Model leaderboard

Arena scores (LMArena)

196 models in creative writing 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.991
195GPT-3.5 Turbo (1106). Closed weights: ranked by its LMArena score, with no size or downloads to show.1035
194GPT-3.5 Turbo (0125). Closed weights: ranked by its LMArena score, with no size or downloads to show.1092
193Gemini Pro. Closed weights: ranked by its LMArena score, with no size or downloads to show.1104
192Reka Flash 21B (20240226). Closed weights: ranked by its LMArena score, with no size or downloads to show.1124
191Gemini Pro (Dev API). Closed weights: ranked by its LMArena score, with no size or downloads to show.1130
190Reka Flash 21B (Online, 20240226). Closed weights: ranked by its LMArena score, with no size or downloads to show.1130
189Claude 3 Haiku (20240307). Closed weights: ranked by its LMArena score, with no size or downloads to show.1157
188Mistral Medium. Closed weights: ranked by its LMArena score, with no size or downloads to show.1158
187Mistral Large (2402). Closed weights: ranked by its LMArena score, with no size or downloads to show.1161
186Hunyuan Standard 256K. Closed weights: ranked by its LMArena score, with no size or downloads to show.1165
185Amazon Nova Micro 1.0. Closed weights: ranked by its LMArena score, with no size or downloads to show.1172
184Claude 3 Sonnet (20240229). Closed weights: ranked by its LMArena score, with no size or downloads to show.1186
183Mercury. Closed weights: ranked by its LMArena score, with no size or downloads to show.1187
182GPT-4 (0314). Closed weights: ranked by its LMArena score, with no size or downloads to show.1190
181GPT-4 (0613). Closed weights: ranked by its LMArena score, with no size or downloads to show.1191
180Amazon Nova Lite 1.0. Closed weights: ranked by its LMArena score, with no size or downloads to show.1197
179GLM-4 (0520). Closed weights: ranked by its LMArena score, with no size or downloads to show.1198
178Reka Flash (20240904). Closed weights: ranked by its LMArena score, with no size or downloads to show.1202
177Amazon Nova Pro 1.0. Closed weights: ranked by its LMArena score, with no size or downloads to show.1212
176Gemini 1.5 Flash-8B (001). Closed weights: ranked by its LMArena score, with no size or downloads to show.1217
175Gemini 1.5 Flash (001). Closed weights: ranked by its LMArena score, with no size or downloads to show.1222
174GPT-4 Turbo Preview (0125). Closed weights: ranked by its LMArena score, with no size or downloads to show.1232
173Claude 3.5 Haiku (20241022). Closed weights: ranked by its LMArena score, with no size or downloads to show.1232
172Claude 3 Opus (20240229). Closed weights: ranked by its LMArena score, with no size or downloads to show.1235
171Reka Core (20240904). Closed weights: ranked by its LMArena score, with no size or downloads to show.1236
170Claude 3.5 Sonnet (20240620). Closed weights: ranked by its LMArena score, with no size or downloads to show.1238
169Grok 2 mini (2024-08-13). Closed weights: ranked by its LMArena score, with no size or downloads to show.1241
168Hunyuan Standard (2025-02-10). Closed weights: ranked by its LMArena score, with no size or downloads to show.1242
167o1-mini. Closed weights: ranked by its LMArena score, with no size or downloads to show.1244
166GPT-4 Turbo Preview (1106). Closed weights: ranked by its LMArena score, with no size or downloads to show.1244
165Magistral Medium (2506). Closed weights: ranked by its LMArena score, with no size or downloads to show.1245
164Hunyuan Large Vision. Closed weights: ranked by its LMArena score, with no size or downloads to show.1248
163GPT-5 nano (High). Closed weights: ranked by its LMArena score, with no size or downloads to show.1250
162GPT-4.1 nano (2025-04-14). Closed weights: ranked by its LMArena score, with no size or downloads to show.1260
161Qwen2.5-Plus (1127). Closed weights: ranked by its LMArena score, with no size or downloads to show.1262
160GLM-4-Plus. Closed weights: ranked by its LMArena score, with no size or downloads to show.1264
159Hunyuan Large (2025-02-10). Closed weights: ranked by its LMArena score, with no size or downloads to show.1264
158GPT-4o mini (2024-07-18). Closed weights: ranked by its LMArena score, with no size or downloads to show.1268
157GPT-4 Turbo (2024-04-09). Closed weights: ranked by its LMArena score, with no size or downloads to show.1268
156Hunyuan Turbo (0110). Closed weights: ranked by its LMArena score, with no size or downloads to show.1269
155Hunyuan TurboS (20250226). Closed weights: ranked by its LMArena score, with no size or downloads to show.1270
154Gemini 1.5 Pro (001). Closed weights: ranked by its LMArena score, with no size or downloads to show.1272
153o3-mini. Closed weights: ranked by its LMArena score, with no size or downloads to show.1273
152GPT-4o (2024-08-06). Closed weights: ranked by its LMArena score, with no size or downloads to show.1274
151Yi Lightning. Closed weights: ranked by its LMArena score, with no size or downloads to show.1280
150Gemini Advanced (0514). Closed weights: ranked by its LMArena score, with no size or downloads to show.1284
149Grok 2 (2024-08-13). Closed weights: ranked by its LMArena score, with no size or downloads to show.1284
148Gemini 1.5 Flash (002). Closed weights: ranked by its LMArena score, with no size or downloads to show.1285
147o3-mini (High). Closed weights: ranked by its LMArena score, with no size or downloads to show.1286
146Mercury 2. Closed weights: ranked by its LMArena score, with no size or downloads to show.1287
145GPT-4o (2024-05-13). Closed weights: ranked by its LMArena score, with no size or downloads to show.1291
144Amazon Nova 2 Lite. Closed weights: ranked by its LMArena score, with no size or downloads to show.1292
143Claude 3.5 Sonnet (20241022). Closed weights: ranked by its LMArena score, with no size or downloads to show.1292
142Qwen-Plus (0125). Closed weights: ranked by its LMArena score, with no size or downloads to show.1292
141o4-mini (2025-04-16). Closed weights: ranked by its LMArena score, with no size or downloads to show.1294
140GPT-4.1 mini (2025-04-14). Closed weights: ranked by its LMArena score, with no size or downloads to show.1299
139amazon-nova-experimental-chat (10-09). Closed weights: ranked by its LMArena score, with no size or downloads to show.1306
138Step-1o Turbo (202506). Closed weights: ranked by its LMArena score, with no size or downloads to show.1307
137GLM-4-Plus (0111). Closed weights: ranked by its LMArena score, with no size or downloads to show.1311
136GPT-5.4 nano (High). Closed weights: ranked by its LMArena score, with no size or downloads to show.1314
135amazon-nova-experimental-chat (10-20). Closed weights: ranked by its LMArena score, with no size or downloads to show.1316
134Claude 3.7 Sonnet (20250219). Closed weights: ranked by its LMArena score, with no size or downloads to show.1317
133Solar Pro 4. Closed weights: ranked by its LMArena score, with no size or downloads to show.1317
132o1-preview. Closed weights: ranked by its LMArena score, with no size or downloads to show.1318
131Gemini 2.0 Flash-Lite Preview (02-05). Closed weights: ranked by its LMArena score, with no size or downloads to show.1319
130GPT-5 mini (High). Closed weights: ranked by its LMArena score, with no size or downloads to show.1325
129Step-2 16K Exp (202412). Closed weights: ranked by its LMArena score, with no size or downloads to show.1328
128amazon-nova-experimental-chat (26-01-10). Closed weights: ranked by its LMArena score, with no size or downloads to show.1328
127Claude 3.7 Sonnet (Thinking 32K, 20250219). Closed weights: ranked by its LMArena score, with no size or downloads to show.1332
126Gemini 1.5 Pro (002). Closed weights: ranked by its LMArena score, with no size or downloads to show.1333
125Claude Haiku 5.5 (High). Closed weights: ranked by its LMArena score, with no size or downloads to show.1334
124Grok 3 Mini (High). Closed weights: ranked by its LMArena score, with no size or downloads to show.1334
123Qwen2.5-Max. Closed weights: ranked by its LMArena score, with no size or downloads to show.1339
122Gemini 2.0 Flash (001). Closed weights: ranked by its LMArena score, with no size or downloads to show.1339
121Grok 3 Mini Beta. Closed weights: ranked by its LMArena score, with no size or downloads to show.1342
120Claude Sonnet 4 (20250514). Closed weights: ranked by its LMArena score, with no size or downloads to show.1342
119Qwen3.5-Flash. Closed weights: ranked by its LMArena score, with no size or downloads to show.1343
118Mistral Medium 3 (2505). Closed weights: ranked by its LMArena score, with no size or downloads to show.1344
117Claude Sonnet 4 (Thinking 32K, 20250514). Closed weights: ranked by its LMArena score, with no size or downloads to show.1345
116o1 (2024-12-17). Closed weights: ranked by its LMArena score, with no size or downloads to show.1347
115amazon-nova-experimental-chat (12-10). Closed weights: ranked by its LMArena score, with no size or downloads to show.1349
114amazon-nova-experimental-chat (11-10). Closed weights: ranked by its LMArena score, with no size or downloads to show.1350
113GPT-5.3 Chat. Closed weights: ranked by its LMArena score, with no size or downloads to show.1356
112Hunyuan TurboS (20250416). Closed weights: ranked by its LMArena score, with no size or downloads to show.1359
111o3 (2025-04-16). Closed weights: ranked by its LMArena score, with no size or downloads to show.1359
110Gemini 2.5 Flash-Lite Preview (Non-Thinking, 09-2025). Closed weights: ranked by its LMArena score, with no size or downloads to show.1359
109GPT-6 Luna (Max). Closed weights: ranked by its LMArena score, with no size or downloads to show.1360
108GPT-4.1 (2025-04-14). Closed weights: ranked by its LMArena score, with no size or downloads to show.1364
107GPT-5 (High). Closed weights: ranked by its LMArena score, with no size or downloads to show.1364
106GPT-5 Chat. Closed weights: ranked by its LMArena score, with no size or downloads to show.1365
105amazon-nova-experimental-chat (26-02-10). Closed weights: ranked by its LMArena score, with no size or downloads to show.1367
104Gemini 2.5 Flash-Lite Preview (Thinking, 06-17). Closed weights: ranked by its LMArena score, with no size or downloads to show.1367
103GPT-5.4 mini (High). Closed weights: ranked by its LMArena score, with no size or downloads to show.1370
102Claude Haiku 4.5 (20251001). Closed weights: ranked by its LMArena score, with no size or downloads to show.1370
101GPT-6 Sol (Max). Closed weights: ranked by its LMArena score, with no size or downloads to show.1371
100GPT-5.2. Closed weights: ranked by its LMArena score, with no size or downloads to show.1375
99Claude Opus 4 (20250514). Closed weights: ranked by its LMArena score, with no size or downloads to show.1375
98GPT-5.2 (High). Closed weights: ranked by its LMArena score, with no size or downloads to show.1375
97Grok 4 Fast (Reasoning). Closed weights: ranked by its LMArena score, with no size or downloads to show.1377
96Grok 4.3. Closed weights: ranked by its LMArena score, with no size or downloads to show.1380
95Qwen3-Max (2025-09-23). Closed weights: ranked by its LMArena score, with no size or downloads to show.1381
94Grok 4.7 (xHigh). Closed weights: ranked by its LMArena score, with no size or downloads to show.1384
93Gemini 2.5 Flash Preview (09-2025). Closed weights: ranked by its LMArena score, with no size or downloads to show.1386
92Grok 4 Fast (Non-Reasoning). Closed weights: ranked by its LMArena score, with no size or downloads to show.1386
91Claude Opus 4 (Thinking 16K, 20250514). Closed weights: ranked by its LMArena score, with no size or downloads to show.1387
90LongCat-Flash-Chat Exp (2602). Closed weights: ranked by its LMArena score, with no size or downloads to show.1387
89Hunyuan Vision 1.5 Thinking. Closed weights: ranked by its LMArena score, with no size or downloads to show.1389
88Mistral Medium 3.1 (2508). Closed weights: ranked by its LMArena score, with no size or downloads to show.1391
87MiMo-V2-Omni. Closed weights: ranked by its LMArena score, with no size or downloads to show.1393
86Hunyuan T1 (20250711). Closed weights: ranked by its LMArena score, with no size or downloads to show.1393
85GPT-4.5 Preview (2025-02-27). Closed weights: ranked by its LMArena score, with no size or downloads to show.1394
84Grok 4.1 Fast (Reasoning). Closed weights: ranked by its LMArena score, with no size or downloads to show.1395
83Grok 4 (0709). Closed weights: ranked by its LMArena score, with no size or downloads to show.1396
82GPT-5.6 Luna (xHigh). Closed weights: ranked by its LMArena score, with no size or downloads to show.1396
81GPT-5.2 Chat (20260210). Closed weights: ranked by its LMArena score, with no size or downloads to show.1399
80Gemini 2.5 Flash. Closed weights: ranked by its LMArena score, with no size or downloads to show.1400
79GPT-6.1 Terra (Max). Closed weights: ranked by its LMArena score, with no size or downloads to show.1401
78Gemini 3.1 Flash-Lite Preview. Closed weights: ranked by its LMArena score, with no size or downloads to show.1402
77Qwen3-Max-Preview. Closed weights: ranked by its LMArena score, with no size or downloads to show.1402
76GPT-6.2 Sol (Max). Closed weights: ranked by its LMArena score, with no size or downloads to show.1403
75GPT-5.1. Closed weights: ranked by its LMArena score, with no size or downloads to show.1403
74Qwen3.6-Plus. Closed weights: ranked by its LMArena score, with no size or downloads to show.1404
73Grok 4.1 (Thinking). Closed weights: ranked by its LMArena score, with no size or downloads to show.1404
72ChatGPT-4o Latest (20250326). Closed weights: ranked by its LMArena score, with no size or downloads to show.1405
71Dola Seed 2.0 Pro. Closed weights: ranked by its LMArena score, with no size or downloads to show.1407
70Claude Opus 4.1 (20250805). Closed weights: ranked by its LMArena score, with no size or downloads to show.1410
69Grok 4.1. Closed weights: ranked by its LMArena score, with no size or downloads to show.1411
68Claude Opus 4.1 (Thinking 16K, 20250805). Closed weights: ranked by its LMArena score, with no size or downloads to show.1412
67GPT-5.6 Terra (xHigh). Closed weights: ranked by its LMArena score, with no size or downloads to show.1414
66Claude Sonnet 5 (High). Closed weights: ranked by its LMArena score, with no size or downloads to show.1414
65Grok 3 Preview (02-24). Closed weights: ranked by its LMArena score, with no size or downloads to show.1414
64MiMo-V2-Pro. Closed weights: ranked by its LMArena score, with no size or downloads to show.1416
63Step 5 Preview. Closed weights: ranked by its LMArena score, with no size or downloads to show.1416
62GPT-6.2 Astra (Max). Closed weights: ranked by its LMArena score, with no size or downloads to show.1417
61ERNIE-5.0-Preview (1022). Closed weights: ranked by its LMArena score, with no size or downloads to show.1418
60GPT-5.5 Instant. Closed weights: ranked by its LMArena score, with no size or downloads to show.1418
59GPT-6.1 Sol (Max). Closed weights: ranked by its LMArena score, with no size or downloads to show.1421
58Gemini 3.5 Flash-Lite. Closed weights: ranked by its LMArena score, with no size or downloads to show.1421
57ERNIE-5.0-Preview (1203). Closed weights: ranked by its LMArena score, with no size or downloads to show.1421
56GPT-6 Astra (Max). Closed weights: ranked by its LMArena score, with no size or downloads to show.1421
55Claude Sonnet 4.5 (High, 32K, 20250929). Closed weights: ranked by its LMArena score, with no size or downloads to show.1424
54GPT-5.4. Closed weights: ranked by its LMArena score, with no size or downloads to show.1426
53ERNIE 5.0 (0110). Closed weights: ranked by its LMArena score, with no size or downloads to show.1426
52GPT-5.1 (High). Closed weights: ranked by its LMArena score, with no size or downloads to show.1427
51Grok 4.6 (High). Closed weights: ranked by its LMArena score, with no size or downloads to show.1428
50Grok 4.20 Beta (Reasoning, 0309). Closed weights: ranked by its LMArena score, with no size or downloads to show.1432
49Claude Sonnet 4.6. Closed weights: ranked by its LMArena score, with no size or downloads to show.1435
48Qwen3.6-Max-Preview. Closed weights: ranked by its LMArena score, with no size or downloads to show.1435
47Muse Spark 1.1. Closed weights: ranked by its LMArena score, with no size or downloads to show.1435
46Gemini 3 Flash (Minimal). Closed weights: ranked by its LMArena score, with no size or downloads to show.1435
45Grok 4.20 Multi-Agent Beta (0309). Closed weights: ranked by its LMArena score, with no size or downloads to show.1437
44GPT-5.4 (High). Closed weights: ranked by its LMArena score, with no size or downloads to show.1437
43Qwen3.7-Plus. Closed weights: ranked by its LMArena score, with no size or downloads to show.1438
42Grok 4.20 Beta 1. Closed weights: ranked by its LMArena score, with no size or downloads to show.1438
41ERNIE 5.1. Closed weights: ranked by its LMArena score, with no size or downloads to show.1441
40Grok 4.5. Closed weights: ranked by its LMArena score, with no size or downloads to show.1442
39Muse Spark 1.2 (xHigh). Closed weights: ranked by its LMArena score, with no size or downloads to show.1442
38Claude Opus 4.5 (20251101). Closed weights: ranked by its LMArena score, with no size or downloads to show.1442
37Claude Sonnet 4.5 (20250929). Closed weights: ranked by its LMArena score, with no size or downloads to show.1442
36Claude Opus 4.5 (High, 32K, 20251101). Closed weights: ranked by its LMArena score, with no size or downloads to show.1444
35Claude Opus 4.8. Closed weights: ranked by its LMArena score, with no size or downloads to show.1447
34Qwen3.7-Max-Preview. Closed weights: ranked by its LMArena score, with no size or downloads to show.1448
33GPT-5.6 Sol (xHigh). Closed weights: ranked by its LMArena score, with no size or downloads to show.1451
32GPT-5.5. Closed weights: ranked by its LMArena score, with no size or downloads to show.1451
31GPT-5.5 (High). Closed weights: ranked by its LMArena score, with no size or downloads to show.1453
30Gemini 2.5 Pro. Closed weights: ranked by its LMArena score, with no size or downloads to show.1454
29Claude Opus 4.8 (High). Closed weights: ranked by its LMArena score, with no size or downloads to show.1455
28Gemini 3 Flash. Closed weights: ranked by its LMArena score, with no size or downloads to show.1456
27Muse Spark. Closed weights: ranked by its LMArena score, with no size or downloads to show.1459
26Claude Sonnet 5.5 (xHigh). Closed weights: ranked by its LMArena score, with no size or downloads to show.1463
25Qwen3.5-Max-Preview. Closed weights: ranked by its LMArena score, with no size or downloads to show.1466
24Gemini 3.6 Flash (High). Closed weights: ranked by its LMArena score, with no size or downloads to show.1467
23Gemini 3.5 Flash (High). Closed weights: ranked by its LMArena score, with no size or downloads to show.1469
22Muse Spark 1.3 (Max). Closed weights: ranked by its LMArena score, with no size or downloads to show.1469
21Gemini 3.5 Flash (Medium). Closed weights: ranked by its LMArena score, with no size or downloads to show.1471
20Claude Opus 4.7. Closed weights: ranked by its LMArena score, with no size or downloads to show.1480
19Gemini 3 Pro. Closed weights: ranked by its LMArena score, with no size or downloads to show.1482
18Gemini 3.1 Pro Preview. Closed weights: ranked by its LMArena score, with no size or downloads to show.1483
17Claude Opus 4.6. Closed weights: ranked by its LMArena score, with no size or downloads to show.1483
16Qwen3.8-Max. Closed weights: ranked by its LMArena score, with no size or downloads to show.1484
15Gemini 3.7 Flash (High). Closed weights: ranked by its LMArena score, with no size or downloads to show.1485
14Claude Opus 5 (High). Closed weights: ranked by its LMArena score, with no size or downloads to show.1486
13Claude Opus 4.7 (High). Closed weights: ranked by its LMArena score, with no size or downloads to show.1487
12Muse Wonder (Max). Closed weights: ranked by its LMArena score, with no size or downloads to show.1488
11Claude Opus 5 (Max). Closed weights: ranked by its LMArena score, with no size or downloads to show.1494
10Gemini 3.8 Flash (High). Closed weights: ranked by its LMArena score, with no size or downloads to show.1494
9Claude Fable 5 (High). Closed weights: ranked by its LMArena score, with no size or downloads to show.1494
8Claude Opus 4.6 (High). Closed weights: ranked by its LMArena score, with no size or downloads to show.1504
7Gemini 4 Hydrogen (High). Closed weights: ranked by its LMArena score, with no size or downloads to show.1508
6Claude Fable 5.2 (Max). Closed weights: ranked by its LMArena score, with no size or downloads to show.1516
5Claude Fable 5.1 (Max). Closed weights: ranked by its LMArena score, with no size or downloads to show.1516
4Gemini 4 Neon (High). Closed weights: ranked by its LMArena score, with no size or downloads to show.1519
3Claude Opus 5.5 (High). Closed weights: ranked by its LMArena score, with no size or downloads to show.1531
2Gemini 4 Argon (High). Closed weights: ranked by its LMArena score, with no size or downloads to show.1531
1Gemini 4 Carbon (High). Closed weights: ranked by its LMArena score, with no size or downloads to show.1533
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.