Text Arena✍️Writing, Literature, & Language

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

Mar 31, 2026
1,373,389 votes
336 models
Rank Spread
1
16
Anthropic
claude-opus-4-6-thinking
Anthropic · Proprietary
1497±11
3,162$5 / $251M
2
17
gemini-3.1-pro-preview
Google · Proprietary
1487±10
3,845$2 / $121M
3
110
Anthropic
claude-opus-4-6
Anthropic · Proprietary
1483±11
3,274$5 / $251M
4
17
gemini-3-pro
Google · Proprietary
1481±7
9,349$2 / $121M
5
116
gpt-5.4-high
OpenAI · Proprietary
1475±15
1,584$2.50 / $151.1M
6
117
grok-4.20-beta1
xAI · Proprietary
1471±15
1,538N/AN/A
7
416
Anthropic
claude-opus-4-5-20251101
Anthropic · Proprietary
1467±7
9,907$5 / $25200K
8
416
Anthropic
claude-opus-4-5-20251101-thinking-32k
Anthropic · Proprietary
1466±7
8,413$5 / $25200K
9
223
grok-4.20-beta-0309-reasoning
xAI · Proprietary
1464±15
1,608$2 / $62M
10
518
gemini-3-flash
Google · Proprietary
1463±8
6,903$0.50 / $31M
11
427
gpt-5.4
OpenAI · Proprietary
1459±15
1,583$2.50 / $151.1M
12
529
qwen3.5-max-preview
Alibaba · Proprietary
1456±16
1,287N/AN/A
13
528
gpt-5.2-chat-latest-20260210
OpenAI · Proprietary
1454±11
2,945$1.75 / $14128K
14
527
gemini-3-flash (thinking-minimal)
Google · Proprietary
1454±8
6,696$0.50 / $31M
15
529
Anthropic
claude-sonnet-4-6
Anthropic · Proprietary
1453±12
2,373$3 / $151M
16
827
Anthropic
claude-sonnet-4-5-20250929
Anthropic · Proprietary
1453±6
12,394$3 / $15200K
17
1027
gemini-2.5-pro
Google · Proprietary
1449±5
23,263$1.25 / $101M
18
536
grok-4.20-multi-agent-beta-0309
xAI · Proprietary
1446±14
1,694$2 / $62M
19
932
gpt-4.5-preview-2025-02-27
OpenAI · Proprietary
1446±10
4,092$75 / $150128K
20
1029
Anthropic
claude-opus-4-1-20250805-thinking-16k
Anthropic · Proprietary
1445±6
11,099$15 / $75200K
21
1029
Anthropic
claude-sonnet-4-5-20250929-thinking-32k
Anthropic · Proprietary
1444±6
12,973$3 / $15200K
22
1129
Anthropic
claude-opus-4-1-20250805
Anthropic · Proprietary
1443±5
17,392$15 / $75200K
23
1038
glm-5
Z.ai · MIT
1440±11
2,710$1 / $3.20202.8K
24
1538
gpt-5.1-high
OpenAI · Proprietary
1436±7
9,154$1.25 / $10400K
25
1144
gpt-5.3-chat-latest
OpenAI · Proprietary
1435±12
2,623$1.75 / $14128K
26
1150
mimo-v2-pro
Xiaomi · Proprietary
1433±16
1,369$1 / $31M
27
1053
gemma-4-31b
Google · Apache 2.0
1432±18
1,035N/AN/A
28
1649
qwen3.5-397b-a17b
Alibaba · Apache 2.0
1430±11
2,856$0.39 / $2.34262.1K
29
2144
grok-4.1-thinking
xAI · Proprietary
1430±7
10,096N/AN/A
30
2242
chatgpt-4o-latest-20250326
OpenAI · Proprietary
1430±5
18,739$5 / $15128K
31
2145
Anthropic
claude-opus-4-20250514-thinking-16k
Anthropic · Proprietary
1429±7
7,974$15 / $75200K
32
1160
gpt-5.4-mini-high
OpenAI · Proprietary
1429±18
1,001$0.75 / $4.50400K
33
2247
grok-4.1
xAI · Proprietary
1427±7
10,559N/AN/A
34
2251
kimi-k2.5-thinking
Moonshot · Modified MIT
1426±10
3,968$0.60 / $3N/A
35
2153
gemini-3.1-flash-lite-preview
Google · Proprietary
1426±11
2,853$0.25 / $1.501M
36
2349
gpt-5.1
OpenAI · Proprietary
1424±7
9,852$1.25 / $10400K
37
2253
ernie-5.0-0110
Baidu · Proprietary
1423±9
4,645N/AN/A
38
2659
Anthropic
claude-opus-4-20250514
Anthropic · Proprietary
1418±7
9,527$15 / $75200K
39
2566
glm-4.7
Z.ai · MIT
1417±11
2,805$0.39 / $1.75202.8K
40
2865
gpt-5.2
OpenAI · Proprietary
1415±8
5,627$1.75 / $14400K
41
2573
ernie-5.0-preview-1203
Baidu · Proprietary
1415±13
2,176N/AN/A
42
2675
deepseek-v3.2-exp
DeepSeek · MIT
1413±12
2,636$0.27 / $0.41163.8K
43
3070
gpt-5.2-high
OpenAI · Proprietary
1412±8
6,203$1.75 / $14400K
44
2585
gemma-4-26b-a4b
Google · Apache 2.0
1411±18
1,034N/AN/A
45
3372
deepseek-v3.2
DeepSeek · MIT
1410±7
8,471$0.26 / $0.38163.8K
46
2979
deepseek-v3.1-thinking
DeepSeek · MIT
1409±11
2,774$1.23 / $4.94N/A
47
2395
deepseek-v3.1-terminus-thinking
DeepSeek · MIT
1408±21
777$0.21 / $0.79163.8K
48
2595
deepseek-v3.1-terminus
DeepSeek · MIT
1408±21
815$0.21 / $0.79163.8K
49
3779
grok-3-preview-02-24
xAI · Proprietary
1406±7
7,840$3 / $15131.1K
50
3085
kimi-k2.5-instant
Moonshot · Modified MIT
1406±14
1,856$0.38 / $1.91262.1K
51
3779
glm-4.6
Z.ai · MIT
1406±7
8,066$0.39 / $1.90204.8K
52
3779
gpt-5-chat
OpenAI · Proprietary
1406±8
6,860$1.25 / $10128K
53
3779
qwen3-max-preview
Alibaba · Proprietary
1405±8
6,271$0.78 / $3.90262.1K
54
3975
gemini-2.5-flash
Google · Proprietary
1405±5
23,331$0.30 / $2.501M
55
3779
grok-4-1-fast-reasoning
xAI · Proprietary
1404±7
9,022$0.20 / $0.502M
56
3290
qwen3-max-2025-09-23
Alibaba · Proprietary
1404±13
1,995$0.78 / $3.90262.1K
57
2995
ernie-5.0-preview-1022
Baidu · Proprietary
1404±17
1,118N/AN/A
58
3981
gpt-4.1-2025-04-14
OpenAI · Proprietary
1403±6
11,487$2 / $81M
59
3983
deepseek-v3.2-thinking
DeepSeek · MIT
1402±7
7,582$0.26 / $0.38163.8K
60
3795
qwen3.5-122b-a10b
Alibaba · Apache 2.0
1399±13
2,118$0.26 / $2.08262.1K
61
4185
kimi-k2-thinking-turbo
Moonshot · Modified MIT
1399±7
9,964$1.15 / $8262.1K
62
4188
grok-4-0709
xAI · Proprietary
1399±7
9,234$3 / $15256K
63
3992
deepseek-v3.1
DeepSeek · MIT
1399±10
3,502$1.23 / $4.94N/A
64
4285
qwen3-235b-a22b-instruct-2507
Alibaba · Apache 2.0
1398±5
17,723$0.26 / $1.06N/A
65
3898
deepseek-v3.2-exp-thinking
DeepSeek · MIT
1397±13
2,110$0.27 / $0.41163.8K
66
4192
gpt-5-high
OpenAI · Proprietary
1397±8
7,103$1.25 / $10400K
67
4192
Anthropic
claude-sonnet-4-20250514-thinking-32k
Anthropic · Proprietary
1397±7
7,568$3 / $151M
68
4292
o1-2024-12-17
OpenAI · Proprietary
1396±7
7,663$15 / $60200K
69
4491
o3-2025-04-16
OpenAI · Proprietary
1396±6
13,424$2 / $8200K
70
4395
gemini-2.5-flash-preview-09-2025
Google · Proprietary
1395±7
7,377$0.30 / $2.501M
71
39100
grok-4-fast-chat
xAI · Proprietary
1395±15
1,541$3 / $15256K
72
34110
longcat-flash-chat-2602-exp
Meituan · Proprietary
1395±20
831N/AN/A
73
4495
mistral-large-3
Mistral · Apache 2.0
1395±7
8,132$0.50 / $1.50N/A
74
4692
Anthropic
claude-haiku-4-5-20251001
Anthropic · Proprietary
1394±6
12,485$1 / $5200K
75
34113
Bytedance
dola-seed-2.0-pro
Bytedance · Proprietary
1392±23
618N/AN/A
76
5298
Anthropic
claude-3-7-sonnet-20250219-thinking-32k
Anthropic · Proprietary
1391±7
8,911$3 / $15200K
77
46100
deepseek-r1-0528
DeepSeek · MIT
1390±10
4,277$0.45 / $2.15163.8K
78
46103
minimax-m2.5
MiniMax · Modified MIT
1389±10
3,344$0.12 / $1196.6K
79
52103
grok-4-fast-reasoning
xAI · Proprietary
1388±9
4,225$0.20 / $0.502M
80
46110
qwen3-vl-235b-a22b-instruct
Alibaba · Apache 2.0
1387±13
2,388$0.20 / $0.88262.1K
81
54100
Anthropic
claude-sonnet-4-20250514
Anthropic · Proprietary
1387±7
8,694$3 / $151M
82
60100
mistral-medium-2508
Mistral · Proprietary
1386±5
16,845$2.70 / $8.1032K
83
59103
deepseek-v3-0324
DeepSeek · MIT
1385±6
10,418$3 / $4.5032.8K
84
58109
glm-4.5
Z.ai · MIT
1384±8
5,411$0.60 / $2.20131.1K
85
61111
deepseek-r1
DeepSeek · MIT
1381±8
5,355$0.70 / $2.5064K
86
58113
kimi-k2-0905-preview
Moonshot · Modified MIT
1381±12
2,608$0.60 / $2.50262.1K
87
39125
Tencent
hunyuan-vision-1.5-thinking
Tencent · Proprietary
1381±26
491N/AN/A
88
66112
o1-preview
OpenAI · Proprietary
1380±8
8,360$15 / $60N/A
89
59117
qwen3.5-flash
Alibaba · Proprietary
1379±12
2,187N/AN/A
90
72112
qwen3-235b-a22b-no-thinking
Alibaba · Apache 2.0
1379±7
8,152$0.46 / $1.82131.1K
91
58118
qwen3-235b-a22b-thinking-2507
Alibaba · Apache 2.0
1379±14
1,889$0.15 / $1.50131.1K
92
72112
gemini-2.5-flash-lite-preview-06-17-thinking
Google · Proprietary
1379±7
7,160$0.10 / $0.401M
93
53124
amazon-nova-experimental-chat-12-10
Amazon · Proprietary
1376±20
842N/AN/A
94
74112
Anthropic
claude-3-7-sonnet-20250219
Anthropic · Proprietary
1376±6
9,852$3 / $15200K
95
53126
amazon-nova-experimental-chat-26-02-10
Amazon · Proprietary
1375±21
700N/AN/A
96
78113
Anthropic
claude-3-5-sonnet-20241022
Anthropic · Proprietary
1374±5
21,914$6 / $30200K
97
54128
amazon-nova-experimental-chat-26-01-10
Amazon · Proprietary
1374±21
771N/AN/A
98
72120
qwen3.5-27b
Alibaba · Apache 2.0
1373±13
2,012$0.20 / $1.56262.1K
99
78118
mimo-v2-flash (non-thinking)
Xiaomi · MIT
1372±8
6,261$0.09 / $0.29262.1K
100
78118
kimi-k2-0711-preview
Moonshot · Modified MIT
1371±8
6,071$0.60 / $2.50131.1K
101
81118
gemini-2.5-flash-lite-preview-09-2025-no-thinking
Google · Proprietary
1371±6
10,561$0.10 / $0.401M
102
74124
qwen3.5-35b-a3b
Alibaba · Apache 2.0
1370±13
2,141$0.16 / $1.30262.1K
103
66132
Tencent
hunyuan-t1-20250711
Tencent · Proprietary
1369±18
1,021N/AN/A
104
81119
mistral-medium-2505
Mistral · Proprietary
1369±8
7,252$0.40 / $2131.1K
105
66134
minimax-m2.7
MiniMax · Proprietary
1369±19
950$0.30 / $1.20204.8K
106
81124
Stepfun
step-3.5-flash
StepFun · Apache 2.0
1368±10
3,657$0.10 / $0.30262.1K
107
82124
qwen3-coder-480b-a35b-instruct
Alibaba · Apache 2.0
1367±8
5,412$0.40 / $1.60262.1K
108
81125
minimax-m2.1-preview
MiniMax · MIT
1366±10
3,951$0.27 / $0.95196.6K
109
81133
qwen3-vl-235b-a22b-thinking
Alibaba · Apache 2.0
1364±14
1,774$0.26 / $2.60131.1K
110
85128
mai-1-preview
Microsoft AI · Proprietary
1362±10
3,949N/AN/A
111
92125
qwen2.5-max
Alibaba · Proprietary
1362±7
8,222N/AN/A
112
93130
gpt-4.1-mini-2025-04-14
OpenAI · Proprietary
1359±7
8,735$0.40 / $1.601M
113
89141
trinity-large
Arcee AI · Apache 2.0
1358±12
2,385N/AN/A
114
92142
longcat-flash-chat
Meituan · MIT
1356±12
2,522$0.20 / $0.80131.1K
115
92142
mimo-v2-flash (thinking)
Xiaomi · MIT
1355±12
2,451$0.09 / $0.29262.1K
116
92142
Tencent
hunyuan-turbos-20250416
Tencent · Proprietary
1355±12
2,555N/AN/A
117
97138
deepseek-v3
DeepSeek · DeepSeek
1355±8
5,913$1.14 / $4.56N/A
118
81157
glm-4.6v
Z.ai · MIT
1355±24
611$0.30 / $0.90131.1K
119
84153
gpt-5.4-nano-high
OpenAI · Proprietary
1354±20
882$0.20 / $1.25400K
120
99138
gemma-3-27b-it
Google · Gemma
1354±6
10,752$0.08 / $0.16131.1K
121
99138
gemini-2.0-flash-001
Google · Proprietary
1354±6
10,582$0.10 / $0.401M
122
99139
o4-mini-2025-04-16
OpenAI · Proprietary
1353±6
10,136$1.10 / $4.40200K
123
99138
gemini-1.5-pro-002
Google · Proprietary
1353±6
14,953$3.50 / $10.502.1M
124
98142
gpt-5-mini-high
OpenAI · Proprietary
1352±8
6,192$0.25 / $2400K
125
107143
Cohere
command-a-03-2025
Cohere · CC-BY-NC-4.0
1347±6
12,905$2.50 / $10256K
126
103148
grok-3-mini-high
xAI · Proprietary
1347±10
3,638$0.30 / $0.50131.1K
127
106146
gemini-2.0-flash-lite-preview-02-05
Google · Proprietary
1346±7
6,681$0.07 / $0.301M
128
107149
qwen3-next-80b-a3b-instruct
Alibaba · Apache 2.0
1345±8
5,128$0.09 / $1.10262.1K
129
109148
qwen3-235b-a22b
Alibaba · Apache 2.0
1344±8
6,213$0.46 / $1.82131.1K
130
113148
gpt-4o-2024-05-13
OpenAI · Proprietary
1343±6
29,959$5 / $15128K
131
110151
qwen3-30b-a3b-instruct-2507
Alibaba · Apache 2.0
1343±8
5,147$0.09 / $0.30262.1K
132
112150
glm-4.5-air
Z.ai · MIT
1342±7
7,105$0.13 / $0.85131.1K
133
111154
grok-3-mini-beta
xAI · Proprietary
1342±9
4,837$0.30 / $0.50131.1K
134
113156
o3-mini-high
OpenAI · Proprietary
1340±9
4,762$1.10 / $4.40200K
135
118155
gpt-4o-2024-08-06
OpenAI · Proprietary
1339±7
12,147$2.50 / $10128K
136
113161
qwen3-next-80b-a3b-thinking
Alibaba · Apache 2.0
1338±11
3,117$0.10 / $0.78131.1K
137
118158
gemini-advanced-0514
Google · Proprietary
1338±8
13,201N/AN/A
138
110167
intellect-3
Prime Intellect · MIT
1335±17
1,283$0.20 / $1.10131.1K
139
123163
amazon-nova-experimental-chat-11-10
Amazon · Proprietary
1334±8
5,711N/AN/A
140
119164
glm-4.7-flash
Z.ai · MIT
1333±12
2,565$0.06 / $0.40202.8K
141
125163
gemini-1.5-pro-001
Google · Proprietary
1332±7
20,950$3.50 / $10.502.1M
142
117171
glm-4-plus-0111
Zhipu · Proprietary
1332±15
1,459N/AN/A
143
109186
Tencent
hunyuan-turbos-20250226
Tencent · Proprietary
1331±21
662N/AN/A
144
125164
minimax-m1
MiniMax · Apache 2.0
1331±7
7,882$0.40 / $2.201M
145
124165
mistral-small-2506
Mistral · Apache 2.0
1329±10
3,822$0.10 / $0.3032K
146
130164
Anthropic
claude-3-5-sonnet-20240620
Anthropic · Proprietary
1329±6
21,916$6 / $30200K
147
131164
gpt-4-turbo-2024-04-09
OpenAI · Proprietary
1328±6
24,529$10 / $30128K
148
113192
nvidia-nemotron-3-super-120b-a12b
Nvidia · NVIDIA Open Model
1327±21
742N/AN/A
149
134165
grok-2-2024-08-13
xAI · Proprietary
1326±6
17,406$2 / $10131.1K
150
137171
o3-mini
OpenAI · Proprietary
1323±6
13,498$1.10 / $4.40200K
151
124196
Tencent
hunyuan-turbo-0110
Tencent · Proprietary
1322±20
711N/AN/A
152
129192
qwen-plus-0125
Alibaba · Proprietary
1321±15
1,512$0.40 / $1.20131.1K
153
124199
llama-3.1-nemotron-ultra-253b-v1
Nvidia · Nvidia Open Model
1320±21
712$0.60 / $1.80131.1K
154
128196
glm-4.5v
Z.ai · MIT
1319±17
1,102$0.60 / $1.8065.5K
155
131194
Stepfun
step-2-16k-exp-202412
StepFun · Proprietary
1319±16
1,326N/AN/A
156
133196
Stepfun
step-3
StepFun · Apache 2.0
1317±15
1,425$0.57 / $1.4265.5K
157
137192
amazon-nova-experimental-chat-10-20
Amazon · Proprietary
1316±12
2,528N/AN/A
158
146189
Anthropic
claude-3-opus-20240229
Anthropic · Proprietary
1314±5
49,929$15 / $75200K
159
144191
Meta
llama-3.1-405b-instruct-fp8
Meta · Llama 3.1 Community
1314±6
15,999$4 / $432.8K
160
138197
deepseek-v2.5-1210
DeepSeek · DeepSeek
1314±13
1,930N/AN/A
161
135203
gemma-3-12b-it
Google · Gemma
1313±18
1,010$0.04 / $0.13131.1K
162
147192
gpt-4o-mini-2024-07-18
OpenAI · Proprietary
1313±6
18,539$0.15 / $0.60128K
163
147192
Meta
llama-4-maverick-17b-128e-instruct
Meta · Llama 4
1311±7
8,834$0.63 / $1.80131.1K
164
149192
Anthropic
claude-3-5-haiku-20241022
Anthropic · Proprietary
1311±5
17,016$0.80 / $4200K
165
132209
llama-3.3-nemotron-49b-super-v1
Nvidia · Nvidia
1311±23
614N/AN/A
166
147194
gpt-oss-120b
OpenAI · Apache 2.0
1310±8
6,742$0.04 / $0.19131.1K
167
149192
Meta
llama-3.1-405b-instruct-bf16
Meta · Llama 3.1 Community
1310±6
11,150$4 / $432.8K
168
149194
o1-mini
OpenAI · Proprietary
1309±6
14,272$1.10 / $4.40N/A
169
149196
gemini-1.5-flash-002
Google · Proprietary
1308±7
9,441$0.07 / $0.301M
170
138206
Tencent
hunyuan-large-2025-02-10
Tencent · Proprietary
1308±19
890N/AN/A
171
149197
glm-4-plus
Zhipu AI · Proprietary
1308±8
7,164$0.44 / $1.76204.8K
172
149197
qwq-32b
Alibaba · Apache 2.0
1308±8
6,194$0.15 / $0.58131.1K
173
140205
qwen3-32b
Alibaba · Apache 2.0
1308±17
1,121$0.08 / $0.2441K
174
136218
amazon-nova-experimental-chat-10-09
Amazon · Proprietary
1307±23
622N/AN/A
175
137218
mercury-2
Inception AI · Proprietary
1307±23
689$0.25 / $0.75128K
176
149201
qwen-max-0919
Alibaba · Qwen
1306±9
4,631$1.60 / $6.4032.8K
177
149199
gpt-4-1106-preview
OpenAI · Proprietary
1306±6
24,682$10 / $30128K
178
149199
Meta
llama-4-scout-17b-16e-instruct
Meta · Llama
1305±8
6,799$0.40 / $0.708.2K
179
149201
qwen3-30b-a3b
Alibaba · Apache 2.0
1305±8
6,012$0.08 / $0.2841K
180
150200
gpt-4-0125-preview
OpenAI · Proprietary
1303±7
23,492$10 / $30128K
181
149207
Stepfun
step-1o-turbo-202506
StepFun · Proprietary
1302±14
1,858N/AN/A
182
150205
01.AI
yi-lightning
01 AI · Proprietary
1302±8
7,632N/AN/A
183
149206
nova-2-lite
Amazon · Proprietary
1302±12
2,776$0.30 / $2.501M
184
147213
minimax-m2
MiniMax · Apache 2.0
1302±16
1,487$0.26 / $1196.6K
185
149206
olmo-3.1-32b-instruct
Ai2 · Apache 2.0
1301±12
2,671$0.20 / $0.6065.5K
186
151204
mistral-large-2407
Mistral · Mistral Research
1301±7
12,224$2 / $6131.1K
187
151205
gemma-3n-e4b-it
Google · Gemma
1300±9
4,937$0.02 / $0.0432.8K
188
149220
gpt-4.1-nano-2025-04-14
OpenAI · Proprietary
1298±14
1,583$0.10 / $0.401M
189
149221
gemma-3-4b-it
Google · Gemma
1297±17
1,080$0.04 / $0.08131.1K
190
146223
nvidia-llama-3.3-nemotron-super-49b-v1.5
Nvidia · Nvidia Open
1297±22
667$0.10 / $0.40131.1K
191
159206
mistral-large-2411
Mistral · MRL
1297±7
7,416$2 / $6131.1K
192
166206
gemma-2-27b-it
Google · Gemma license
1295±5
20,390$0.65 / $0.658.2K
193
169211
grok-2-mini-2024-08-13
xAI · Proprietary
1293±6
14,508$2 / $10131.1K
194
150224
Tencent
hunyuan-standard-2025-02-10
Tencent · Proprietary
1292±18
937N/AN/A
195
175216
Meta
llama-3.3-70b-instruct
Meta · Llama-3.3
1291±6
13,876$0.10 / $0.32131.1K
196
162222
magistral-medium-2506
Mistral · Proprietary
1290±12
2,431$2 / $540K
197
173220
gemini-1.5-flash-001
Google · Proprietary
1290±7
16,463$0.07 / $0.301M
198
159223
gpt-5-nano-high
OpenAI · Proprietary
1290±14
1,747$0.05 / $0.40400K
199
152225
Tencent
hunyuan-large-vision
Tencent · Proprietary
1290±18
1,091N/AN/A
200
172220
mistral-small-3.1-24b-instruct-2503
Mistral · Apache 2.0
1289±7
7,181$0.10 / $0.3032K
201
169222
qwen2.5-plus-1127
Alibaba · Proprietary
1289±11
2,823N/AN/A
202
162224
ring-flash-2.0
Ant Group · MIT
1287±15
1,505N/AN/A
203
180223
deepseek-v2.5
DeepSeek · DeepSeek
1282±8
6,613N/AN/A
204
186223
gpt-4-0613
OpenAI · Proprietary
1282±7
22,099$30 / $608.2K
205
187223
qwen2.5-72b-instruct
Alibaba · Qwen
1281±7
10,827$1.20 / $1.20N/A
206
185224
gpt-4-0314
OpenAI · Proprietary
1281±8
12,861$30 / $608.2K
207
176230
ling-flash-2.0
Ant Group · MIT
1280±15
1,476N/AN/A
208
176230
olmo-3-32b-think
Ai2 · Apache 2.0
1278±17
1,347$0.15 / $0.5065.5K
209
189225
athene-v2-chat
NexusFlow · NexusFlow
1278±8
6,686N/AN/A
210
175232
llama-3.1-tulu-3-70b
Ai2 · Llama 3.1
1277±20
758N/AN/A
211
189227
athene-70b-0725
NexusFlow · CC-BY-NC-4.0
1277±9
5,378N/AN/A
212
188230
Cohere
command-r-plus-08-2024
Cohere · CC-BY-NC-4.0
1276±11
2,672$2.50 / $10128K
213
187230
jamba-1.5-large
AI21 Labs · Jamba Open
1275±13
2,350$2 / $8256K
214
190230
nvidia-nemotron-3-nano-30b-a3b-bf16
Nvidia · NVIDIA Open Model
1274±10
3,520$0.06 / $0.24262.1K
215
188231
gpt-oss-20b
OpenAI · Apache 2.0
1274±13
2,198$0.03 / $0.11131.1K
216
195228
amazon-nova-pro-v1.0
Amazon · Proprietary
1273±7
6,609$0.80 / $3.20300K
217
192231
gemma-2-9b-it-simpo
Princeton · MIT
1272±12
2,801$0.03 / $0.098.2K
218
190232
reka-core-20240904
Reka AI · Proprietary
1271±14
1,890N/AN/A
219
192232
olmo-3.1-32b-think
Ai2 · Apache 2.0
1270±14
1,965$0.15 / $0.5065.5K
220
203231
Anthropic
claude-3-sonnet-20240229
Anthropic · Proprietary
1267±7
27,297$3 / $15200K
221
189237
llama-3.1-nemotron-51b-instruct
Nvidia · Llama 3.1
1267±18
1,007N/AN/A
222
206232
gemma-2-9b-it
Google · Gemma license
1266±6
14,640$0.03 / $0.098.2K
223
196235
llama-3.1-nemotron-70b-instruct
Nvidia · Llama 3.1
1265±14
1,828$1.20 / $1.20131.1K
224
208232
Meta
llama-3.1-70b-instruct
Meta · Llama 3.1 Community
1262±6
14,962$0.40 / $0.40131.1K
225
186244
mercury
Inception AI · Proprietary
1260±29
463$0.25 / $0.75128K
226
198240
ibm-granite-h-small
IBM · Apache 2.0
1260±18
1,224N/AN/A
227
210236
Cohere
command-r-plus
Cohere · CC-BY-NC-4.0
1258±7
19,567$2.50 / $10128K
228
209239
nemotron-4-340b-instruct
Nvidia · NVIDIA Open Model
1257±9
5,386N/AN/A
229
208240
reka-flash-20240904
Reka AI · Proprietary
1257±13
1,950N/AN/A
230
218240
gemini-1.5-flash-8b-001
Google · Proprietary
1253±7
9,499$0.07 / $0.301M
231
215240
Cohere
c4ai-aya-expanse-32b
Cohere · CC-BY-NC-4.0
1253±8
7,297N/AN/A
232
210241
glm-4-0520
Zhipu AI · Proprietary
1252±12
2,609N/AN/A
233
223240
Meta
llama-3-70b-instruct
Meta · Llama 3 Community
1248±6
37,706$0.51 / $0.748.2K
234
223242
mistral-small-24b-instruct-2501
Mistral · Apache 2.0
1247±9
3,942$0.05 / $0.0832.8K
235
224242
Anthropic
claude-3-haiku-20240307
Anthropic · Proprietary
1244±6
29,876$0.25 / $1.25200K
236
226243
qwen2-72b-instruct
Alibaba · Qianwen LICENSE
1241±8
9,976$0.90 / $0.9032.8K
237
225246
deepseek-coder-v2
DeepSeek · DeepSeek License
1239±11
3,882$0.14 / $0.28128K
238
227244
amazon-nova-lite-v1.0
Amazon · Proprietary
1238±8
5,254$0.06 / $0.24300K
239
226249
Cohere
command-r-08-2024
Cohere · CC-BY-NC-4.0
1237±12
2,597$0.15 / $0.60128K
240
223258
olmo-2-0325-32b-instruct
Ai2 · Apache-2.0
1232±19
872$0.05 / $0.20128K
241
235253
phi-4
Microsoft · MIT
1228±8
6,470$0.07 / $0.1416.4K
242
232258
qwen2.5-coder-32b-instruct
Alibaba · Apache 2.0
1227±15
1,540$0.87 / $0.8732K
243
233259
ministral-8b-2410
Mistral · MRL
1224±16
1,350$0.10 / $0.10131.1K
244
236254
mistral-large-2402
Mistral · Proprietary
1224±8
15,192$4 / $1232K
245
238258
gpt-3.5-turbo-0125
OpenAI · Proprietary
1222±7
16,149$0.50 / $1.5016.4K
246
238258
amazon-nova-micro-v1.0
Amazon · Proprietary
1221±8
5,246$0.04 / $0.14128K
247
239260
qwen1.5-110b-chat
Alibaba · Qianwen LICENSE
1217±9
6,502N/AN/A
248
239261
gemini-pro-dev-api
Google · Proprietary
1214±12
4,634$0.35 / $1.0532.8K
249
240263
jamba-1.5-mini
AI21 Labs · Jamba Open
1212±13
2,361$0.20 / $0.40256K
250
240261
qwen1.5-72b-chat
Alibaba · Qianwen LICENSE
1212±9
9,492N/AN/A
251
240262
Cohere
c4ai-aya-expanse-8b
Cohere · CC-BY-NC-4.0
1212±11
2,746N/AN/A
252
242262
mixtral-8x22b-instruct-v0.1
Mistral · Apache 2.0
1207±8
12,808$0.90 / $0.9065.5K
253
239269
Tencent
hunyuan-standard-256k
Tencent · Proprietary
1207±21
752N/AN/A
254
242263
Cohere
command-r
Cohere · CC-BY-NC-4.0
1207±8
13,537$0.15 / $0.60128K
255
242265
mistral-medium
Mistral · Proprietary
1206±9
8,402$2.70 / $8.1032K
256
240269
gemini-pro
Google · Proprietary
1204±19
1,319$0.35 / $1.0532.8K
257
242266
reka-flash-21b-20240226-online
Reka AI · Proprietary
1202±12
3,632N/AN/A
258
241273
llama-3.1-tulu-3-8b
Ai2 · Llama 3.1
1200±20
816N/AN/A
259
248269
reka-flash-21b-20240226
Reka AI · Proprietary
1196±10
5,831N/AN/A
260
246276
zephyr-orpo-141b-A35b-v0.1
HuggingFace · Apache 2.0
1193±18
1,129N/AN/A
261
247275
wizardlm-70b
Microsoft · Llama 2 Community
1193±15
2,313N/AN/A
262
254269
gemma-2-2b-it
Google · Gemma license
1192±6
12,543N/AN/A
263
255270
Meta
llama-3-8b-instruct
Meta · Llama 3 Community
1190±7
25,481$0.03 / $0.048.2K
264
250277
gpt-3.5-turbo-1106
OpenAI · Proprietary
1187±13
3,932$1 / $216.4K
265
256276
Meta
llama-3.1-8b-instruct
Meta · Llama 3.1 Community
1182±7
13,505$0.02 / $0.0516.4K
266
254288
granite-3.1-8b-instruct
IBM · Apache 2.0
1178±21
837N/AN/A
267
260282
dbrx-instruct-preview
Databricks · DBRX LICENSE
1174±10
7,999$0.60 / $0.6032.8K
268
261282
01.AI
yi-1.5-34b-chat
01 AI · Apache-2.0
1174±9
6,540N/AN/A
269
256287
openchat-3.5
OpenChat · Apache-2.0
1174±15
1,995$0.20 / $0.20N/A
270
262283
phi-3-medium-4k-instruct
Microsoft · MIT
1171±9
6,655$0.17 / $0.68N/A
271
261284
qwen1.5-32b-chat
Alibaba · Qianwen LICENSE
1170±10
5,401N/AN/A
272
262286
vicuna-33b
LMSYS · Non-commercial
1169±10
5,627$0 / $02K
273
263283
mixtral-8x7b-instruct-v0.1
Mistral · Apache 2.0
1169±7
17,942$0.63 / $0.6332K
274
256292
deepseek-llm-67b-chat
DeepSeek · DeepSeek License
1168±19
1,142N/AN/A
275
252301
falcon-180b-chat
TII · Falcon-180B TII License
1168±32
342N/AN/A
276
261295
tulu-2-dpo-70b
AllenAI/UW · AI2 ImpACT Low-risk
1164±17
1,547N/AN/A
277
266292
qwen1.5-14b-chat
Alibaba · Qianwen LICENSE
1163±11
4,502$0.30 / $0.30N/A
278
266292
01.AI
yi-34b-chat
01 AI · Yi License
1162±11
3,702$0.90 / $0.904.1K
279
266293
openchat-3.5-0106
OpenChat · Apache-2.0
1161±12
3,121N/AN/A
280
266294
snowflake-arctic-instruct
Snowflake · Apache 2.0
1158±10
7,241N/AN/A
281
265299
openhermes-2.5-mistral-7b
NousResearch · Apache-2.0
1156±18
1,136$0.17 / $0.17N/A
282
268298
internlm2_5-20b-chat
InternLM · Other
1151±12
2,757$0 / $032.8K
283
266301
wizardlm-13b
Microsoft · Llama 2 Community
1151±15
1,814$0.30 / $0.30N/A
284
271297
gemma-1.1-7b-it
Google · Gemma license
1150±9
6,034$0.03 / $0.098.2K
285
274302
vicuna-13b
LMSYS · Llama 2 Community
1143±11
4,672$0.30 / $0.30N/A
286
274304
granite-3.0-8b-instruct
IBM · Apache 2.0
1141±16
1,751N/AN/A
287
274304
Meta
llama-3.2-3b-instruct
Meta · Llama 3.2
1141±14
2,118$0.05 / $0.3480K
288
271306
nous-hermes-2-mixtral-8x7b-dpo
NousResearch · Apache-2.0
1139±20
858$0.90 / $0.90N/A
289
277303
phi-3-small-8k-instruct
Microsoft · MIT
1139±10
4,639$0.15 / $0.60N/A
290
274304
starling-lm-7b-alpha
UC Berkeley · CC-BY-NC-4.0
1138±13
2,509N/AN/A
291
273308
solar-10.7b-instruct-v1.0
Upstage AI · CC-BY-NC-4.0
1137±21
894$0.30 / $0.30N/A
292
270308
mpt-30b-chat
MosaicML · CC-BY-NC-SA-4.0
1137±23
647N/AN/A
293
272316
dolphin-2.2.1-mistral-7b
Cognitive Computations · Apache-2.0
1130±29
382$0.50 / $0.5016.4K
294
282305
Meta
llama-2-70b-chat
Meta · Llama 2 Community
1129±9
9,591$0.70 / $2.804.1K
295
281308
starling-lm-7b-beta
Nexusflow · Apache-2.0
1127±12
4,016N/AN/A
296
278314
llama2-70b-steerlm-chat
Nvidia · Llama 2 Community
1127±22
836N/AN/A
297
279314
granite-3.1-2b-instruct
IBM · Apache 2.0
1126±21
850N/AN/A
298
280317
zephyr-7b-alpha
HuggingFace · MIT
1121±25
569N/AN/A
299
280317
guanaco-33b
UW · Non-commercial
1121±23
714N/AN/A
300
285314
zephyr-7b-beta
HuggingFace · MIT
1120±14
2,691$0.15 / $0.1516.4K
301
283317
qwen-14b-chat
Alibaba · Qianwen LICENSE
1118±18
1,230N/AN/A
302
283318
qwq-32b-preview
Alibaba · Apache 2.0
1116±21
855$0.15 / $0.58131.1K
303
287317
vicuna-7b
LMSYS · Llama 2 Community
1113±15
1,783$0.20 / $0.20N/A
304
290316
mistral-7b-instruct-v0.2
Mistral · Apache-2.0
1112±11
4,703$0.20 / $0.2032.8K
305
286318
qwen1.5-7b-chat
Alibaba · Qianwen LICENSE
1111±18
1,093$0.20 / $0.20N/A
306
291321
granite-3.0-2b-instruct
IBM · Apache 2.0
1104±16
1,820N/AN/A
307
295318
Meta
llama-2-13b-chat
Meta · Llama 2 Community
1103±11
4,785$0.25 / $0.254.1K
308
292322
Meta
codellama-34b-instruct
Meta · Llama 2 Community
1102±15
2,003$0.35 / $1.4016.4K
309
292322
gemma-7b-it
Google · Gemma license
1102±15
2,191$0.05 / $0.088.2K
310
295319
phi-3-mini-4k-instruct-june-2024
Microsoft · MIT
1102±11
3,382$0.13 / $0.524.1K
311
295323
phi-3-mini-128k-instruct
Microsoft · MIT
1096±12
4,627$0.13 / $0.52N/A
312
295323
palm-2
Google · Proprietary
1093±15
2,155$0.50 / $0.5025.8K
313
295323
mistral-7b-instruct
Mistral · Apache 2.0
1093±15
2,336$0.07 / $0.284.1K
314
298323
phi-3-mini-4k-instruct
Microsoft · MIT
1091±11
5,207$0.13 / $0.52N/A
315
295325
stripedhyena-nous-7b
Together AI · Apache 2.0
1090±18
1,271$0.20 / $0.20N/A
316
300324
gemma-1.1-2b-it
Google · Gemma license
1088±13
2,596N/AN/A
317
298327
smollm2-1.7b-instruct
HuggingFace · Apache 2.0
1077±27
627N/AN/A
318
304327
alpaca-13b
Stanford · Non-commercial
1075±19
1,217N/AN/A
319
311326
Meta
llama-2-7b-chat
Meta · Llama 2 Community
1074±11
3,454$0.15 / $0.154.1K
320
308326
Meta
llama-3.2-1b-instruct
Meta · Llama 3.2
1074±15
2,047$0.03 / $0.2060K
321
309326
qwen1.5-4b-chat
Alibaba · Qianwen LICENSE
1073±15
1,895$0.10 / $0.10N/A
322
308330
gpt4all-13b-snoozy
Nomic AI · Non-commercial
1058±32
347N/AN/A
323
316329
gemma-2b-it
Google · Gemma license
1054±19
1,152$0.10 / $0.10N/A
324
307331
Meta
codellama-70b-instruct
Meta · Llama 2 Community
1053±37
262$0.70 / $2.8016.4K
325
315329
mpt-7b-chat
MosaicML · CC-BY-NC-SA-4.0
1053±21
892N/AN/A
326
317329
koala-13b
UC Berkeley · Non-commercial
1046±18
1,515N/AN/A
327
320331
chatglm3-6b
Tsinghua · Apache-2.0
1038±20
1,108N/AN/A
328
322332
olmo-7b-instruct
Ai2 · Apache-2.0
1022±18
1,511$0.20 / $0.20N/A
329
322334
chatglm2-6b
Tsinghua · Apache-2.0
1013±22
775N/AN/A
330
325334
oasst-pythia-12b
OpenAssistant · Apache 2.0
1009±18
1,408N/AN/A
331
326334
RWKV-4-Raven-14B
RWKV · Apache 2.0
1000±20
1,098N/AN/A
332
328334
fastchat-t5-3b
LMSYS · Apache 2.0
994±21
940N/AN/A
333
329334
chatglm-6b
Tsinghua · Non-commercial
979±21
1,056N/AN/A
334
329336
dolly-v2-12b
Databricks · MIT
970±23
732N/AN/A
335
334336
Stability
stablelm-tuned-alpha-7b
Stability AI · CC-BY-NC-SA-4.0
928±24
681N/AN/A
336
334336
Meta
llama-13b
Meta · Non-commercial
923±29
513$0.23 / $0.23N/A

Default Leaderboard Plots

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

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

Battle Count for Each Combination of Models (without Ties)

Confidence Intervals on Model Strength (via Bootstrapping)