Model leaderboard

Arena scores (LMArena)

196 models in hard prompts 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.1005
195Gemini Pro. Closed weights: ranked by its LMArena score, with no size or downloads to show.1094
194GPT-3.5 Turbo (1106). Closed weights: ranked by its LMArena score, with no size or downloads to show.1098
193GPT-3.5 Turbo (0125). Closed weights: ranked by its LMArena score, with no size or downloads to show.1108
192Gemini Pro (Dev API). Closed weights: ranked by its LMArena score, with no size or downloads to show.1109
191Reka Flash 21B (20240226). Closed weights: ranked by its LMArena score, with no size or downloads to show.1136
190Reka Flash 21B (Online, 20240226). Closed weights: ranked by its LMArena score, with no size or downloads to show.1137
189Mistral Medium. Closed weights: ranked by its LMArena score, with no size or downloads to show.1149
188Mistral Large (2402). Closed weights: ranked by its LMArena score, with no size or downloads to show.1167
187Claude 3 Haiku (20240307). Closed weights: ranked by its LMArena score, with no size or downloads to show.1174
186GPT-4 (0613). Closed weights: ranked by its LMArena score, with no size or downloads to show.1174
185Reka Flash (20240904). Closed weights: ranked by its LMArena score, with no size or downloads to show.1181
184Amazon Nova Micro 1.0. Closed weights: ranked by its LMArena score, with no size or downloads to show.1191
183Claude 3 Sonnet (20240229). Closed weights: ranked by its LMArena score, with no size or downloads to show.1197
182GPT-4 (0314). Closed weights: ranked by its LMArena score, with no size or downloads to show.1200
181Gemini 1.5 Flash-8B (001). Closed weights: ranked by its LMArena score, with no size or downloads to show.1209
180Reka Core (20240904). Closed weights: ranked by its LMArena score, with no size or downloads to show.1211
179GLM-4 (0520). Closed weights: ranked by its LMArena score, with no size or downloads to show.1212
178Hunyuan Standard 256K. Closed weights: ranked by its LMArena score, with no size or downloads to show.1218
177Gemini 1.5 Flash (001). Closed weights: ranked by its LMArena score, with no size or downloads to show.1220
176Amazon Nova Lite 1.0. Closed weights: ranked by its LMArena score, with no size or downloads to show.1220
175GPT-4 Turbo Preview (0125). Closed weights: ranked by its LMArena score, with no size or downloads to show.1238
174GPT-4 Turbo Preview (1106). Closed weights: ranked by its LMArena score, with no size or downloads to show.1241
173Claude 3 Opus (20240229). Closed weights: ranked by its LMArena score, with no size or downloads to show.1245
172Amazon Nova Pro 1.0. Closed weights: ranked by its LMArena score, with no size or downloads to show.1245
171Gemini Advanced (0514). Closed weights: ranked by its LMArena score, with no size or downloads to show.1248
170Claude 3.5 Haiku (20241022). Closed weights: ranked by its LMArena score, with no size or downloads to show.1251
169GPT-4 Turbo (2024-04-09). Closed weights: ranked by its LMArena score, with no size or downloads to show.1251
168Gemini 1.5 Pro (001). Closed weights: ranked by its LMArena score, with no size or downloads to show.1255
167Grok 2 mini (2024-08-13). Closed weights: ranked by its LMArena score, with no size or downloads to show.1255
166Hunyuan Large Vision. Closed weights: ranked by its LMArena score, with no size or downloads to show.1256
165Gemini 1.5 Flash (002). Closed weights: ranked by its LMArena score, with no size or downloads to show.1257
164GPT-4o (2024-08-06). Closed weights: ranked by its LMArena score, with no size or downloads to show.1264
163Hunyuan Standard (2025-02-10). Closed weights: ranked by its LMArena score, with no size or downloads to show.1264
162Magistral Medium (2506). Closed weights: ranked by its LMArena score, with no size or downloads to show.1267
161GPT-4o mini (2024-07-18). Closed weights: ranked by its LMArena score, with no size or downloads to show.1267
160Grok 2 (2024-08-13). Closed weights: ranked by its LMArena score, with no size or downloads to show.1272
159GLM-4-Plus. Closed weights: ranked by its LMArena score, with no size or downloads to show.1273
158Claude 3.5 Sonnet (20240620). Closed weights: ranked by its LMArena score, with no size or downloads to show.1275
157GPT-4o (2024-05-13). Closed weights: ranked by its LMArena score, with no size or downloads to show.1281
156Mercury. Closed weights: ranked by its LMArena score, with no size or downloads to show.1284
155GPT-4.1 nano (2025-04-14). Closed weights: ranked by its LMArena score, with no size or downloads to show.1286
154Hunyuan Large (2025-02-10). Closed weights: ranked by its LMArena score, with no size or downloads to show.1286
153GLM-4-Plus (0111). Closed weights: ranked by its LMArena score, with no size or downloads to show.1293
152Gemini 1.5 Pro (002). Closed weights: ranked by its LMArena score, with no size or downloads to show.1296
151Step-2 16K Exp (202412). Closed weights: ranked by its LMArena score, with no size or downloads to show.1299
150Qwen2.5-Plus (1127). Closed weights: ranked by its LMArena score, with no size or downloads to show.1299
149Yi Lightning. Closed weights: ranked by its LMArena score, with no size or downloads to show.1302
148Claude 3.5 Sonnet (20241022). Closed weights: ranked by its LMArena score, with no size or downloads to show.1305
147Hunyuan Turbo (0110). Closed weights: ranked by its LMArena score, with no size or downloads to show.1308
146Claude 3.7 Sonnet (20250219). Closed weights: ranked by its LMArena score, with no size or downloads to show.1315
145Qwen-Plus (0125). Closed weights: ranked by its LMArena score, with no size or downloads to show.1316
144Gemini 2.0 Flash-Lite Preview (02-05). Closed weights: ranked by its LMArena score, with no size or downloads to show.1324
143Hunyuan TurboS (20250226). Closed weights: ranked by its LMArena score, with no size or downloads to show.1325
142GPT-5 nano (High). Closed weights: ranked by its LMArena score, with no size or downloads to show.1328
141o3-mini. Closed weights: ranked by its LMArena score, with no size or downloads to show.1333
140o1-mini. Closed weights: ranked by its LMArena score, with no size or downloads to show.1333
139Claude 3.7 Sonnet (Thinking 32K, 20250219). Closed weights: ranked by its LMArena score, with no size or downloads to show.1333
138Step-1o Turbo (202506). Closed weights: ranked by its LMArena score, with no size or downloads to show.1335
137Gemini 2.0 Flash (001). Closed weights: ranked by its LMArena score, with no size or downloads to show.1346
136GPT-4.1 mini (2025-04-14). Closed weights: ranked by its LMArena score, with no size or downloads to show.1349
135o4-mini (2025-04-16). Closed weights: ranked by its LMArena score, with no size or downloads to show.1350
134o1-preview. Closed weights: ranked by its LMArena score, with no size or downloads to show.1354
133Claude Sonnet 4 (20250514). Closed weights: ranked by its LMArena score, with no size or downloads to show.1355
132amazon-nova-experimental-chat (10-09). Closed weights: ranked by its LMArena score, with no size or downloads to show.1355
131Qwen2.5-Max. Closed weights: ranked by its LMArena score, with no size or downloads to show.1360
130Mercury 2. Closed weights: ranked by its LMArena score, with no size or downloads to show.1362
129Grok 3 Mini Beta. Closed weights: ranked by its LMArena score, with no size or downloads to show.1364
128Amazon Nova 2 Lite. Closed weights: ranked by its LMArena score, with no size or downloads to show.1364
127Mistral Medium 3 (2505). Closed weights: ranked by its LMArena score, with no size or downloads to show.1364
126o3-mini (High). Closed weights: ranked by its LMArena score, with no size or downloads to show.1365
125o1 (2024-12-17). Closed weights: ranked by its LMArena score, with no size or downloads to show.1371
124Claude Sonnet 4 (Thinking 32K, 20250514). Closed weights: ranked by its LMArena score, with no size or downloads to show.1372
123Gemini 2.5 Flash-Lite Preview (Thinking, 06-17). Closed weights: ranked by its LMArena score, with no size or downloads to show.1374
122Hunyuan TurboS (20250416). Closed weights: ranked by its LMArena score, with no size or downloads to show.1374
121Grok 3 Mini (High). Closed weights: ranked by its LMArena score, with no size or downloads to show.1374
120Claude Opus 4 (20250514). Closed weights: ranked by its LMArena score, with no size or downloads to show.1376
119Gemini 2.5 Flash-Lite Preview (Non-Thinking, 09-2025). Closed weights: ranked by its LMArena score, with no size or downloads to show.1377
118GPT-5.4 nano (High). Closed weights: ranked by its LMArena score, with no size or downloads to show.1380
117GPT-5 mini (High). Closed weights: ranked by its LMArena score, with no size or downloads to show.1380
116GPT-4.1 (2025-04-14). Closed weights: ranked by its LMArena score, with no size or downloads to show.1384
115amazon-nova-experimental-chat (10-20). Closed weights: ranked by its LMArena score, with no size or downloads to show.1396
114Grok 4.3. Closed weights: ranked by its LMArena score, with no size or downloads to show.1396
113GPT-5.3 Chat. Closed weights: ranked by its LMArena score, with no size or downloads to show.1399
112Hunyuan T1 (20250711). Closed weights: ranked by its LMArena score, with no size or downloads to show.1399
111Claude Opus 4 (Thinking 16K, 20250514). Closed weights: ranked by its LMArena score, with no size or downloads to show.1399
110Solar Pro 4. Closed weights: ranked by its LMArena score, with no size or downloads to show.1400
109o3 (2025-04-16). Closed weights: ranked by its LMArena score, with no size or downloads to show.1402
108GPT-4.5 Preview (2025-02-27). Closed weights: ranked by its LMArena score, with no size or downloads to show.1403
107Qwen3.5-Flash. Closed weights: ranked by its LMArena score, with no size or downloads to show.1404
106Grok 4 Fast (Reasoning). Closed weights: ranked by its LMArena score, with no size or downloads to show.1404
105GPT-5 Chat. Closed weights: ranked by its LMArena score, with no size or downloads to show.1404
104Gemini 3.1 Flash-Lite Preview. Closed weights: ranked by its LMArena score, with no size or downloads to show.1408
103Grok 4.1 Fast (Reasoning). Closed weights: ranked by its LMArena score, with no size or downloads to show.1408
102GPT-6 Luna (Max). Closed weights: ranked by its LMArena score, with no size or downloads to show.1408
101Grok 4 (0709). Closed weights: ranked by its LMArena score, with no size or downloads to show.1409
100Gemini 2.5 Flash Preview (09-2025). Closed weights: ranked by its LMArena score, with no size or downloads to show.1409
99Grok 4 Fast (Non-Reasoning). Closed weights: ranked by its LMArena score, with no size or downloads to show.1412
98amazon-nova-experimental-chat (26-01-10). Closed weights: ranked by its LMArena score, with no size or downloads to show.1414
97Grok 4.7 (xHigh). Closed weights: ranked by its LMArena score, with no size or downloads to show.1415
96Claude Haiku 5.5 (High). Closed weights: ranked by its LMArena score, with no size or downloads to show.1416
95GPT-5 (High). Closed weights: ranked by its LMArena score, with no size or downloads to show.1416
94Hunyuan Vision 1.5 Thinking. Closed weights: ranked by its LMArena score, with no size or downloads to show.1417
93GPT-6.2 Sol (Max). Closed weights: ranked by its LMArena score, with no size or downloads to show.1419
92Claude Haiku 4.5 (20251001). Closed weights: ranked by its LMArena score, with no size or downloads to show.1420
91ERNIE-5.0-Preview (1022). Closed weights: ranked by its LMArena score, with no size or downloads to show.1420
90GPT-6 Sol (Max). Closed weights: ranked by its LMArena score, with no size or downloads to show.1421
89amazon-nova-experimental-chat (11-10). Closed weights: ranked by its LMArena score, with no size or downloads to show.1422
88Gemini 2.5 Flash. Closed weights: ranked by its LMArena score, with no size or downloads to show.1422
87Qwen3-Max (2025-09-23). Closed weights: ranked by its LMArena score, with no size or downloads to show.1423
86ChatGPT-4o Latest (20250326). Closed weights: ranked by its LMArena score, with no size or downloads to show.1424
85GPT-5.4 mini (High). Closed weights: ranked by its LMArena score, with no size or downloads to show.1425
84GPT-6.2 Astra (Max). Closed weights: ranked by its LMArena score, with no size or downloads to show.1425
83Mistral Medium 3.1 (2508). Closed weights: ranked by its LMArena score, with no size or downloads to show.1426
82GPT-5.2. Closed weights: ranked by its LMArena score, with no size or downloads to show.1427
81GPT-5.5 Instant. Closed weights: ranked by its LMArena score, with no size or downloads to show.1427
80amazon-nova-experimental-chat (12-10). Closed weights: ranked by its LMArena score, with no size or downloads to show.1427
79GPT-5.2 (High). Closed weights: ranked by its LMArena score, with no size or downloads to show.1428
78Grok 4.1 (Thinking). Closed weights: ranked by its LMArena score, with no size or downloads to show.1433
77Grok 3 Preview (02-24). Closed weights: ranked by its LMArena score, with no size or downloads to show.1434
76GPT-5.1. Closed weights: ranked by its LMArena score, with no size or downloads to show.1434
75Grok 4.1. Closed weights: ranked by its LMArena score, with no size or downloads to show.1436
74ERNIE-5.0-Preview (1203). Closed weights: ranked by its LMArena score, with no size or downloads to show.1438
73Gemini 3 Flash (Minimal). Closed weights: ranked by its LMArena score, with no size or downloads to show.1438
72LongCat-Flash-Chat Exp (2602). Closed weights: ranked by its LMArena score, with no size or downloads to show.1439
71Grok 4.20 Beta 1. Closed weights: ranked by its LMArena score, with no size or downloads to show.1441
70Gemini 3.5 Flash-Lite. Closed weights: ranked by its LMArena score, with no size or downloads to show.1441
69Claude Opus 4.1 (20250805). Closed weights: ranked by its LMArena score, with no size or downloads to show.1442
68Claude Opus 4.1 (Thinking 16K, 20250805). Closed weights: ranked by its LMArena score, with no size or downloads to show.1442
67MiMo-V2-Omni. Closed weights: ranked by its LMArena score, with no size or downloads to show.1444
66GPT-5.2 Chat (20260210). Closed weights: ranked by its LMArena score, with no size or downloads to show.1445
65ERNIE 5.0 (0110). Closed weights: ranked by its LMArena score, with no size or downloads to show.1445
64Grok 4.6 (High). Closed weights: ranked by its LMArena score, with no size or downloads to show.1448
63Qwen3.6-Plus. Closed weights: ranked by its LMArena score, with no size or downloads to show.1448
62Qwen3-Max-Preview. Closed weights: ranked by its LMArena score, with no size or downloads to show.1448
61Grok 4.20 Multi-Agent Beta (0309). Closed weights: ranked by its LMArena score, with no size or downloads to show.1449
60GPT-6.1 Terra (Max). Closed weights: ranked by its LMArena score, with no size or downloads to show.1451
59Grok 4.20 Beta (Reasoning, 0309). Closed weights: ranked by its LMArena score, with no size or downloads to show.1452
58GPT-5.6 Luna (xHigh). Closed weights: ranked by its LMArena score, with no size or downloads to show.1452
57Dola Seed 2.0 Pro. Closed weights: ranked by its LMArena score, with no size or downloads to show.1453
56Gemini 2.5 Pro. Closed weights: ranked by its LMArena score, with no size or downloads to show.1455
55Qwen3.6-Max-Preview. Closed weights: ranked by its LMArena score, with no size or downloads to show.1456
54GPT-5.1 (High). Closed weights: ranked by its LMArena score, with no size or downloads to show.1457
53MiMo-V2-Pro. Closed weights: ranked by its LMArena score, with no size or downloads to show.1458
52Qwen3.7-Plus. Closed weights: ranked by its LMArena score, with no size or downloads to show.1459
51amazon-nova-experimental-chat (26-02-10). Closed weights: ranked by its LMArena score, with no size or downloads to show.1459
50Claude Sonnet 5 (High). Closed weights: ranked by its LMArena score, with no size or downloads to show.1461
49Claude Sonnet 4.5 (High, 32K, 20250929). Closed weights: ranked by its LMArena score, with no size or downloads to show.1461
48Grok 4.5. Closed weights: ranked by its LMArena score, with no size or downloads to show.1462
47Claude Sonnet 4.5 (20250929). Closed weights: ranked by its LMArena score, with no size or downloads to show.1462
46GPT-6 Astra (Max). Closed weights: ranked by its LMArena score, with no size or downloads to show.1463
45Step 5 Preview. Closed weights: ranked by its LMArena score, with no size or downloads to show.1463
44Gemini 3 Flash. Closed weights: ranked by its LMArena score, with no size or downloads to show.1465
43GPT-6.1 Sol (Max). Closed weights: ranked by its LMArena score, with no size or downloads to show.1468
42GPT-5.4. Closed weights: ranked by its LMArena score, with no size or downloads to show.1469
41GPT-5.6 Terra (xHigh). Closed weights: ranked by its LMArena score, with no size or downloads to show.1470
40Claude Opus 4.5 (High, 32K, 20251101). Closed weights: ranked by its LMArena score, with no size or downloads to show.1473
39Claude Opus 4.8. Closed weights: ranked by its LMArena score, with no size or downloads to show.1473
38Muse Spark. Closed weights: ranked by its LMArena score, with no size or downloads to show.1474
37Claude Opus 4.5 (20251101). Closed weights: ranked by its LMArena score, with no size or downloads to show.1476
36Gemini 3 Pro. Closed weights: ranked by its LMArena score, with no size or downloads to show.1480
35ERNIE 5.1. Closed weights: ranked by its LMArena score, with no size or downloads to show.1481
34Qwen3.7-Max-Preview. Closed weights: ranked by its LMArena score, with no size or downloads to show.1481
33Claude Opus 4.8 (High). Closed weights: ranked by its LMArena score, with no size or downloads to show.1482
32GPT-5.6 Sol (xHigh). Closed weights: ranked by its LMArena score, with no size or downloads to show.1483
31Qwen3.5-Max-Preview. Closed weights: ranked by its LMArena score, with no size or downloads to show.1484
30Claude Fable 5.2 (Max). Closed weights: ranked by its LMArena score, with no size or downloads to show.1484
29Claude Sonnet 4.6. Closed weights: ranked by its LMArena score, with no size or downloads to show.1484
28Gemini 3.1 Pro Preview. Closed weights: ranked by its LMArena score, with no size or downloads to show.1485
27GPT-5.4 (High). Closed weights: ranked by its LMArena score, with no size or downloads to show.1485
26Gemini 3.5 Flash (Medium). Closed weights: ranked by its LMArena score, with no size or downloads to show.1485
25GPT-5.5. Closed weights: ranked by its LMArena score, with no size or downloads to show.1485
24Gemini 3.6 Flash (High). Closed weights: ranked by its LMArena score, with no size or downloads to show.1486
23Muse Spark 1.1. Closed weights: ranked by its LMArena score, with no size or downloads to show.1486
22Claude Sonnet 5.5 (xHigh). Closed weights: ranked by its LMArena score, with no size or downloads to show.1487
21GPT-5.5 (High). Closed weights: ranked by its LMArena score, with no size or downloads to show.1488
20Gemini 3.5 Flash (High). Closed weights: ranked by its LMArena score, with no size or downloads to show.1489
19Muse Spark 1.2 (xHigh). Closed weights: ranked by its LMArena score, with no size or downloads to show.1493
18Gemini 3.7 Flash (High). Closed weights: ranked by its LMArena score, with no size or downloads to show.1498
17Claude Opus 4.7. Closed weights: ranked by its LMArena score, with no size or downloads to show.1500
16Qwen3.8-Max. Closed weights: ranked by its LMArena score, with no size or downloads to show.1500
15Muse Spark 1.3 (Max). Closed weights: ranked by its LMArena score, with no size or downloads to show.1504
14Claude Opus 4.7 (High). Closed weights: ranked by its LMArena score, with no size or downloads to show.1506
13Claude Fable 5 (High). Closed weights: ranked by its LMArena score, with no size or downloads to show.1508
12Gemini 3.8 Flash (High). Closed weights: ranked by its LMArena score, with no size or downloads to show.1509
11Muse Wonder (Max). Closed weights: ranked by its LMArena score, with no size or downloads to show.1514
10Gemini 4 Hydrogen (High). Closed weights: ranked by its LMArena score, with no size or downloads to show.1517
9Claude Opus 5 (High). Closed weights: ranked by its LMArena score, with no size or downloads to show.1522
8Claude Opus 4.6. Closed weights: ranked by its LMArena score, with no size or downloads to show.1522
7Claude Opus 4.6 (High). Closed weights: ranked by its LMArena score, with no size or downloads to show.1524
6Claude Opus 5 (Max). Closed weights: ranked by its LMArena score, with no size or downloads to show.1525
5Claude Fable 5.1 (Max). Closed weights: ranked by its LMArena score, with no size or downloads to show.1527
4Claude Opus 5.5 (High). Closed weights: ranked by its LMArena score, with no size or downloads to show.1531
3Gemini 4 Argon (High). Closed weights: ranked by its LMArena score, with no size or downloads to show.1542
2Gemini 4 Neon (High). Closed weights: ranked by its LMArena score, with no size or downloads to show.1547
1Gemini 4 Carbon (High). Closed weights: ranked by its LMArena score, with no size or downloads to show.1551
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.