPT-5.4 mini (High). Closed weights: ranked by its LMArena score, with no size or downloads to show.1405
85Gemini 2.5 Flash. Closed weights: ranked by its LMArena score, with no size or downloads to show.1405
86GPT-6 Luna (Max). Closed weights: ranked by its LMArena score, with no size or downloads to show.1405
87GPT-4.5 Preview (2025-02-27). Closed weights: ranked by its LMArena score, with no size or downloads to show.1404
88ChatGPT-4o Latest (20250326). Closed weights: ranked by its LMArena score, with no size or downloads to show.1403
89GPT-5.2. Closed weights: ranked by its LMArena score, with no size or downloads to show.1403
90Grok 4.7 (xHigh). Closed weights: ranked by its LMArena score, with no size or downloads to show.1403
91ERNIE-5.0-Preview (1203). Closed weights: ranked by its LMArena score, with no size or downloads to show.1401
92Grok 4.1. Closed weights: ranked by its LMArena score, with no size or downloads to show.1400
93Mistral Medium 3.1 (2508). Closed weights: ranked by its LMArena score, with no size or downloads to show.1398
94Qwen3-Max (2025-09-23). Closed weights: ranked by its LMArena score, with no size or downloads to show.1397
95Hunyuan Vision 1.5 Thinking. Closed weights: ranked by its LMArena score, with no size or downloads to show.1397
96Grok 4.1 (Thinking). Closed weights: ranked by its LMArena score, with no size or downloads to show.1395
97Gemini 2.5 Flash Preview (09-2025). Closed weights: ranked by its LMArena score, with no size or downloads to show.1394
98ERNIE-5.0-Preview (1022). Closed weights: ranked by its LMArena score, with no size or downloads to show.1393
99GPT-5 (High). Closed weights: ranked by its LMArena score, with no size or downloads to show.1388
100Grok 4 Fast (Non-Reasoning). Closed weights: ranked by its LMArena score, with no size or downloads to show.1387
101Grok 4 (0709). Closed weights: ranked by its LMArena score, with no size or downloads to show.1387
102amazon-nova-experimental-chat (12-10). Closed weights: ranked by its LMArena score, with no size or downloads to show.1386
103amazon-nova-experimental-chat (11-10). Closed weights: ranked by its LMArena score, with no size or downloads to show.1386
104Grok 4 Fast (Reasoning). Closed weights: ranked by its LMArena score, with no size or downloads to show.1382
105GPT-5 Chat. Closed weights: ranked by its LMArena score, with no size or downloads to show.1381
106amazon-nova-experimental-chat (26-01-10). Closed weights: ranked by its LMArena score, with no size or downloads to show.1380
107Gemini 3.1 Flash-Lite Preview. Closed weights: ranked by its LMArena score, with no size or downloads to show.1378
108GPT-5.3 Chat. Closed weights: ranked by its LMArena score, with no size or downloads to show.1378
109Grok 4.1 Fast (Reasoning). Closed weights: ranked by its LMArena score, with no size or downloads to show.1376
110Claude Sonnet 4 (Thinking 32K, 20250514). Closed weights: ranked by its LMArena score, with no size or downloads to show.1376
111Hunyuan T1 (20250711). Closed weights: ranked by its LMArena score, with no size or downloads to show.1375
112Solar Pro 4. Closed weights: ranked by its LMArena score, with no size or downloads to show.1375
113Qwen3.5-Flash. Closed weights: ranked by its LMArena score, with no size or downloads to show.1375
114Claude Opus 4 (20250514). Closed weights: ranked by its LMArena score, with no size or downloads to show.1373
115o3 (2025-04-16). Closed weights: ranked by its LMArena score, with no size or downloads to show.1368
116o1 (2024-12-17). Closed weights: ranked by its LMArena score, with no size or downloads to show.1367
117GPT-4.1 (2025-04-14). Closed weights: ranked by its LMArena score, with no size or downloads to show.1367
118Gemini 2.5 Flash-Lite Preview (Thinking, 06-17). Closed weights: ranked by its LMArena score, with no size or downloads to show.1366
119Grok 4.3. Closed weights: ranked by its LMArena score, with no size or downloads to show.1366
120amazon-nova-experimental-chat (10-20). Closed weights: ranked by its LMArena score, with no size or downloads to show.1365
121GPT-5.4 nano (High). Closed weights: ranked by its LMArena score, with no size or downloads to show.1361
122GPT-5 mini (High). Closed weights: ranked by its LMArena score, with no size or downloads to show.1357
123Grok 3 Mini (High). Closed weights: ranked by its LMArena score, with no size or downloads to show.1356
124Gemini 2.5 Flash-Lite Preview (Non-Thinking, 09-2025). Closed weights: ranked by its LMArena score, with no size or downloads to show.1355
125Claude Sonnet 4 (20250514). Closed weights: ranked by its LMArena score, with no size or downloads to show.1352
126Claude 3.7 Sonnet (Thinking 32K, 20250219). Closed weights: ranked by its LMArena score, with no size or downloads to show.1352
127Grok 3 Mini Beta. Closed weights: ranked by its LMArena score, with no size or downloads to show.1346
128Hunyuan TurboS (20250416). Closed weights: ranked by its LMArena score, with no size or downloads to show.1344
129o1-preview. Closed weights: ranked by its LMArena score, with no size or downloads to show.1342
130Mistral Medium 3 (2505). Closed weights: ranked by its LMArena score, with no size or downloads to show.1338
131o3-mini (High). Closed weights: ranked by its LMArena score, with no size or downloads to show.1337
132Gemini 2.0 Flash (001). Closed weights: ranked by its LMArena score, with no size or downloads to show.1336
133Amazon Nova 2 Lite. Closed weights: ranked by its LMArena score, with no size or downloads to show.1335
134Qwen2.5-Max. Closed weights: ranked by its LMArena score, with no size or downloads to show.1335
135GPT-4.1 mini (2025-04-14). Closed weights: ranked by its LMArena score, with no size or downloads to show.1333
136Mercury 2. Closed weights: ranked by its LMArena score, with no size or downloads to show.1329
137Claude 3.7 Sonnet (20250219). Closed weights: ranked by its LMArena score, with no size or downloads to show.1324
138o4-mini (2025-04-16). Closed weights: ranked by its LMArena score, with no size or downloads to show.1320
139Hunyuan TurboS (20250226). Closed weights: ranked by its LMArena score, with no size or downloads to show.1316
140o3-mini. Closed weights: ranked by its LMArena score, with no size or downloads to show.1315
141amazon-nova-experimental-chat (10-09). Closed weights: ranked by its LMArena score, with no size or downloads to show.1314
142Step-1o Turbo (202506). Closed weights: ranked by its LMArena score, with no size or downloads to show.1310
143GPT-5 nano (High). Closed weights: ranked by its LMArena score, with no size or downloads to show.1306
144Gemini 2.0 Flash-Lite Preview (02-05). Closed weights: ranked by its LMArena score, with no size or downloads to show.1305
145o1-mini. Closed weights: ranked by its LMArena score, with no size or downloads to show.1304
146Qwen-Plus (0125). Closed weights: ranked by its LMArena score, with no size or downloads to show.1303
147Claude 3.5 Sonnet (20241022). Closed weights: ranked by its LMArena score, with no size or downloads to show.1297
148Gemini 1.5 Pro (002). Closed weights: ranked by its LMArena score, with no size or downloads to show.1297
149GLM-4-Plus (0111). Closed weights: ranked by its LMArena score, with no size or downloads to show.1292
150Step-2 16K Exp (202412). Closed weights: ranked by its LMArena score, with no size or downloads to show.1287
151Hunyuan Turbo (0110). Closed weights: ranked by its LMArena score, with no size or downloads to show.1278
152Yi Lightning. Closed weights: ranked by its LMArena score, with no size or downloads to show.1278
153GPT-4o (2024-05-13). Closed weights: ranked by its LMArena score, with no size or downloads to show.1278
154Hunyuan Large (2025-02-10). Closed weights: ranked by its LMArena score, with no size or downloads to show.1277
155Qwen2.5-Plus (1127). Closed weights: ranked by its LMArena score, with no size or downloads to show.1274
156Grok 2 (2024-08-13). Closed weights: ranked by its LMArena score, with no size or downloads to show.1270
157Claude 3.5 Sonnet (20240620). Closed weights: ranked by its LMArena score, with no size or downloads to show.1269
158GPT-4o (2024-08-06). Closed weights: ranked by its LMArena score, with no size or downloads to show.1267
159GPT-4.1 nano (2025-04-14). Closed weights: ranked by its LMArena score, with no size or downloads to show.1266
160GLM-4-Plus. Closed weights: ranked by its LMArena score, with no size or downloads to show.1264
161GPT-4o mini (2024-07-18). Closed weights: ranked by its LMArena score, with no size or downloads to show.1258
162Gemini 1.5 Flash (002). Closed weights: ranked by its LMArena score, with no size or downloads to show.1257
163Gemini 1.5 Pro (001). Closed weights: ranked by its LMArena score, with no size or downloads to show.1254
164Magistral Medium (2506). Closed weights: ranked by its LMArena score, with no size or downloads to show.1253
165Gemini Advanced (0514). Closed weights: ranked by its LMArena score, with no size or downloads to show.1253
166Hunyuan Large Vision. Closed weights: ranked by its LMArena score, with no size or downloads to show.1250
167GPT-4 Turbo (2024-04-09). Closed weights: ranked by its LMArena score, with no size or downloads to show.1249
168Claude 3 Opus (20240229). Closed weights: ranked by its LMArena score, with no size or downloads to show.1248
169Hunyuan Standard (2025-02-10). Closed weights: ranked by its LMArena score, with no size or downloads to show.1245
170Grok 2 mini (2024-08-13). Closed weights: ranked by its LMArena score, with no size or downloads to show.1245
171Claude 3.5 Haiku (20241022). Closed weights: ranked by its LMArena score, with no size or downloads to show.1241
172GPT-4 Turbo Preview (1106). Closed weights: ranked by its LMArena score, with no size or downloads to show.1240
173Mercury. Closed weights: ranked by its LMArena score, with no size or downloads to show.1239
174Amazon Nova Pro 1.0. Closed weights: ranked by its LMArena score, with no size or downloads to show.1235
175GPT-4 Turbo Preview (0125). Closed weights: ranked by its LMArena score, with no size or downloads to show.1235
176Gemini 1.5 Flash (001). Closed weights: ranked by its LMArena score, with no size or downloads to show.1212
177Reka Core (20240904). Closed weights: ranked by its LMArena score, with no size or downloads to show.1212
178Amazon Nova Lite 1.0. Closed weights: ranked by its LMArena score, with no size or downloads to show.1205
179GLM-4 (0520). Closed weights: ranked by its LMArena score, with no size or downloads to show.1203
180Hunyuan Standard 256K. Closed weights: ranked by its LMArena score, with no size or downloads to show.1202
181GPT-4 (0314). Closed weights: ranked by its LMArena score, with no size or downloads to show.1201
182Claude 3 Sonnet (20240229). Closed weights: ranked by its LMArena score, with no size or downloads to show.1199
183Gemini 1.5 Flash-8B (001). Closed weights: ranked by its LMArena score, with no size or downloads to show.1199
184GPT-4 (0613). Closed weights: ranked by its LMArena score, with no size or downloads to show.1188
185Reka Flash (20240904). Closed weights: ranked by its LMArena score, with no size or downloads to show.1185
186Amazon Nova Micro 1.0. Closed weights: ranked by its LMArena score, with no size or downloads to show.1174
187Claude 3 Haiku (20240307). Closed weights: ranked by its LMArena score, with no size or downloads to show.1173
188Mistral Large (2402). Closed weights: ranked by its LMArena score, with no size or downloads to show.1169
189Mistral Medium. Closed weights: ranked by its LMArena score, with no size or downloads to show.1152
190Reka Flash 21B (Online, 20240226). Closed weights: ranked by its LMArena score, with no size or downloads to show.1129
191Reka Flash 21B (20240226). Closed weights: ranked by its LMArena score, with no size or downloads to show.1121
192GPT-3.5 Turbo (0125). Closed weights: ranked by its LMArena score, with no size or downloads to show.1119
193Gemini Pro (Dev API). Closed weights: ranked by its LMArena score, with no size or downloads to show.1114
194Gemini Pro. Closed weights: ranked by its LMArena score, with no size or downloads to show.1110
195GPT-3.5 Turbo (1106). Closed weights: ranked by its LMArena score, with no size or downloads to show.1093
196PaLM 2. Closed weights: ranked by its LMArena score, with no size or downloads to show.1010
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.