Who's Winningthe AI Race?

Monitor AI model performance over time. See how GPT, Claude, Gemini, and others compete as the landscape evolves.

Breaking · Feb 7, 2026

Claude Opus 4.6 Takes the #1 Spot

Anthropic's latest model overtakes Google's Gemini Pro with an Elo score of 1496.

View the full rankings
Claude Opus 4.6
TEXT LEADER
1496
Top Elo Score
163
Models Tracked
16
Organizations
+25%
Elo Growth vs GPT-4
Elo Score Growth
GPT-4 (Mar 2023): 1200 Elo baseline
Current leader: 1496 Elo
296 points improvement

Performance Over Time

Elo scores by release date

Groups:
Swipe

← Swipe chart to explore · Tap any model for details →

Leadership Race

Which company held the #1 spot over time

Leadership Timeline
GPT-4 Launch
Gemini 1.5 Pro
GPT-4o Launch
o1 Preview
Grok-3 Preview
GPT-4.5 Preview
Gemini 2.5 Pro
Claude 4.5 Thinking
Gemini Pro
Claude Opus 4.6
OpenAI
GPT-4 · 338 days
Google
Gemini 1.5 Pro · 88 days
OpenAI
GPT-4o / o1 · 287 days
xAI
Grok-3 Preview · 3 days
OpenAI
GPT-4.5 Preview · 26 days
Google
Gemini 2.5 Pro · 221 days
Anthropic
Claude 4.5 Thinking · 75 days
Google
Gemini Pro · 23 days
Anthropic
Claude Opus 4.6 · 1 days
2023202420252026
Total Days at #1
OpenAI651
Google332
Anthropic76
xAI3

The Leaderboard

All tracked models ranked by Elo score

RankModelScoreDetails
1
Claude Opus 4.6
Anthropic
1496
2
Gemini 3 Pro
Google
1486
3
Grok 4.1 Thinking
xAI
1475
4
Gemini 3 Flash
Google
1470
5
Claude Opus 4.5 Thinking
Anthropic
1468
6
Claude Opus 4.5
Anthropic
1467
7
Grok 4.1
xAI
1465
8
Gemini 3 Flash Thinking
Google
1463
9
GPT-5.1 High
OpenAI
1458
10
ERNIE 5.0
Baidu
1452
11
Claude Sonnet 4.5
Anthropic
1450
12
Claude Sonnet 4.5 Thinking
Anthropic
1450
13
Gemini 2.5 Pro
Google
1450
14
ERNIE 5.0 Preview
Baidu
1203
15
Kimi K2.5 Thinking
Moonshot
1449
16
Claude Opus 4.1 Thinking
Anthropic
1449
17
Claude Opus 4.1
Anthropic
1445
18
GPT-4.5 Preview
OpenAI
1444
19
ChatGPT-4o Latest
OpenAI
1442
20
GLM-4.7
Zhipu
1441
21
GPT-5.2 High
OpenAI
1438
22
GPT-5.1
OpenAI
1437
23
GPT-5.2
OpenAI
1437
24
GPT-5 High
OpenAI
1434
25
Qwen3 Max Preview
Alibaba
1434
26
Kimi K2.5 Instant
Moonshot
1433
27
o3
OpenAI
1433
28
Grok 4.1 Fast Reasoning
xAI
1430
29
Kimi K2 Thinking Turbo
Moonshot
1428
30
GPT-5
OpenAI
1426
31
GLM-4.6
Zhipu
1425
32
Qwen3 Max
Alibaba
1425
33
Claude Opus 4 Thinking
Anthropic
1424
34
DeepSeek V3.2 Exp
DeepSeek
1423
35
DeepSeek V3.2 Exp Thinking
DeepSeek
1423
36
Qwen3 235B
Alibaba
1422
37
Grok 4 Fast Chat
xAI
1422
38
DeepSeek V3.2 Thinking
DeepSeek
1420
39
DeepSeek V3.2
DeepSeek
1419
40
DeepSeek R1 (May)
DeepSeek
1418
41
ERNIE 5.0 Preview (Oct)
Baidu
1022
42
DeepSeek V3.1
DeepSeek
1418
43
Kimi K2 Preview
Moonshot
1418
44
DeepSeek V3.1 Thinking
DeepSeek
1417
45
Kimi K2
Moonshot
1417
46
DeepSeek V3.1 Terminus
DeepSeek
1416
47
DeepSeek V3.1 Terminus Thinking
DeepSeek
1416
48
Qwen 3 Vl 235b A22b
Alibaba
1415
49
Mistral Large 3
Mistral
1414
50
Claude Opus 4
Anthropic
1414
51
GPT-4.1
OpenAI
1413
52
Mistral Medium
Mistral
1411
53
Grok-3 Preview
xAI
1411
54
Gemini 2.5 Flash
Google
1410
55
GLM-4.5
Zhipu
1410
56
Grok-4
xAI
1410
57
Gemini 2.5 Flash Preview 09 2025
Google
1405
58
Claude Haiku 4.5
Anthropic
1404
59
Grok 4 Fast Reasoning
xAI
1404
60
o1
OpenAI
1402
61
Qwen 3 235b A22b No Thinking
Alibaba
1401
62
Qwen 3 Next 80b A3b
Alibaba
1401
63
Claude Sonnet 4 Thinking
Anthropic
1400
65
Qwen 3 235b A22b Thinking 2507
Alibaba
1398
66
DeepSeek R1
DeepSeek
1398
67
Qwen 3 Vl 235b A22b Thinking
Alibaba
1395
70
DeepSeek V3 (Mar)
DeepSeek
1394
73
o4-mini
OpenAI
1391
74
GPT-5 Mini High
OpenAI
1390
75
Claude Sonnet 4
Anthropic
1390
76
Claude 3.7 Sonnet Thinking
Anthropic
1389
77
o1-preview
OpenAI
1388
79
Qwen 3 Coder 480b A35b
Alibaba
1387
81
Mistral medium 2505
Mistral
1385
82
Qwen 3 30b A3b Instruct 2507
Alibaba
1383
84
GPT-4.1 Mini
OpenAI
1382
85
Gemini 2.5 Flash Lite Preview 09 2025 No Thinking
Google
1380
86
GLM 4.6v
Zhipu
1378
87
Gemini 2.5 Flash Lite Preview 06 17 Thinking
Google
1375
88
Qwen 3 235b A22b
Alibaba
1375
89
Qwen 2.5 Max
Alibaba
1374
90
Claude 3.5 Sonnet v2
Anthropic
1373
91
Claude 3.7 Sonnet
Anthropic
1372
92
GLM 4.5 Air
Zhipu
1371
93
Qwen 3 Next 80b A3b Thinking
Alibaba
1369
97
o3-mini High
OpenAI
1364
98
Grok 3 Mini High
xAI
1363
99
Gemini 2.0 Flash
Google
1361
100
GLM 4.7 Flash
Zhipu
1360
101
DeepSeek V3
DeepSeek
1359
102
Grok 3 Mini Beta
xAI
1357
103
Mistral small 2506
Mistral
1356
105
GPT Oss 120b
OpenAI
1354
106
Gemini 2.0 Flash Lite Preview 02 05
Google
1353
107
GLM 4.5v
Zhipu
1353
109
Gemini 1.5 Pro 002
Google
1352
112
o3-mini
OpenAI
1348
115
Qwen 3 32b
Alibaba
1347
119
Qwen Plus 0125
Alibaba
1346
120
GPT-4o
OpenAI
1346
121
GLM 4 Plus 0111
Zhipu
1343
122
Claude 3.5 Sonnet
Anthropic
1343
126
GPT-5 Nano High
OpenAI
1338
127
o1-mini
OpenAI
1337
131
GPT-4o (Aug)
OpenAI
1335
132
Grok-2
xAI
1335
133
Gemini advanced 0514
Google
1335
137
Qwen 3 30b A3b
Alibaba
1328
142
GPT 4 Turbo 2024 04 09
OpenAI
1325
143
Claude 3.5 Haiku
Anthropic
1324
144
DeepSeek v2.5 1210
DeepSeek
1210
145
Gemini 1.5 Pro
Google
1323
147
Claude 3 Opus
Anthropic
1323
148
GPT-4.1 Nano
OpenAI
1322
151
Llama 3.3
Meta
1320
152
GLM 4 Plus
Zhipu AI
1319
154
Qwen Max 0919
Alibaba
1318
155
GPT-4o Mini
OpenAI
1318
156
GPT Oss 20b
OpenAI
1318
158
Qwen 2.5 Plus 1127
Alibaba
1127
160
Mistral large 2407
Mistral
1314
161
GPT 4 0125 Preview
OpenAI
1314
162
GPT 4 1106 Preview
OpenAI
1106
165
Gemini 1.5 Flash 002
Google
1310
166
Grok 2 Mini 2024 08 13
xAI
1308
167
DeepSeek v2.5
DeepSeek
1307
170
Mistral large 2411
Mistral
1305
172
Mistral small 3.1 24b Instruct 2503
Mistral
1305
174
Qwen 2.5 72b
Alibaba
1303
183
GPT-4
OpenAI
1288
184
Llama 3.1 Tulu 3 70b
Ai2
1287
186
Gemini 1.5 Flash
Google
1286
188
Claude 3 Sonnet
Anthropic
1282
193
GPT 4 0613
OpenAI
1276
194
Mistral small 24b Instruct 2501
Mistral
1274
195
GLM 4 0520
Zhipu AI
1274
197
Qwen 2.5 Coder 32b
Alibaba
1271
200
DeepSeek coder V2
DeepSeek
1265
202
Qwen 2 72b
Alibaba
1262
203
Claude 3 Haiku
Anthropic
1262
205
Gemini 1.5 Flash 8b 001
Google
1259
209
Mistral large 2402
Mistral
1243
213
Gemini pro Dev Api
Google
1236
214
Qwen 1.5 110b Chat
Alibaba
1235
216
Qwen 1.5 72b Chat
Alibaba
1234
221
GPT 3.5 Turbo 0125
OpenAI
1225
222
Mistral medium
Mistral
1224
225
Gemini pro
Google
1222
226
Llama 3.1 Tulu 3 8b
Ai2
1221
231
Qwen 1.5 32b Chat
Alibaba
1205
232
GPT 3.5 Turbo 1106
OpenAI
1106
238
Qwen 1.5 14b Chat
Alibaba
1191
240
DeepSeek llm 67b Chat
DeepSeek
1185
249
Mistral 7b
NousResearch
1176
255
3.2
Meta
1167
261
Mistral 7b
Cognitive Computations
1153
263
Mistral 7b Instruct V0.2
Mistral
1150
266
Qwen 1.5 7b Chat
Alibaba
1144
270
Qwen 14b Chat
Alibaba
1139
284
3.2
Meta
1112
285
Mistral 7b
Mistral
1110
288
Qwen 1.5 4b Chat
Alibaba
1091
292
Gpt4all 13b Snoozy
Nomic AI
1067

Trusted Data Sources

🏟️
LMArena
🤗
Hugging Face
📄
arXiv
💬
Chatbot Arena

Frequently Asked Questions

Which AI model is the best in 2026?

As of February 7, 2026, Anthropic's Claude Opus 4.6 holds the #1 position with an Elo score of 1496, followed by Google's Gemini 3 Pro (1486) and xAI's Grok 4.1 Thinking (1475).

What is an Elo score for AI models?

An Elo score is a rating system where models compete head-to-head. Users compare responses without knowing which model produced them, and scores adjust based on wins and losses.

Who leads the AI race?

Leadership has changed multiple times. OpenAI led with GPT-4 through most of 2024. Google took the lead with Gemini 3 Pro in January 2026. As of February 2026, Anthropic leads with Claude Opus 4.6.

How often are rankings updated?

We capture daily snapshots to track how rankings evolve over time. This reveals score drift as new models enter the arena.