Text Arena🏆Overall

View overall rankings across various AI models in text-to-text tasks across math, coding, creative writing, and other open-ended domains.

Apr 17, 2026
5,839,864 votes
341 models
Rank Spread
1
13
Anthropic
claude-opus-4-6-thinking
Anthropic · Proprietary
1500±5
18,144$5 / $251M
2
15
Anthropic
claude-opus-4-6
Anthropic · Proprietary
1496±5
19,373$5 / $251M
3
18
Anthropic
claude-opus-4-7-thinking
Anthropic · Proprietary
1490±11
2,618$5 / $251M
4
27
gemini-3.1-pro-preview
Google · Proprietary
1487±5
22,905$2 / $121M
5
210
Anthropic
claude-opus-4-7
Anthropic · Proprietary
1485±10
3,485$5 / $251M
6
310
Meta
muse-spark
Meta · Proprietary
1481±8
5,155N/AN/A
7
310
gemini-3-pro
Google · Proprietary
1479±4
41,404$2 / $121M
8
411
qwen3.5-max-preview
Alibaba · Proprietary
1472±7
9,591N/AN/A
9
511
gpt-5.4-high
OpenAI · Proprietary
1472±6
11,568$2.50 / $151.1M
10
513
glm-5.1
Z.ai · MIT
1469±7
7,179$0.95 / $3.15202.8K
11
813
gemini-3-flash
Google · Proprietary
1467±4
30,817$0.50 / $31M
12
1017
gemini-2.5-pro
Google · Proprietary
1461±3
109,121$1.25 / $101M
13
1221
Bytedance
dola-seed-2.0-pro
Bytedance · Proprietary
1457±5
20,678N/AN/A
14
1023
grok-4.20-beta-0309-reasoning
xAI · Proprietary
1456±6
11,661$2 / $62M
15
1227
grok-4.20-beta1
xAI · Proprietary
1454±6
12,069N/AN/A
16
1228
gpt-5.4
OpenAI · Proprietary
1453±6
11,988$2.50 / $151.1M
17
1331
grok-4.20-multi-agent-beta-0309
xAI · Proprietary
1450±6
12,049$2 / $62M
18
1330
ernie-5.0-0110
Baidu · Proprietary
1450±5
24,211N/AN/A
19
1236
amazon-nova-experimental-chat-26-02-10
Amazon · Proprietary
1449±10
3,431N/AN/A
20
1331
gemini-3-flash (thinking-minimal)
Google · Proprietary
1448±4
35,422$0.50 / $31M
21
1432
Anthropic
claude-opus-4-5-20251101
Anthropic · Proprietary
1448±4
49,272$5 / $25200K
22
1434
kimi-k2.5-thinking
Moonshot · Modified MIT
1447±5
22,439$0.60 / $3N/A
23
1534
Anthropic
claude-opus-4-5-20251101-thinking-32k
Anthropic · Proprietary
1446±4
37,184$5 / $25200K
24
1336
Anthropic
claude-sonnet-4-6
Anthropic · Proprietary
1446±6
11,255$3 / $151M
25
1536
glm-5
Z.ai · MIT
1445±5
15,839$1 / $3.20202.8K
26
1637
qwen3.5-397b-a17b
Alibaba · Apache 2.0
1443±5
17,212$0.39 / $2.34262.1K
27
1538
ernie-5.0-preview-1203
Baidu · Proprietary
1442±7
9,776N/AN/A
28
1736
grok-4.1-thinking
xAI · Proprietary
1442±4
49,408N/AN/A
29
1540
gemma-4-31b
Google · Apache 2.0
1442±8
5,827$0.14 / $0.40262.1K
30
1737
gpt-5.1-high
OpenAI · Proprietary
1441±4
40,899$1.25 / $10400K
31
2038
glm-4.6
Z.ai · MIT
1440±4
35,734$0.39 / $1.90204.8K
32
1839
gpt-5.2-chat-latest-20260210
OpenAI · Proprietary
1440±5
17,827$1.75 / $14128K
33
2140
qwen3-max-preview
Alibaba · Proprietary
1438±5
27,782$0.78 / $3.90262.1K
34
2339
grok-4.1
xAI · Proprietary
1438±4
53,332N/AN/A
35
2347
glm-4.7
Z.ai · MIT
1436±6
12,149$0.39 / $1.75202.8K
36
2155
gemma-4-26b-a4b
Google · Apache 2.0
1435±8
5,782N/AN/A
37
3147
Anthropic
claude-sonnet-4-5-20250929
Anthropic · Proprietary
1432±3
59,693$3 / $15200K
38
2960
mimo-v2-pro
Xiaomi · Proprietary
1431±6
10,116$1 / $31M
39
3357
mistral-large-3
Mistral · Apache 2.0
1430±4
40,077$0.50 / $1.50N/A
40
2769
ernie-5.0-preview-1022
Baidu · Proprietary
1429±9
4,730N/AN/A
41
3562
glm-4.5
Z.ai · MIT
1429±5
24,356$0.60 / $2.20131.1K
42
3559
chatgpt-4o-latest-20250326
OpenAI · Proprietary
1429±3
82,590$5 / $15128K
43
3566
deepseek-r1-0528
DeepSeek · MIT
1428±6
18,480$0.50 / $2.15163.8K
44
3561
Anthropic
claude-sonnet-4-5-20250929-thinking-32k
Anthropic · Proprietary
1427±3
61,734$3 / $15200K
45
3764
mistral-medium-2508
Mistral · Proprietary
1426±3
78,918$2.70 / $8.1032K
46
3575
longcat-flash-chat-2602-exp
Meituan · Proprietary
1425±7
7,739N/AN/A
47
3770
grok-3-preview-02-24
xAI · Proprietary
1425±4
32,918$3 / $15131.1K
48
3576
deepseek-v3.2-exp-thinking
DeepSeek · MIT
1423±7
9,078$0.27 / $0.41163.8K
49
3873
deepseek-v3.2
DeepSeek · MIT
1423±4
42,815$0.26 / $0.42163.8K
50
3777
deepseek-v3.2-exp
DeepSeek · MIT
1422±6
11,952$0.27 / $0.41163.8K
51
3975
gpt-5.1
OpenAI · Proprietary
1422±4
43,538$1.25 / $10400K
52
3777
longcat-flash-chat
Meituan · MIT
1422±6
11,418$0.20 / $0.80131.1K
53
3977
gemini-3.1-flash-lite-preview
Google · Proprietary
1421±5
17,931$0.25 / $1.501M
54
3777
qwen3-vl-235b-a22b-instruct
Alibaba · Apache 2.0
1421±6
11,533$0.20 / $0.88262.1K
55
3777
gpt-5.4-mini-high
OpenAI · Proprietary
1421±7
9,135$2.50 / $151.1M
56
3778
kimi-k2.5-instant
Moonshot · Modified MIT
1421±7
8,217$0.60 / $3262.1K
57
3581
amazon-nova-experimental-chat-12-10
Amazon · Proprietary
1421±10
3,688N/AN/A
58
4277
gpt-5.2-high
OpenAI · Proprietary
1420±4
32,296$1.75 / $14400K
59
4377
deepseek-v3.2-thinking
DeepSeek · MIT
1420±4
37,197$0.26 / $0.42163.8K
60
4079
deepseek-v3.1
DeepSeek · MIT
1419±6
14,995$1.23 / $4.94N/A
61
4576
qwen3-235b-a22b-instruct-2507
Alibaba · Apache 2.0
1419±3
83,341$0.26 / $1.06N/A
62
4179
qwen3.5-122b-a10b
Alibaba · Apache 2.0
1419±5
14,023$0.26 / $2.08262.1K
63
3783
deepseek-v3.1-terminus-thinking
DeepSeek · MIT
1419±10
3,475$0.21 / $0.79163.8K
64
4577
Anthropic
claude-opus-4-1-20250805-thinking-16k
Anthropic · Proprietary
1418±4
49,886$15 / $75200K
65
4479
qwen3-next-80b-a3b-instruct
Alibaba · Apache 2.0
1418±5
22,909$0.09 / $1.10262.1K
66
4677
gemini-2.5-flash
Google · Proprietary
1418±3
108,688$0.30 / $2.501M
67
3886
deepseek-v3.1-terminus
DeepSeek · MIT
1417±10
3,713$0.21 / $0.79163.8K
68
4778
Anthropic
claude-opus-4-1-20250805
Anthropic · Proprietary
1417±3
77,473$15 / $75200K
69
4481
gpt-4.5-preview-2025-02-27
OpenAI · Proprietary
1417±6
14,547$75 / $150128K
70
4382
deepseek-v3.1-thinking
DeepSeek · MIT
1417±7
11,762$1.23 / $4.94N/A
71
4581
amazon-nova-experimental-chat-11-10
Amazon · Proprietary
1417±4
25,448N/AN/A
72
4781
gpt-5.2
OpenAI · Proprietary
1416±4
29,417$1.75 / $14400K
73
5082
kimi-k2-thinking-turbo
Moonshot · Modified MIT
1414±4
47,731$1.15 / $8262.1K
74
4788
qwen3-235b-a22b-thinking-2507
Alibaba · Apache 2.0
1414±7
9,013$0.13 / $0.60262.1K
75
4889
qwen3-max-2025-09-23
Alibaba · Proprietary
1413±6
9,184$0.78 / $3.90262.1K
76
6189
mimo-v2-flash (non-thinking)
Xiaomi · MIT
1411±4
31,981$0.09 / $0.29262.1K
77
6389
grok-4-0709
xAI · Proprietary
1410±4
41,442$3 / $15256K
78
6689
o3-2025-04-16
OpenAI · Proprietary
1409±4
59,810$2 / $8200K
79
6689
grok-4-1-fast-reasoning
xAI · Proprietary
1409±4
44,414$0.20 / $0.502M
80
5293
grok-4-fast-chat
xAI · Proprietary
1409±8
6,829$3 / $15256K
81
7090
gemini-2.5-flash-preview-09-2025
Google · Proprietary
1407±4
32,971$0.30 / $2.501M
82
4899
Tencent
hunyuan-vision-1.5-thinking
Tencent · Proprietary
1406±12
2,218N/AN/A
83
7293
gpt-5-high
OpenAI · Proprietary
1405±4
31,994$1.25 / $10400K
84
7494
gpt-5-chat
OpenAI · Proprietary
1403±4
31,638$1.25 / $10128K
85
7397
qwen3.5-27b
Alibaba · Apache 2.0
1402±5
13,687$0.20 / $1.56262.1K
86
7597
Stepfun
step-3.5-flash
StepFun · Apache 2.0
1402±5
20,186$0.10 / $0.30262.1K
87
7499
qwen3-vl-235b-a22b-thinking
Alibaba · Apache 2.0
1401±7
7,960$0.26 / $2.60131.1K
88
8099
qwen3.5-flash
Alibaba · Proprietary
1400±5
14,459N/AN/A
89
7399
Tencent
hunyuan-t1-20250711
Tencent · Proprietary
1400±9
4,717N/AN/A
90
73100
amazon-nova-experimental-chat-26-01-10
Amazon · Proprietary
1399±10
3,420N/AN/A
91
8199
grok-4-fast-reasoning
xAI · Proprietary
1397±5
18,750$0.20 / $0.502M
92
8199
qwen3.5-35b-a3b
Alibaba · Apache 2.0
1396±5
14,275$0.16 / $1.30262.1K
93
81100
mimo-v2-flash (thinking)
Xiaomi · MIT
1395±6
10,994$0.09 / $0.29262.1K
94
83101
amazon-nova-experimental-chat-10-20
Amazon · Proprietary
1394±6
11,488N/AN/A
95
84100
qwen3-235b-a22b-no-thinking
Alibaba · Apache 2.0
1394±4
38,253$0.46 / $1.82131.1K
96
84101
mai-1-preview
Microsoft AI · Proprietary
1393±5
17,907N/AN/A
97
84106
minimax-m2.7
MiniMax · Modified MIT
1391±7
8,484$0.30 / $1.20196.6K
98
86104
minimax-m2.1-preview
MiniMax · MIT
1391±5
17,175$0.29 / $0.95196.6K
99
86106
gpt-5.3-chat-latest
OpenAI · Proprietary
1390±5
16,480$1.75 / $14128K
100
92106
Anthropic
claude-haiku-4-5-20251001
Anthropic · Proprietary
1387±3
61,177$1 / $5200K
101
95111
qwen3-30b-a3b-instruct-2507
Alibaba · Apache 2.0
1384±5
23,783$0.09 / $0.30262.1K
102
97112
glm-4.5-air
Z.ai · MIT
1383±4
31,149$0.13 / $0.85131.1K
103
98112
gpt-4.1-2025-04-14
OpenAI · Proprietary
1382±4
51,085$2 / $81M
104
97118
kimi-k2-0905-preview
Moonshot · Modified MIT
1379±6
11,805$0.60 / $2.50262.1K
105
101115
gemini-2.5-flash-lite-preview-09-2025-no-thinking
Google · Proprietary
1379±3
47,332$0.10 / $0.401M
106
98120
nvidia-nemotron-3-super-120b-a12b
Nvidia · NVIDIA Open Model
1378±7
7,413N/AN/A
107
101120
minimax-m2.5
MiniMax · Modified MIT
1376±5
19,156$0.12 / $0.99196.6K
108
101125
Tencent
hunyuan-turbos-20250416
Tencent · Proprietary
1376±6
10,724N/AN/A
109
101120
Anthropic
claude-opus-4-20250514-thinking-16k
Anthropic · Proprietary
1375±4
36,956$15 / $75200K
110
102120
deepseek-v3-0324
DeepSeek · MIT
1375±4
45,555$3 / $4.5032.8K
111
97130
glm-4.6v
Z.ai · MIT
1375±11
2,807$0.30 / $0.90131.1K
112
101128
gpt-5.4-nano-high
OpenAI · Proprietary
1374±7
8,430$2.50 / $151.1M
113
104126
gpt-5-mini-high
OpenAI · Proprietary
1373±5
27,071$0.25 / $2400K
114
104127
deepseek-r1
DeepSeek · MIT
1373±5
18,524$0.70 / $2.5064K
115
104129
kimi-k2-0711-preview
Moonshot · Modified MIT
1371±5
27,669$0.60 / $2.50131.1K
116
105130
mistral-medium-2505
Mistral · Proprietary
1369±5
33,267$0.40 / $2131.1K
117
106130
gemini-2.5-flash-lite-preview-06-17-thinking
Google · Proprietary
1368±4
32,965$0.10 / $0.401M
118
105131
qwen3-next-80b-a3b-thinking
Alibaba · Apache 2.0
1367±6
13,717$0.10 / $0.78131.1K
119
110130
qwen2.5-max
Alibaba · Proprietary
1366±4
32,632N/AN/A
120
106132
grok-3-mini-high
xAI · Proprietary
1366±5
16,988$0.30 / $0.50131.1K
121
110131
o1-2024-12-17
OpenAI · Proprietary
1366±4
27,807$15 / $60200K
122
110132
qwen3-235b-a22b
Alibaba · Apache 2.0
1366±5
26,285$0.46 / $1.82131.1K
123
110132
gpt-oss-120b
OpenAI · Apache 2.0
1365±4
30,675$0.04 / $0.19131.1K
124
112132
Anthropic
claude-opus-4-20250514
Anthropic · Proprietary
1364±4
44,273$15 / $75200K
125
105138
amazon-nova-experimental-chat-10-09
Amazon · Proprietary
1364±11
2,840N/AN/A
126
111135
nova-2-lite
Amazon · Proprietary
1363±6
12,266$0.30 / $2.501M
127
113135
grok-3-mini-beta
xAI · Proprietary
1363±5
22,732$0.30 / $0.50131.1K
128
110137
ling-flash-2.0
Ant Group · MIT
1362±7
7,017N/AN/A
129
119138
gemma-3-27b-it
Google · Gemma
1358±4
47,584$0.08 / $0.16131.1K
130
115141
intellect-3
Prime Intellect · MIT
1357±8
5,337$0.20 / $1.10131.1K
131
114143
mercury-2
Inception AI · Proprietary
1356±11
3,119$0.25 / $0.75128K
132
121139
qwen3-coder-480b-a35b-instruct
Alibaba · Apache 2.0
1356±5
25,768$0.40 / $1.60262.1K
133
125139
gemini-2.0-flash-001
Google · Proprietary
1354±4
43,780$0.10 / $0.401M
134
125141
glm-4.7-flash
Z.ai · MIT
1353±6
11,778$0.06 / $0.40202.8K
135
125141
o1-preview
OpenAI · Proprietary
1353±5
31,122$15 / $60N/A
136
127141
o4-mini-2025-04-16
OpenAI · Proprietary
1353±4
45,488$1.10 / $4.40200K
137
128145
nvidia-nemotron-3-nano-30b-a3b-bf16
Nvidia · NVIDIA Open Model
1349±6
15,543$0.06 / $0.24262.1K
138
127149
Stepfun
step-3
StepFun · Apache 2.0
1349±7
6,555$0.57 / $1.4265.5K
139
130145
Anthropic
claude-sonnet-4-20250514-thinking-32k
Anthropic · Proprietary
1348±4
35,165$3 / $151M
140
136152
minimax-m1
MiniMax · Apache 2.0
1342±4
35,260$0.40 / $2.201M
141
132156
minimax-m2
MiniMax · Apache 2.0
1342±8
6,875$0.26 / $1196.6K
142
137153
gpt-4.1-mini-2025-04-14
OpenAI · Proprietary
1340±4
39,371$0.40 / $1.601M
143
132160
qwen3-32b
Alibaba · Apache 2.0
1340±9
3,926$0.08 / $0.2441K
144
137157
mistral-small-2506
Mistral · Apache 2.0
1339±5
17,729$0.10 / $0.3032K
145
139158
Anthropic
claude-sonnet-4-20250514
Anthropic · Proprietary
1338±4
40,370$3 / $151M
146
136161
nvidia-llama-3.3-nemotron-super-49b-v1.5
Nvidia · Nvidia Open
1337±10
3,347$0.10 / $0.40131.1K
147
139159
o3-mini-high
OpenAI · Proprietary
1336±5
18,589$1.10 / $4.40200K
148
139161
Stepfun
step-1o-turbo-202506
StepFun · Proprietary
1335±7
9,045N/AN/A
149
139162
gemma-3-12b-it
Google · Gemma
1334±9
3,829$0.04 / $0.13131.1K
150
139162
glm-4.5v
Z.ai · MIT
1333±8
4,969$0.60 / $1.8065.5K
151
141161
deepseek-v3
DeepSeek · DeepSeek
1332±5
21,770$1.14 / $4.56N/A
152
140162
ring-flash-2.0
Ant Group · MIT
1331±7
7,157N/AN/A
153
142161
Cohere
command-a-03-2025
Cohere · CC-BY-NC-4.0
1331±3
56,351$2.50 / $10256K
154
140165
glm-4-plus-0111
Zhipu · Proprietary
1331±8
5,760N/AN/A
155
142162
trinity-large-preview
Arcee AI · Apache 2.0
1331±5
15,015N/AN/A
156
143162
gemini-2.0-flash-lite-preview-02-05
Google · Proprietary
1329±4
24,955$0.07 / $0.301M
157
144162
qwq-32b
Alibaba · Apache 2.0
1329±4
25,412$0.15 / $0.58131.1K
158
142170
qwen-plus-0125
Alibaba · Proprietary
1326±8
5,819$0.40 / $1.20131.1K
159
147171
Stepfun
step-2-16k-exp-202412
StepFun · Proprietary
1321±9
4,833N/AN/A
160
151171
gpt-5-nano-high
OpenAI · Proprietary
1320±7
8,286$0.05 / $0.40400K
161
145173
Tencent
hunyuan-turbos-20250226
Tencent · Proprietary
1320±12
2,220N/AN/A
162
146173
llama-3.1-nemotron-ultra-253b-v1
Nvidia · Nvidia Open Model
1319±12
2,549$0.60 / $1.80131.1K
163
157170
gemini-1.5-pro-002
Google · Proprietary
1319±3
55,606$3.50 / $10.502.1M
164
157170
o3-mini
OpenAI · Proprietary
1319±4
57,374$1.10 / $4.40200K
165
158171
qwen3-30b-a3b
Alibaba · Apache 2.0
1317±5
26,510$0.08 / $0.2841K
166
158171
o1-mini
OpenAI · Proprietary
1317±4
51,981$1.10 / $4.40N/A
167
158172
Anthropic
claude-3-7-sonnet-20250219-thinking-32k
Anthropic · Proprietary
1314±4
38,845$3 / $15200K
168
158175
olmo-3.1-32b-instruct
Ai2 · Apache 2.0
1312±6
12,244$0.20 / $0.6065.5K
169
157181
Tencent
hunyuan-turbo-0110
Tencent · Proprietary
1311±12
2,290N/AN/A
170
158182
llama-3.3-nemotron-49b-super-v1
Nvidia · Nvidia
1308±12
2,218N/AN/A
171
165179
gemma-3n-e4b-it
Google · Gemma
1306±5
22,620$0.06 / $0.1232.8K
172
166179
grok-2-2024-08-13
xAI · Proprietary
1305±4
63,498$2 / $10131.1K
173
168182
01.AI
yi-lightning
01 AI · Proprietary
1301±5
27,332N/AN/A
174
169182
gpt-4o-2024-05-13
OpenAI · Proprietary
1300±4
112,881$5 / $15128K
175
169186
qwen2.5-plus-1127
Alibaba · Proprietary
1299±6
10,187N/AN/A
176
169184
Anthropic
claude-3-7-sonnet-20250219
Anthropic · Proprietary
1299±4
43,218$3 / $15200K
177
168190
olmo-3-32b-think
Ai2 · Apache 2.0
1299±8
5,967$0.15 / $0.5065.5K
178
171185
Anthropic
claude-3-5-sonnet-20241022
Anthropic · Proprietary
1298±3
88,363$3 / $15200K
179
169194
deepseek-v2.5-1210
DeepSeek · DeepSeek
1294±8
6,795N/AN/A
180
161208
molmo-2-8b
Ai2 · Apache 2.0
1294±22
804$0.20 / $0.2036.9K
181
175193
athene-v2-chat
NexusFlow · NexusFlow
1291±5
24,739N/AN/A
182
171201
gemma-3-4b-it
Google · Gemma
1291±9
4,171$0.04 / $0.08131.1K
183
176196
glm-4-plus
Zhipu AI · Proprietary
1290±5
26,126$0.44 / $1.76204.8K
184
172202
Tencent
hunyuan-large-2025-02-10
Tencent · Proprietary
1288±10
3,738N/AN/A
185
178200
Meta
llama-4-maverick-17b-128e-instruct
Meta · Llama 4
1287±4
40,010$0.63 / $1.80131.1K
186
177201
gpt-oss-20b
OpenAI · Apache 2.0
1287±6
10,639$0.03 / $0.14131.1K
187
178200
gemini-1.5-flash-002
Google · Proprietary
1287±4
34,902$0.07 / $0.301M
188
179200
gpt-4o-mini-2024-07-18
OpenAI · Proprietary
1286±4
68,710$0.15 / $0.60128K
189
178204
gpt-4.1-nano-2025-04-14
OpenAI · Proprietary
1285±8
6,103$0.10 / $0.401M
190
179201
Meta
llama-3.1-405b-instruct-bf16
Meta · Llama 3.1 Community
1284±4
41,375$4 / $432.8K
191
178206
llama-3.1-nemotron-70b-instruct
Nvidia · Llama 3.1
1283±8
7,140$1.20 / $1.20131.1K
192
180202
gpt-4o-2024-08-06
OpenAI · Proprietary
1282±4
45,499$2.50 / $10128K
193
179204
qwen-max-0919
Alibaba · Qwen
1282±6
16,478$1.60 / $6.4032.8K
194
181202
Meta
llama-3.1-405b-instruct-fp8
Meta · Llama 3.1 Community
1282±4
59,656$4 / $432.8K
195
175211
mercury
Inception AI · Proprietary
1282±14
1,961$0.25 / $0.75128K
196
182204
Anthropic
claude-3-5-sonnet-20240620
Anthropic · Proprietary
1281±4
82,419$3 / $15200K
197
182204
grok-2-mini-2024-08-13
xAI · Proprietary
1281±4
52,567$2 / $10131.1K
198
181204
Meta
llama-4-scout-17b-16e-instruct
Meta · Llama
1281±5
30,316$0.40 / $0.708.2K
199
182206
gemini-advanced-0514
Google · Proprietary
1278±5
50,148N/AN/A
200
185206
mistral-small-3.1-24b-instruct-2503
Mistral · Apache 2.0
1278±5
33,249$0.10 / $0.3032K
201
188208
Meta
llama-3.3-70b-instruct
Meta · Llama-3.3
1275±3
54,757$0.10 / $0.32131.1K
202
182216
Tencent
hunyuan-standard-2025-02-10
Tencent · Proprietary
1274±10
3,904N/AN/A
203
191211
gemini-1.5-pro-001
Google · Proprietary
1273±4
79,138$3.50 / $10.502.1M
204
196211
gpt-4-turbo-2024-04-09
OpenAI · Proprietary
1272±4
98,114$10 / $30128K
205
196212
deepseek-v2.5
DeepSeek · DeepSeek
1271±5
24,572N/AN/A
206
191216
olmo-3.1-32b-think
Ai2 · Apache 2.0
1271±7
8,512$0.15 / $0.5065.5K
207
199215
qwen2.5-72b-instruct
Alibaba · Qwen
1269±4
39,406$1.20 / $1.20N/A
208
201217
mistral-large-2407
Mistral · Mistral Research
1266±4
45,459$2 / $6131.1K
209
201217
mistral-large-2411
Mistral · MRL
1265±4
28,073$2 / $6131.1K
210
201218
athene-70b-0725
NexusFlow · CC-BY-NC-4.0
1265±6
19,621N/AN/A
211
204218
gpt-4-1106-preview
OpenAI · Proprietary
1263±4
100,105$10 / $30128K
212
199220
Tencent
hunyuan-large-vision
Tencent · Proprietary
1263±9
5,373N/AN/A
213
205219
gpt-4-0125-preview
OpenAI · Proprietary
1262±4
93,439$10 / $30128K
214
205218
Anthropic
claude-3-opus-20240229
Anthropic · Proprietary
1262±3
194,909$15 / $75200K
215
206219
Meta
llama-3.1-70b-instruct
Meta · Llama 3.1 Community
1261±4
55,240$0.40 / $0.40131.1K
216
208220
amazon-nova-pro-v1.0
Amazon · Proprietary
1259±5
24,745$0.80 / $3.20300K
217
205221
llama-3.1-tulu-3-70b
Ai2 · Llama 3.1
1256±11
2,846N/AN/A
218
213220
Anthropic
claude-3-5-haiku-20241022
Anthropic · Proprietary
1255±3
70,032$0.80 / $4200K
219
210221
magistral-medium-2506
Mistral · Proprietary
1254±6
11,647$2 / $540K
220
215223
reka-core-20240904
Reka AI · Proprietary
1248±7
7,312N/AN/A
221
218231
ibm-granite-h-small
IBM · Apache 2.0
1241±8
5,691N/AN/A
222
220228
gemini-1.5-flash-001
Google · Proprietary
1239±5
62,833$0.07 / $0.301M
223
220233
jamba-1.5-large
AI21 Labs · Jamba Open
1237±7
8,662$2 / $8256K
224
221235
mistral-small-24b-instruct-2501
Mistral · Apache 2.0
1233±6
14,681$0.05 / $0.0832.8K
225
221235
gemma-2-27b-it
Google · Gemma license
1231±3
75,754$0.65 / $0.658.2K
226
221238
qwen2.5-coder-32b-instruct
Alibaba · Apache 2.0
1230±8
5,432$0.87 / $0.8732K
227
221237
Cohere
command-r-plus-08-2024
Cohere · CC-BY-NC-4.0
1229±7
9,866$2.50 / $10128K
228
222237
amazon-nova-lite-v1.0
Amazon · Proprietary
1228±5
19,372$0.06 / $0.24300K
229
221239
llama-3.1-nemotron-51b-instruct
Nvidia · Llama 3.1
1228±10
3,749N/AN/A
230
222239
gemma-2-9b-it-simpo
Princeton · MIT
1227±7
10,072$0.03 / $0.098.2K
231
222239
glm-4-0520
Zhipu AI · Proprietary
1226±7
9,788N/AN/A
232
223238
gemini-1.5-flash-8b-001
Google · Proprietary
1226±4
35,558$0.07 / $0.301M
233
223239
nemotron-4-340b-instruct
Nvidia · NVIDIA Open Model
1225±5
19,659N/AN/A
234
224239
Cohere
c4ai-aya-expanse-32b
Cohere · CC-BY-NC-4.0
1224±5
27,124N/AN/A
235
226239
Meta
llama-3-70b-instruct
Meta · Llama 3 Community
1221±4
156,876$0.51 / $0.748.2K
236
228239
Anthropic
claude-3-sonnet-20240229
Anthropic · Proprietary
1218±4
109,284$3 / $15200K
237
226243
reka-flash-20240904
Reka AI · Proprietary
1218±7
7,536N/AN/A
238
224245
olmo-2-0325-32b-instruct
Ai2 · Apache-2.0
1218±11
3,334$0.05 / $0.20128K
239
230241
phi-4
Microsoft · MIT
1217±5
24,126$0.07 / $0.1416.4K
240
237246
amazon-nova-micro-v1.0
Amazon · Proprietary
1208±5
19,364$0.04 / $0.14128K
241
238246
gemma-2-9b-it
Google · Gemma license
1207±4
54,611$0.03 / $0.098.2K
242
238246
gpt-4-0314
OpenAI · Proprietary
1206±5
54,173$30 / $608.2K
243
239247
Cohere
command-r-plus
Cohere · CC-BY-NC-4.0
1204±4
77,554$2.50 / $10128K
244
239248
qwen2-72b-instruct
Alibaba · Qianwen LICENSE
1203±5
37,325$0.90 / $0.9032.8K
245
237254
Tencent
hunyuan-standard-256k
Tencent · Proprietary
1202±12
2,728N/AN/A
246
244252
Anthropic
claude-3-haiku-20240307
Anthropic · Proprietary
1195±4
117,701$0.25 / $1.25200K
247
240254
llama-3.1-tulu-3-8b
Ai2 · Llama 3.1
1193±11
2,896N/AN/A
248
245254
deepseek-coder-v2
DeepSeek · DeepSeek License
1191±6
15,147$0.14 / $0.28128K
249
243254
ministral-8b-2410
Mistral · MRL
1191±9
4,781$0.10 / $0.10131.1K
250
245255
Cohere
command-r-08-2024
Cohere · CC-BY-NC-4.0
1187±7
10,140$0.15 / $0.60128K
251
245256
jamba-1.5-mini
AI21 Labs · Jamba Open
1187±7
8,858$0.20 / $0.40256K
252
246254
Meta
llama-3.1-8b-instruct
Meta · Llama 3.1 Community
1187±4
49,605$0.02 / $0.0516.4K
253
246254
gpt-4-0613
OpenAI · Proprietary
1186±4
88,723$30 / $608.2K
254
245256
Cohere
c4ai-aya-expanse-8b
Cohere · CC-BY-NC-4.0
1185±7
9,818N/AN/A
255
252259
mistral-large-2402
Mistral · Proprietary
1176±5
62,436$4 / $1232K
256
253263
qwen1.5-110b-chat
Alibaba · Qianwen LICENSE
1175±6
26,195N/AN/A
257
255264
01.AI
yi-1.5-34b-chat
01 AI · Apache-2.0
1173±5
24,146N/AN/A
258
255266
reka-flash-21b-20240226-online
Reka AI · Proprietary
1170±7
15,450N/AN/A
259
256266
qwen1.5-72b-chat
Alibaba · Qianwen LICENSE
1166±5
39,302N/AN/A
260
256266
Meta
llama-3-8b-instruct
Meta · Llama 3 Community
1166±4
104,642$0.03 / $0.048.2K
261
256268
mistral-medium
Mistral · Proprietary
1165±6
34,550$2.70 / $8.1032K
262
256268
reka-flash-21b-20240226
Reka AI · Proprietary
1165±6
24,806N/AN/A
263
257268
Cohere
command-r
Cohere · CC-BY-NC-4.0
1163±5
54,036$0.15 / $0.60128K
264
258268
mixtral-8x22b-instruct-v0.1
Mistral · Apache 2.0
1162±5
51,416$0.90 / $0.9065.5K
265
255270
qwq-32b-preview
Alibaba · Apache 2.0
1162±12
3,231$0.15 / $0.58131.1K
266
258270
internlm2_5-20b-chat
InternLM · Other
1158±7
9,901$0 / $032.8K
267
261270
gemma-2-2b-it
Google · Gemma license
1156±4
46,616N/AN/A
268
261275
granite-3.1-8b-instruct
IBM · Apache 2.0
1149±11
3,090N/AN/A
269
265273
gemini-pro-dev-api
Google · Proprietary
1149±7
18,354$0.35 / $1.0532.8K
270
265278
zephyr-orpo-141b-A35b-v0.1
HuggingFace · Apache 2.0
1144±11
4,652N/AN/A
271
268278
phi-3-medium-4k-instruct
Microsoft · MIT
1137±5
25,055$0.17 / $0.68N/A
272
268278
qwen1.5-32b-chat
Alibaba · Qianwen LICENSE
1137±6
21,741N/AN/A
273
269282
starling-lm-7b-beta
Nexusflow · Apache-2.0
1132±7
16,056N/AN/A
274
270281
mixtral-8x7b-instruct-v0.1
Mistral · Apache 2.0
1131±4
73,503$0.63 / $0.6332K
275
268284
gemini-pro
Google · Proprietary
1130±12
6,390$0.35 / $1.0532.8K
276
270283
01.AI
yi-34b-chat
01 AI · Yi License
1128±7
15,483$0.90 / $0.904.1K
277
270284
qwen1.5-14b-chat
Alibaba · Qianwen LICENSE
1128±7
17,839$0.30 / $0.30N/A
278
269286
granite-3.1-2b-instruct
IBM · Apache 2.0
1127±11
3,188N/AN/A
279
273284
gpt-3.5-turbo-0125
OpenAI · Proprietary
1125±5
66,207$0.50 / $1.5016.4K
280
273290
tulu-2-dpo-70b
AllenAI/UW · AI2 ImpACT Low-risk
1121±10
6,535N/AN/A
281
273291
wizardlm-70b
Microsoft · Llama 2 Community
1119±10
8,214N/AN/A
282
274289
dbrx-instruct-preview
Databricks · DBRX LICENSE
1119±6
32,191$0.60 / $0.6032.8K
283
276291
Meta
llama-2-70b-chat
Meta · Llama 2 Community
1115±6
38,492$0.70 / $2.804.1K
284
275297
nous-hermes-2-mixtral-8x7b-dpo
NousResearch · Apache-2.0
1112±12
3,777$0.90 / $0.90N/A
285
280294
phi-3-small-8k-instruct
Microsoft · MIT
1110±6
17,766$0.15 / $0.60N/A
286
279296
Meta
llama-3.2-3b-instruct
Meta · Llama 3.2
1109±8
7,936$0.05 / $0.3480K
287
280297
starling-lm-7b-alpha
UC Berkeley · CC-BY-NC-4.0
1108±8
10,224N/AN/A
288
280297
openchat-3.5-0106
OpenChat · Apache-2.0
1107±8
12,637N/AN/A
289
281297
vicuna-33b
LMSYS · Non-commercial
1105±6
22,479$0 / $02K
290
279301
deepseek-llm-67b-chat
DeepSeek · DeepSeek License
1105±12
4,932N/AN/A
291
284300
snowflake-arctic-instruct
Snowflake · Apache 2.0
1101±6
32,832N/AN/A
292
282305
llama2-70b-steerlm-chat
Nvidia · Llama 2 Community
1098±13
3,585N/AN/A
293
284303
openchat-3.5
OpenChat · Apache-2.0
1097±10
7,968$0.20 / $0.20N/A
294
284303
granite-3.0-8b-instruct
IBM · Apache 2.0
1096±9
6,638N/AN/A
295
285305
gpt-3.5-turbo-1106
OpenAI · Proprietary
1094±9
16,619$1 / $216.4K
296
286303
gemma-1.1-7b-it
Google · Gemma license
1094±6
23,893$0.03 / $0.098.2K
297
285305
openhermes-2.5-mistral-7b
NousResearch · Apache-2.0
1092±11
5,006$0.17 / $0.17N/A
298
290305
mistral-7b-instruct-v0.2
Mistral · Apache-2.0
1089±7
19,402$0.20 / $0.2032.8K
299
292308
Meta
llama-2-13b-chat
Meta · Llama 2 Community
1084±7
19,174$0.25 / $0.254.1K
300
291311
qwen1.5-7b-chat
Alibaba · Qianwen LICENSE
1083±10
4,737$0.20 / $0.20N/A
301
290312
solar-10.7b-instruct-v1.0
Upstage AI · CC-BY-NC-4.0
1083±13
4,155$0.30 / $0.30N/A
302
290314
dolphin-2.2.1-mistral-7b
Cognitive Computations · Apache-2.0
1081±16
1,679$0.50 / $0.5016.4K
303
295311
phi-3-mini-4k-instruct-june-2024
Microsoft · MIT
1080±6
12,297$0.13 / $0.524.1K
304
292312
granite-3.0-2b-instruct
IBM · Apache 2.0
1080±8
6,837N/AN/A
305
295312
wizardlm-13b
Microsoft · Llama 2 Community
1076±10
7,044$0.30 / $0.30N/A
306
299312
phi-3-mini-4k-instruct
Microsoft · MIT
1073±6
20,118$0.13 / $0.52N/A
307
299318
zephyr-7b-beta
HuggingFace · MIT
1069±9
11,118$0.15 / $0.1516.4K
308
299320
mpt-30b-chat
MosaicML · CC-BY-NC-SA-4.0
1069±13
2,572N/AN/A
309
300319
Meta
codellama-34b-instruct
Meta · Llama 2 Community
1065±9
7,366$0.35 / $1.4016.4K
310
300322
zephyr-7b-alpha
HuggingFace · MIT
1058±16
1,785N/AN/A
311
307320
vicuna-13b
LMSYS · Llama 2 Community
1058±7
19,367$0.30 / $0.30N/A
312
300323
Meta
codellama-70b-instruct
Meta · Llama 2 Community
1057±18
1,143$0.70 / $2.8016.4K
313
306321
gemma-7b-it
Google · Gemma license
1056±10
8,925$0.05 / $0.088.2K
314
307321
Meta
llama-3.2-1b-instruct
Meta · Llama 3.2
1055±8
8,045$0.03 / $0.2060K
315
302323
falcon-180b-chat
TII · Falcon-180B TII License
1054±17
1,295N/AN/A
316
307321
Meta
llama-2-7b-chat
Meta · Llama 2 Community
1053±7
14,148$0.15 / $0.154.1K
317
306322
guanaco-33b
UW · Non-commercial
1053±12
2,921N/AN/A
318
307323
qwen-14b-chat
Alibaba · Qianwen LICENSE
1051±11
4,964N/AN/A
319
308322
phi-3-mini-128k-instruct
Microsoft · MIT
1050±7
20,685$0.13 / $0.52N/A
320
309326
smollm2-1.7b-instruct
HuggingFace · Apache 2.0
1042±14
2,199N/AN/A
321
311326
stripedhyena-nous-7b
Together AI · Apache 2.0
1038±11
5,182$0.20 / $0.20N/A
322
314326
olmo-7b-instruct
Ai2 · Apache-2.0
1032±11
6,328$0.20 / $0.20N/A
323
317326
vicuna-7b
LMSYS · Llama 2 Community
1031±9
6,923$0.20 / $0.20N/A
324
320326
palm-2
Google · Proprietary
1027±10
8,554$0.50 / $0.5025.8K
325
320326
mistral-7b-instruct
Mistral · Apache 2.0
1023±9
8,977$0.07 / $0.284.1K
326
320326
gemma-1.1-2b-it
Google · Gemma license
1022±8
10,854N/AN/A
327
327329
gemma-2b-it
Google · Gemma license
1002±12
4,780$0.10 / $0.10N/A
328
327329
qwen1.5-4b-chat
Alibaba · Qianwen LICENSE
997±9
7,597$0.10 / $0.10N/A
329
327330
koala-13b
UC Berkeley · Non-commercial
990±10
6,965N/AN/A
330
329332
chatglm3-6b
Tsinghua · Apache-2.0
972±12
4,658N/AN/A
331
330335
gpt4all-13b-snoozy
Nomic AI · Non-commercial
956±16
1,743N/AN/A
332
330335
mpt-7b-chat
MosaicML · CC-BY-NC-SA-4.0
955±12
3,924N/AN/A
333
331335
RWKV-4-Raven-14B
RWKV · Apache 2.0
948±12
4,845N/AN/A
334
331337
chatglm2-6b
Tsinghua · Apache-2.0
939±14
2,658N/AN/A
335
331337
alpaca-13b
Stanford · Non-commercial
933±12
5,745N/AN/A
336
334338
chatglm-6b
Tsinghua · Non-commercial
918±13
4,914N/AN/A
337
334338
oasst-pythia-12b
OpenAssistant · Apache 2.0
916±11
6,310N/AN/A
338
336338
fastchat-t5-3b
LMSYS · Apache 2.0
894±13
4,203N/AN/A
339
339340
Stability
stablelm-tuned-alpha-7b
Stability AI · CC-BY-NC-SA-4.0
866±13
3,287N/AN/A
340
339341
dolly-v2-12b
Databricks · MIT
851±14
3,412N/AN/A
341
340341
Meta
llama-13b
Meta · Non-commercial
833±16
2,391$0.23 / $0.23N/A

Remove Style Control Leaderboard Plots

Fraction of Model A Wins for All Non-tied A vs. B Battles

Confidence Intervals on Model Strength (via Bootstrapping)

Battle Count for Each Combination of Models (without Ties)

Average Win Rate Against All Other Models (Uniform Sampling and No Ties)