Text Arena🧮Mathematical

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

Apr 10, 2026
472,373 votes
322 models
Rank Spread
1
19
Anthropic
claude-opus-4-6-thinking
Anthropic · Proprietary
1525±22
718$5 / $251M
2
113
Anthropic
claude-opus-4-6
Anthropic · Proprietary
1514±20
842$5 / $251M
3
122
gpt-5.4-high
OpenAI · Proprietary
1509±26
486$2.50 / $151.1M
4
126
qwen3.5-max-preview
Alibaba · Proprietary
1508±29
396N/AN/A
5
132
gemini-3.1-pro-preview
Google · Proprietary
1493±18
1,029$2 / $121M
6
138
grok-4.20-multi-agent-beta-0309
xAI · Proprietary
1488±27
488$2 / $62M
7
137
Anthropic
claude-sonnet-4-6
Anthropic · Proprietary
1488±25
558$3 / $151M
8
135
kimi-k2.5-thinking
Moonshot · Modified MIT
1485±20
854$0.60 / $3N/A
9
234
gemini-3-pro
Google · Proprietary
1483±13
1,990$2 / $121M
10
168
gemma-4-26b-a4b
Google · Apache 2.0
1473±32
300N/AN/A
11
347
gemini-3-flash
Google · Proprietary
1472±16
1,450$0.50 / $31M
12
342
Anthropic
claude-opus-4-5-20251101
Anthropic · Proprietary
1471±13
2,079$5 / $25200K
13
348
Anthropic
claude-opus-4-5-20251101-thinking-32k
Anthropic · Proprietary
1470±15
1,598$5 / $25200K
14
270
gemma-4-31b
Google · Apache 2.0
1469±31
317$0.14 / $0.40262.1K
15
444
Anthropic
claude-sonnet-4-5-20250929-thinking-32k
Anthropic · Proprietary
1468±11
2,719$3 / $15200K
16
281
glm-5.1
Z.ai · MIT
1468±34
284$0.95 / $3.15202.8K
17
364
glm-5
Z.ai · MIT
1466±22
684$1 / $3.20202.8K
18
369
gpt-5.4
OpenAI · Proprietary
1465±26
499$2.50 / $151.1M
19
458
gpt-5.2-high
OpenAI · Proprietary
1465±16
1,375$1.75 / $14400K
20
281
gpt-5.4-mini-high
OpenAI · Proprietary
1465±31
355$2.50 / $151.1M
21
381
grok-4.20-beta1
xAI · Proprietary
1462±28
407N/AN/A
22
368
gpt-5.2-chat-latest-20260210
OpenAI · Proprietary
1462±21
768$1.75 / $14128K
23
562
gpt-5.1-high
OpenAI · Proprietary
1460±14
1,756$1.25 / $10400K
24
382
grok-4.20-beta-0309-reasoning
xAI · Proprietary
1460±27
447$2 / $62M
25
564
gemini-3-flash (thinking-minimal)
Google · Proprietary
1460±15
1,510$0.50 / $31M
26
476
qwen3.5-27b
Alibaba · Apache 2.0
1459±23
619$0.20 / $1.56262.1K
27
383
mimo-v2-pro
Xiaomi · Proprietary
1458±27
470$1 / $31M
28
579
qwen3.5-397b-a17b
Alibaba · Apache 2.0
1455±20
780$0.39 / $2.34262.1K
29
683
Bytedance
dola-seed-2.0-pro
Bytedance · Proprietary
1450±19
953N/AN/A
30
1068
gemini-2.5-pro
Google · Proprietary
1450±8
5,625$1.25 / $101M
31
970
Anthropic
claude-opus-4-1-20250805-thinking-16k
Anthropic · Proprietary
1450±12
2,440$15 / $75200K
32
782
gpt-5.2
OpenAI · Proprietary
1449±17
1,243$1.75 / $14400K
33
4102
gpt-5.4-nano-high
OpenAI · Proprietary
1449±33
301$2.50 / $151.1M
34
1070
o3-2025-04-16
OpenAI · Proprietary
1448±10
3,491$2 / $8200K
35
5101
deepseek-v3.2-exp-thinking
DeepSeek · MIT
1446±29
412$0.27 / $0.41163.8K
36
1082
kimi-k2-thinking-turbo
Moonshot · Modified MIT
1446±13
2,061$1.15 / $8262.1K
37
1083
grok-4.1-thinking
xAI · Proprietary
1445±13
2,092N/AN/A
38
5107
kimi-k2.5-instant
Moonshot · Modified MIT
1445±31
334$0.38 / $1.72262.1K
39
1282
Anthropic
claude-sonnet-4-5-20250929
Anthropic · Proprietary
1445±12
2,751$3 / $15200K
40
5107
grok-4-fast-chat
xAI · Proprietary
1444±32
320$3 / $15256K
41
1188
deepseek-v3.2-thinking
DeepSeek · MIT
1442±15
1,438$0.26 / $0.38163.8K
42
1386
gpt-5-high
OpenAI · Proprietary
1442±14
1,781$1.25 / $10400K
43
8101
deepseek-v3.1-thinking
DeepSeek · MIT
1442±24
568$1.23 / $4.94N/A
44
1289
qwen3-max-preview
Alibaba · Proprietary
1441±16
1,338$0.78 / $3.90262.1K
45
1488
deepseek-v3.2
DeepSeek · MIT
1441±14
1,892$0.26 / $0.38163.8K
46
1483
Anthropic
claude-opus-4-1-20250805
Anthropic · Proprietary
1440±10
3,861$15 / $75200K
47
1489
glm-4.6
Z.ai · MIT
1440±14
1,742$0.39 / $1.90204.8K
48
6113
longcat-flash-chat-2602-exp
Meituan · Proprietary
1438±32
323N/AN/A
49
14101
ernie-5.0-0110
Baidu · Proprietary
1436±18
996N/AN/A
50
8112
qwen3-vl-235b-a22b-thinking
Alibaba · Apache 2.0
1435±29
389$0.26 / $2.60131.1K
51
1595
grok-4-0709
xAI · Proprietary
1435±13
2,196$3 / $15256K
52
1890
qwen3-235b-a22b-instruct-2507
Alibaba · Apache 2.0
1434±10
4,086$0.26 / $1.06N/A
53
1595
gpt-5.1
OpenAI · Proprietary
1434±13
2,088$1.25 / $10400K
54
14107
gemini-3.1-flash-lite-preview
Google · Proprietary
1434±20
803$0.25 / $1.501M
55
14107
minimax-m2.5
MiniMax · Modified MIT
1431±20
855$0.12 / $0.99196.6K
56
14114
qwen3.5-122b-a10b
Alibaba · Apache 2.0
1428±23
596$0.26 / $2.08262.1K
57
14115
qwen3.5-flash
Alibaba · Proprietary
1426±23
622N/AN/A
58
15116
glm-4.7
Z.ai · MIT
1425±23
565$0.39 / $1.75202.8K
59
25107
grok-4.1
xAI · Proprietary
1425±12
2,486N/AN/A
60
14120
qwen3-235b-a22b-thinking-2507
Alibaba · Apache 2.0
1425±25
495$0.15 / $1.50131.1K
61
11125
qwen3-32b
Alibaba · Apache 2.0
1425±32
282$0.08 / $0.2441K
62
25108
Anthropic
claude-opus-4-20250514-thinking-16k
Anthropic · Proprietary
1423±13
2,076$15 / $75200K
63
16117
kimi-k2-0905-preview
Moonshot · Modified MIT
1423±23
648$0.60 / $2.50262.1K
64
25109
grok-4-1-fast-reasoning
xAI · Proprietary
1423±14
1,980$0.20 / $0.502M
65
12126
ernie-5.0-preview-1022
Baidu · Proprietary
1422±34
268N/AN/A
66
18118
gpt-5.3-chat-latest
OpenAI · Proprietary
1422±22
724$1.75 / $14128K
67
16122
longcat-flash-chat
Meituan · MIT
1422±24
548$0.20 / $0.80131.1K
68
25112
gemini-2.5-flash-preview-09-2025
Google · Proprietary
1422±14
1,673$0.30 / $2.501M
69
25115
glm-4.5
Z.ai · MIT
1421±17
1,279$0.60 / $2.20131.1K
70
18122
minimax-m2.1-preview
MiniMax · MIT
1421±22
681$0.29 / $0.95196.6K
71
38107
gemini-2.5-flash
Google · Proprietary
1420±8
5,877$0.30 / $2.501M
72
25116
qwen3-next-80b-a3b-instruct
Alibaba · Apache 2.0
1419±18
1,078$0.09 / $1.10262.1K
73
38114
Anthropic
claude-haiku-4-5-20251001
Anthropic · Proprietary
1416±12
2,775$1 / $5200K
74
26122
Stepfun
step-3.5-flash
StepFun · Apache 2.0
1416±19
864$0.10 / $0.30262.1K
75
27122
deepseek-r1-0528
DeepSeek · MIT
1416±19
953$0.45 / $2.15163.8K
76
26123
deepseek-v3.1
DeepSeek · MIT
1416±20
846$1.23 / $4.94N/A
77
34124
grok-4-fast-reasoning
xAI · Proprietary
1413±19
967$0.20 / $0.502M
78
38122
gpt-4.5-preview-2025-02-27
OpenAI · Proprietary
1413±16
1,283$75 / $150128K
79
14144
amazon-nova-experimental-chat-12-10
Amazon · Proprietary
1413±40
197N/AN/A
80
22126
qwen3-max-2025-09-23
Alibaba · Proprietary
1413±26
491$0.78 / $3.90262.1K
81
21126
ernie-5.0-preview-1203
Baidu · Proprietary
1413±26
503N/AN/A
82
44116
o1-2024-12-17
OpenAI · Proprietary
1413±11
2,644$15 / $60200K
83
18129
minimax-m2.7
MiniMax · Proprietary
1413±30
360$0.30 / $1.20204.8K
84
39122
deepseek-r1
DeepSeek · MIT
1412±15
1,504$0.70 / $2.5064K
85
41122
o3-mini-high
OpenAI · Proprietary
1412±14
1,711$1.10 / $4.40200K
86
27126
deepseek-v3.2-exp
DeepSeek · MIT
1412±23
645$0.27 / $0.41163.8K
87
26126
qwen3-vl-235b-a22b-instruct
Alibaba · Apache 2.0
1412±24
605$0.20 / $0.88262.1K
88
30126
qwen3.5-35b-a3b
Alibaba · Apache 2.0
1411±23
605$0.16 / $1.30262.1K
89
44123
gpt-5-chat
OpenAI · Proprietary
1410±15
1,587$1.25 / $10128K
90
46116
chatgpt-4o-latest-20250326
OpenAI · Proprietary
1410±9
4,851$5 / $15128K
91
44123
Anthropic
claude-sonnet-4-20250514-thinking-32k
Anthropic · Proprietary
1409±13
1,943$3 / $151M
92
43125
gpt-5-mini-high
OpenAI · Proprietary
1409±16
1,300$0.25 / $2400K
93
44125
mistral-large-3
Mistral · Apache 2.0
1409±15
1,682$0.50 / $1.50N/A
94
46122
o4-mini-2025-04-16
OpenAI · Proprietary
1408±11
2,816$1.10 / $4.40200K
95
46122
Anthropic
claude-opus-4-20250514
Anthropic · Proprietary
1408±11
2,671$15 / $75200K
96
15149
nvidia-llama-3.3-nemotron-super-49b-v1.5
Nvidia · Nvidia Open
1406±40
184$0.10 / $0.40131.1K
97
50123
mistral-medium-2508
Mistral · Proprietary
1405±10
3,877$2.70 / $8.1032K
98
50126
qwen3-235b-a22b-no-thinking
Alibaba · Apache 2.0
1403±12
2,322$0.46 / $1.82131.1K
99
46127
qwen3-30b-a3b-instruct-2507
Alibaba · Apache 2.0
1402±16
1,234$0.09 / $0.30262.1K
100
50126
qwen3-235b-a22b
Alibaba · Apache 2.0
1401±15
1,515$0.46 / $1.82131.1K
101
39145
nvidia-nemotron-3-super-120b-a12b
Nvidia · NVIDIA Open Model
1400±28
411N/AN/A
102
50136
amazon-nova-experimental-chat-11-10
Amazon · Proprietary
1397±18
1,083N/AN/A
103
49142
mai-1-preview
Microsoft AI · Proprietary
1396±20
841N/AN/A
104
61126
o1-preview
OpenAI · Proprietary
1396±10
3,876$15 / $60N/A
105
63133
grok-3-preview-02-24
xAI · Proprietary
1393±12
2,461$3 / $15131.1K
106
60142
glm-4.5-air
Z.ai · MIT
1392±15
1,483$0.13 / $0.85131.1K
107
46149
mimo-v2-flash (thinking)
Xiaomi · MIT
1392±27
431$0.09 / $0.29262.1K
108
71130
o3-mini
OpenAI · Proprietary
1391±9
4,397$1.10 / $4.40200K
109
58143
mimo-v2-flash (non-thinking)
Xiaomi · MIT
1391±16
1,329$0.09 / $0.29262.1K
110
69142
Anthropic
claude-sonnet-4-20250514
Anthropic · Proprietary
1389±12
2,365$3 / $151M
111
56149
qwen3-next-80b-a3b-thinking
Alibaba · Apache 2.0
1389±22
685$0.10 / $0.78131.1K
112
72140
Anthropic
claude-3-7-sonnet-20250219-thinking-32k
Anthropic · Proprietary
1389±11
2,572$3 / $15200K
113
50149
glm-4.7-flash
Z.ai · MIT
1389±26
483$0.06 / $0.40202.8K
114
57149
amazon-nova-experimental-chat-10-20
Amazon · Proprietary
1387±23
609N/AN/A
115
44156
Tencent
hunyuan-t1-20250711
Tencent · Proprietary
1386±38
225N/AN/A
116
71147
kimi-k2-0711-preview
Moonshot · Modified MIT
1385±15
1,588$0.60 / $2.50131.1K
117
72147
gpt-oss-120b
OpenAI · Apache 2.0
1385±15
1,574$0.04 / $0.19131.1K
118
46157
intellect-3
Prime Intellect · MIT
1383±36
239$0.20 / $1.10131.1K
119
81149
qwen3-coder-480b-a35b-instruct
Alibaba · Apache 2.0
1381±15
1,474$0.40 / $1.60262.1K
120
86149
minimax-m1
MiniMax · Apache 2.0
1381±14
1,809$0.40 / $2.201M
121
70153
trinity-large-preview
Arcee AI · Apache 2.0
1377±23
644N/AN/A
122
85151
grok-3-mini-high
xAI · Proprietary
1377±18
1,006$0.30 / $0.50131.1K
123
58160
Stepfun
step-3
StepFun · Apache 2.0
1377±33
309$0.57 / $1.4265.5K
124
99149
o1-mini
OpenAI · Proprietary
1375±8
6,318$1.10 / $4.40N/A
125
58162
minimax-m2
MiniMax · Apache 2.0
1374±34
289$0.26 / $1196.6K
126
101150
gpt-4.1-2025-04-14
OpenAI · Proprietary
1372±10
3,110$2 / $81M
127
100151
gemini-2.5-flash-lite-preview-09-2025-no-thinking
Google · Proprietary
1370±13
2,157$0.10 / $0.401M
128
101152
gemini-2.5-flash-lite-preview-06-17-thinking
Google · Proprietary
1369±13
2,027$0.10 / $0.401M
129
103151
qwen2.5-max
Alibaba · Proprietary
1368±10
2,953N/AN/A
130
103151
deepseek-v3-0324
DeepSeek · MIT
1368±11
2,960$3 / $4.5032.8K
131
101153
qwen3-30b-a3b
Alibaba · Apache 2.0
1367±14
1,594$0.08 / $0.2841K
132
65170
llama-3.3-nemotron-49b-super-v1
Nvidia · Nvidia
1365±37
207N/AN/A
133
103155
qwq-32b
Alibaba · Apache 2.0
1364±14
1,585$0.15 / $0.58131.1K
134
107153
gpt-4.1-mini-2025-04-14
OpenAI · Proprietary
1364±12
2,506$0.40 / $1.601M
135
110153
gemini-2.0-flash-001
Google · Proprietary
1363±9
3,781$0.10 / $0.401M
136
104156
grok-3-mini-beta
xAI · Proprietary
1362±15
1,477$0.30 / $0.50131.1K
137
99162
nvidia-nemotron-3-nano-30b-a3b-bf16
Nvidia · NVIDIA Open Model
1362±22
689$0.06 / $0.24262.1K
138
89166
ring-flash-2.0
Ant Group · MIT
1362±30
368N/AN/A
139
110154
Anthropic
claude-3-7-sonnet-20250219
Anthropic · Proprietary
1361±10
3,214$3 / $15200K
140
103162
Tencent
hunyuan-turbos-20250416
Tencent · Proprietary
1358±20
802N/AN/A
141
98170
ling-flash-2.0
Ant Group · MIT
1357±29
384N/AN/A
142
108162
mistral-small-2506
Mistral · Apache 2.0
1356±18
1,005$0.10 / $0.3032K
143
112160
mistral-medium-2505
Mistral · Proprietary
1356±12
2,216$0.40 / $2131.1K
144
120156
Anthropic
claude-3-5-sonnet-20241022
Anthropic · Proprietary
1355±7
8,646$3 / $15200K
145
102174
olmo-3.1-32b-instruct
Ai2 · Apache 2.0
1353±28
433$0.20 / $0.6065.5K
146
121160
gemini-1.5-pro-002
Google · Proprietary
1352±8
6,506$3.50 / $10.502.1M
147
102176
gpt-5-nano-high
OpenAI · Proprietary
1351±28
442$0.05 / $0.40400K
148
102177
gemma-3-12b-it
Google · Gemma
1349±30
333$0.04 / $0.13131.1K
149
109174
nova-2-lite
Amazon · Proprietary
1349±24
599$0.30 / $2.501M
150
104198
glm-4.5v
Z.ai · MIT
1340±37
235$0.60 / $1.8065.5K
151
132169
gemma-3-27b-it
Google · Gemma
1340±10
3,230$0.08 / $0.16131.1K
152
136169
Anthropic
claude-3-5-sonnet-20240620
Anthropic · Proprietary
1337±8
10,038$3 / $15200K
153
135172
gemini-2.0-flash-lite-preview-02-05
Google · Proprietary
1336±11
2,399$0.07 / $0.301M
154
125184
qwen-plus-0125
Alibaba · Proprietary
1335±21
627$0.40 / $1.20131.1K
155
126188
gpt-oss-20b
OpenAI · Apache 2.0
1331±24
590$0.03 / $0.14131.1K
156
112207
olmo-3-32b-think
Ai2 · Apache 2.0
1331±39
206$0.15 / $0.5065.5K
157
130198
Stepfun
step-1o-turbo-202506
StepFun · Proprietary
1327±24
575N/AN/A
158
143183
Cohere
command-a-03-2025
Cohere · CC-BY-NC-4.0
1324±10
3,674$2.50 / $10256K
159
131201
Tencent
hunyuan-large-2025-02-10
Tencent · Proprietary
1324±26
431N/AN/A
160
136198
Stepfun
step-2-16k-exp-202412
StepFun · Proprietary
1323±22
543N/AN/A
161
144185
athene-v2-chat
NexusFlow · NexusFlow
1321±10
2,942N/AN/A
162
144187
Meta
llama-4-maverick-17b-128e-instruct
Meta · Llama 4
1320±11
2,612$0.63 / $1.80131.1K
163
149186
Meta
llama-3.1-405b-instruct-fp8
Meta · Llama 3.1 Community
1318±8
7,242$4 / $432.8K
164
146188
deepseek-v3
DeepSeek · DeepSeek
1317±12
2,326$1.14 / $4.56N/A
165
144198
qwen2.5-plus-1127
Alibaba · Proprietary
1317±15
1,265N/AN/A
166
149188
Meta
llama-3.1-405b-instruct-bf16
Meta · Llama 3.1 Community
1317±8
4,366$4 / $432.8K
167
148188
01.AI
yi-lightning
01 AI · Proprietary
1317±10
3,206N/AN/A
168
151192
gemini-advanced-0514
Google · Proprietary
1315±10
5,787N/AN/A
169
148200
Meta
llama-4-scout-17b-16e-instruct
Meta · Llama
1313±14
1,832$0.40 / $0.708.2K
170
139209
Tencent
hunyuan-large-vision
Tencent · Proprietary
1312±28
366N/AN/A
171
136217
Tencent
hunyuan-turbo-0110
Tencent · Proprietary
1311±34
216N/AN/A
172
152198
gpt-4o-2024-08-06
OpenAI · Proprietary
1311±8
5,805$2.50 / $10128K
173
153198
qwen2.5-72b-instruct
Alibaba · Qwen
1309±9
4,565$1.20 / $1.20N/A
174
153198
gpt-4o-2024-05-13
OpenAI · Proprietary
1309±7
13,306$5 / $15128K
175
153198
gemini-1.5-pro-001
Google · Proprietary
1309±8
9,328$3.50 / $10.502.1M
176
154198
Anthropic
claude-3-opus-20240229
Anthropic · Proprietary
1308±6
22,970$15 / $75200K
177
153199
gpt-4-1106-preview
OpenAI · Proprietary
1308±8
11,549$10 / $30128K
178
143213
Tencent
hunyuan-standard-2025-02-10
Tencent · Proprietary
1308±26
441N/AN/A
179
139219
ibm-granite-h-small
IBM · Apache 2.0
1306±35
294N/AN/A
180
143218
olmo-3.1-32b-think
Ai2 · Apache 2.0
1303±30
363$0.15 / $0.5065.5K
181
151213
glm-4-plus-0111
Zhipu · Proprietary
1303±21
638N/AN/A
182
143219
Tencent
hunyuan-turbos-20250226
Tencent · Proprietary
1302±32
224N/AN/A
183
156207
gemini-1.5-flash-002
Google · Proprietary
1301±9
4,114$0.07 / $0.301M
184
158204
Meta
llama-3.3-70b-instruct
Meta · Llama-3.3
1301±8
5,247$0.10 / $0.32131.1K
185
155209
qwen-max-0919
Alibaba · Qwen
1300±13
1,804$1.60 / $6.4032.8K
186
153214
llama-3.1-nemotron-70b-instruct
Nvidia · Llama 3.1
1299±18
874$1.20 / $1.20131.1K
187
157209
glm-4-plus
Zhipu AI · Proprietary
1299±10
2,991$0.44 / $1.76204.8K
188
162207
grok-2-2024-08-13
xAI · Proprietary
1298±7
7,604$2 / $10131.1K
189
162207
gpt-4-turbo-2024-04-09
OpenAI · Proprietary
1298±8
11,796$10 / $30128K
190
162207
gpt-4-0125-preview
OpenAI · Proprietary
1297±8
10,830$10 / $30128K
191
163209
mistral-large-2407
Mistral · Mistral Research
1296±8
5,745$2 / $6131.1K
192
163209
Anthropic
claude-3-5-haiku-20241022
Anthropic · Proprietary
1296±8
5,806$0.80 / $4200K
193
162209
deepseek-v2.5
DeepSeek · DeepSeek
1295±10
3,039N/AN/A
194
153223
magistral-medium-2506
Mistral · Proprietary
1292±26
585$2 / $540K
195
163216
mistral-small-3.1-24b-instruct-2503
Mistral · Apache 2.0
1290±13
1,968$0.10 / $0.3032K
196
163220
deepseek-v2.5-1210
DeepSeek · DeepSeek
1287±18
893N/AN/A
197
175217
gpt-4-0314
OpenAI · Proprietary
1286±10
6,112$30 / $608.2K
198
176215
gpt-4o-mini-2024-07-18
OpenAI · Proprietary
1285±7
7,971$0.15 / $0.60128K
199
172220
gemma-3n-e4b-it
Google · Gemma
1284±16
1,421$0.02 / $0.0432.8K
200
176217
grok-2-mini-2024-08-13
xAI · Proprietary
1284±8
6,253$2 / $10131.1K
201
175218
amazon-nova-pro-v1.0
Amazon · Proprietary
1284±10
2,650$0.80 / $3.20300K
202
176218
mistral-large-2411
Mistral · MRL
1282±10
3,037$2 / $6131.1K
203
163228
gpt-4.1-nano-2025-04-14
OpenAI · Proprietary
1280±24
534$0.10 / $0.401M
204
181223
phi-4
Microsoft · MIT
1277±11
2,350$0.07 / $0.1416.4K
205
187221
Meta
llama-3.1-70b-instruct
Meta · Llama 3.1 Community
1275±8
6,524$0.40 / $0.40131.1K
206
174234
llama-3.1-nemotron-51b-instruct
Nvidia · Llama 3.1
1274±25
422N/AN/A
207
163235
gemma-3-4b-it
Google · Gemma
1274±30
365$0.04 / $0.08131.1K
208
187224
qwen2-72b-instruct
Alibaba · Qianwen LICENSE
1274±10
4,235$0.90 / $0.9032.8K
209
173235
llama-3.1-tulu-3-70b
Ai2 · Llama 3.1
1272±28
349N/AN/A
210
191224
gemini-1.5-flash-001
Google · Proprietary
1270±8
7,315$0.07 / $0.301M
211
187229
mistral-small-24b-instruct-2501
Mistral · Apache 2.0
1269±14
1,447$0.05 / $0.0832.8K
212
181234
qwen2.5-coder-32b-instruct
Alibaba · Apache 2.0
1268±21
619$0.87 / $0.8732K
213
189230
deepseek-coder-v2
DeepSeek · DeepSeek License
1268±14
1,669$0.14 / $0.28128K
214
186230
reka-core-20240904
Reka AI · Proprietary
1268±15
1,039N/AN/A
215
192228
athene-70b-0725
NexusFlow · CC-BY-NC-4.0
1266±11
2,559N/AN/A
216
195227
gpt-4-0613
OpenAI · Proprietary
1266±9
9,862$30 / $608.2K
217
175243
Tencent
hunyuan-standard-256k
Tencent · Proprietary
1266±31
292N/AN/A
218
190234
glm-4-0520
Zhipu AI · Proprietary
1263±16
1,067N/AN/A
219
203230
gemma-2-27b-it
Google · Gemma license
1259±7
8,869$0.65 / $0.658.2K
220
203230
Anthropic
claude-3-sonnet-20240229
Anthropic · Proprietary
1259±8
12,413$3 / $15200K
221
205230
Meta
llama-3-70b-instruct
Meta · Llama 3 Community
1258±7
18,728$0.51 / $0.748.2K
222
202235
amazon-nova-lite-v1.0
Amazon · Proprietary
1257±11
2,173$0.06 / $0.24300K
223
200235
nemotron-4-340b-instruct
Nvidia · NVIDIA Open Model
1257±13
2,133N/AN/A
224
198238
jamba-1.5-large
AI21 Labs · Jamba Open
1255±17
962$2 / $8256K
225
207236
gemini-1.5-flash-8b-001
Google · Proprietary
1251±9
4,171$0.07 / $0.301M
226
211243
Cohere
c4ai-aya-expanse-32b
Cohere · CC-BY-NC-4.0
1244±10
3,239N/AN/A
227
207248
Cohere
command-r-plus-08-2024
Cohere · CC-BY-NC-4.0
1244±15
1,243$2.50 / $10128K
228
207251
reka-flash-20240904
Reka AI · Proprietary
1243±15
1,109N/AN/A
229
216247
mistral-large-2402
Mistral · Proprietary
1239±9
7,028$4 / $1232K
230
223251
Anthropic
claude-3-haiku-20240307
Anthropic · Proprietary
1235±8
13,491$0.25 / $1.25200K
231
219253
amazon-nova-micro-v1.0
Amazon · Proprietary
1235±12
2,016$0.04 / $0.14128K
232
216255
gemma-2-9b-it-simpo
Princeton · MIT
1233±16
1,139$0.03 / $0.098.2K
233
224252
gemma-2-9b-it
Google · Gemma license
1233±8
6,297$0.03 / $0.098.2K
234
224255
qwen1.5-110b-chat
Alibaba · Qianwen LICENSE
1230±12
2,860N/AN/A
235
225254
mixtral-8x22b-instruct-v0.1
Mistral · Apache 2.0
1228±9
6,001$0.90 / $0.9065.5K
236
208267
granite-3.1-2b-instruct
IBM · Apache 2.0
1228±29
341N/AN/A
237
225257
mistral-medium
Mistral · Proprietary
1225±11
3,806$2.70 / $8.1032K
238
210269
granite-3.1-8b-instruct
IBM · Apache 2.0
1224±31
320N/AN/A
239
227257
phi-3-medium-4k-instruct
Microsoft · MIT
1223±11
2,729$0.17 / $0.68N/A
240
216268
qwq-32b-preview
Alibaba · Apache 2.0
1223±26
422$0.15 / $0.58131.1K
241
225260
Cohere
command-r-08-2024
Cohere · CC-BY-NC-4.0
1221±14
1,361$0.15 / $0.60128K
242
227257
01.AI
yi-1.5-34b-chat
01 AI · Apache-2.0
1221±11
2,568N/AN/A
243
227257
qwen1.5-72b-chat
Alibaba · Qianwen LICENSE
1220±10
4,522N/AN/A
244
216269
olmo-2-0325-32b-instruct
Ai2 · Apache-2.0
1219±30
336$0.05 / $0.20128K
245
231258
Cohere
command-r-plus
Cohere · CC-BY-NC-4.0
1218±9
8,796$2.50 / $10128K
246
225269
ministral-8b-2410
Mistral · MRL
1215±22
543$0.10 / $0.10131.1K
247
229266
reka-flash-21b-20240226-online
Reka AI · Proprietary
1215±14
1,867N/AN/A
248
229267
Cohere
c4ai-aya-expanse-8b
Cohere · CC-BY-NC-4.0
1212±16
1,146N/AN/A
249
229268
internlm2_5-20b-chat
InternLM · Other
1212±16
1,086$0 / $032.8K
250
232266
qwen1.5-32b-chat
Alibaba · Qianwen LICENSE
1212±12
2,405N/AN/A
251
227269
granite-3.0-8b-instruct
IBM · Apache 2.0
1211±21
675N/AN/A
252
228270
gemini-pro
Google · Proprietary
1209±21
844$0.35 / $1.0532.8K
253
225272
llama-3.1-tulu-3-8b
Ai2 · Llama 3.1
1208±29
304N/AN/A
254
234269
reka-flash-21b-20240226
Reka AI · Proprietary
1207±12
2,967N/AN/A
255
236270
phi-3-small-8k-instruct
Microsoft · MIT
1201±13
1,849$0.15 / $0.60N/A
256
236272
gpt-3.5-turbo-1106
OpenAI · Proprietary
1199±16
1,746$1 / $216.4K
257
233274
zephyr-orpo-141b-A35b-v0.1
HuggingFace · Apache 2.0
1199±24
526N/AN/A
258
242269
Meta
llama-3-8b-instruct
Meta · Llama 3 Community
1199±8
12,836$0.03 / $0.048.2K
259
240272
phi-3-mini-4k-instruct-june-2024
Microsoft · MIT
1195±14
1,357$0.13 / $0.524.1K
260
242271
Meta
llama-3.1-8b-instruct
Meta · Llama 3.1 Community
1194±8
5,985$0.02 / $0.0516.4K
261
242271
gpt-3.5-turbo-0125
OpenAI · Proprietary
1192±9
7,493$0.50 / $1.5016.4K
262
242271
mixtral-8x7b-instruct-v0.1
Mistral · Apache 2.0
1192±9
8,472$0.63 / $0.6332K
263
242273
gemini-pro-dev-api
Google · Proprietary
1192±15
1,975$0.35 / $1.0532.8K
264
241275
jamba-1.5-mini
AI21 Labs · Jamba Open
1192±17
932$0.20 / $0.40256K
265
243274
dbrx-instruct-preview
Databricks · DBRX LICENSE
1188±12
3,599$0.60 / $0.6032.8K
266
242281
granite-3.0-2b-instruct
IBM · Apache 2.0
1186±21
751N/AN/A
267
248274
Cohere
command-r
Cohere · CC-BY-NC-4.0
1185±10
5,906$0.15 / $0.60128K
268
246278
qwen1.5-14b-chat
Alibaba · Qianwen LICENSE
1182±14
1,972$0.30 / $0.30N/A
269
256277
gemma-2-2b-it
Google · Gemma license
1178±8
5,632N/AN/A
270
241293
smollm2-1.7b-instruct
HuggingFace · Apache 2.0
1174±34
240N/AN/A
271
254284
Meta
llama-3.2-3b-instruct
Meta · Llama 3.2
1172±17
980$0.05 / $0.3480K
272
259284
starling-lm-7b-beta
Nexusflow · Apache-2.0
1168±15
1,816N/AN/A
273
267290
01.AI
yi-34b-chat
01 AI · Yi License
1158±14
1,719$0.90 / $0.904.1K
274
268290
snowflake-arctic-instruct
Snowflake · Apache 2.0
1158±12
4,220N/AN/A
275
269290
gemma-1.1-7b-it
Google · Gemma license
1156±12
2,659$0.03 / $0.098.2K
276
262296
openhermes-2.5-mistral-7b
NousResearch · Apache-2.0
1156±22
568$0.17 / $0.17N/A
277
266296
wizardlm-70b
Microsoft · Llama 2 Community
1154±21
764N/AN/A
278
263298
qwen1.5-7b-chat
Alibaba · Qianwen LICENSE
1154±23
578$0.20 / $0.20N/A
279
269293
phi-3-mini-4k-instruct
Microsoft · MIT
1153±13
2,198$0.13 / $0.52N/A
280
269294
openchat-3.5-0106
OpenChat · Apache-2.0
1152±15
1,467N/AN/A
281
267299
deepseek-llm-67b-chat
DeepSeek · DeepSeek License
1147±26
484N/AN/A
282
270299
tulu-2-dpo-70b
AllenAI/UW · AI2 ImpACT Low-risk
1141±20
751N/AN/A
283
270299
Meta
llama-3.2-1b-instruct
Meta · Llama 3.2
1140±18
976$0.03 / $0.2060K
284
272299
phi-3-mini-128k-instruct
Microsoft · MIT
1139±14
2,569$0.13 / $0.52N/A
285
272298
Meta
llama-2-70b-chat
Meta · Llama 2 Community
1139±11
4,052$0.70 / $2.804.1K
286
270300
qwen-14b-chat
Alibaba · Qianwen LICENSE
1137±26
467N/AN/A
287
272299
mistral-7b-instruct-v0.2
Mistral · Apache-2.0
1133±13
2,193$0.20 / $0.2032.8K
288
272299
starling-lm-7b-alpha
UC Berkeley · CC-BY-NC-4.0
1132±17
1,103N/AN/A
289
272301
openchat-3.5
OpenChat · Apache-2.0
1129±20
826$0.20 / $0.20N/A
290
275299
vicuna-33b
LMSYS · Non-commercial
1127±13
2,352$0 / $02K
291
277304
palm-2
Google · Proprietary
1119±21
801$0.50 / $0.5025.8K
292
280302
Meta
llama-2-13b-chat
Meta · Llama 2 Community
1118±14
1,977$0.25 / $0.254.1K
293
278304
gemma-7b-it
Google · Gemma license
1118±18
982$0.05 / $0.088.2K
294
278306
Meta
codellama-34b-instruct
Meta · Llama 2 Community
1113±21
667$0.35 / $1.4016.4K
295
275309
llama2-70b-steerlm-chat
Nvidia · Llama 2 Community
1113±30
353N/AN/A
296
272310
mpt-30b-chat
MosaicML · CC-BY-NC-SA-4.0
1111±37
218N/AN/A
297
282306
gemma-1.1-2b-it
Google · Gemma license
1109±17
1,224N/AN/A
298
275310
dolphin-2.2.1-mistral-7b
Cognitive Computations · Apache-2.0
1108±34
201$0.50 / $0.5016.4K
299
280308
solar-10.7b-instruct-v1.0
Upstage AI · CC-BY-NC-4.0
1108±24
529$0.30 / $0.30N/A
300
290310
zephyr-7b-beta
HuggingFace · MIT
1093±18
1,113$0.15 / $0.1516.4K
301
292310
Meta
llama-2-7b-chat
Meta · Llama 2 Community
1088±15
1,401$0.15 / $0.154.1K
302
289311
nous-hermes-2-mixtral-8x7b-dpo
NousResearch · Apache-2.0
1087±26
464$0.90 / $0.90N/A
303
294310
vicuna-13b
LMSYS · Llama 2 Community
1081±15
1,884$0.30 / $0.30N/A
304
292311
stripedhyena-nous-7b
Together AI · Apache 2.0
1080±23
530$0.20 / $0.20N/A
305
291312
guanaco-33b
UW · Non-commercial
1074±35
236N/AN/A
306
294312
gemma-2b-it
Google · Gemma license
1070±24
525$0.10 / $0.10N/A
307
296312
mistral-7b-instruct
Mistral · Apache 2.0
1070±21
814$0.07 / $0.284.1K
308
296312
wizardlm-13b
Microsoft · Llama 2 Community
1068±23
567$0.30 / $0.30N/A
309
297312
qwen1.5-4b-chat
Alibaba · Qianwen LICENSE
1064±20
820$0.10 / $0.10N/A
310
298312
olmo-7b-instruct
Ai2 · Apache-2.0
1058±21
726$0.20 / $0.20N/A
311
303312
vicuna-7b
LMSYS · Llama 2 Community
1042±24
590$0.20 / $0.20N/A
312
305316
chatglm3-6b
Tsinghua · Apache-2.0
1026±27
466N/AN/A
313
312319
RWKV-4-Raven-14B
RWKV · Apache 2.0
989±26
488N/AN/A
314
312319
koala-13b
UC Berkeley · Non-commercial
984±23
692N/AN/A
315
312320
mpt-7b-chat
MosaicML · CC-BY-NC-SA-4.0
981±28
397N/AN/A
316
312320
alpaca-13b
Stanford · Non-commercial
974±25
565N/AN/A
317
313321
chatglm-6b
Tsinghua · Non-commercial
970±28
466N/AN/A
318
313321
oasst-pythia-12b
OpenAssistant · Apache 2.0
968±25
629N/AN/A
319
315322
dolly-v2-12b
Databricks · MIT
930±31
343N/AN/A
320
313322
Meta
llama-13b
Meta · Non-commercial
926±37
228$0.23 / $0.23N/A
321
317322
fastchat-t5-3b
LMSYS · Apache 2.0
918±28
400N/AN/A
322
319322
Stability
stablelm-tuned-alpha-7b
Stability AI · CC-BY-NC-SA-4.0
893±31
294N/AN/A

Default Leaderboard Plots

Confidence Intervals on Model Strength (via Bootstrapping)

Battle Count for Each Combination of Models (without Ties)

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

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