Text Arena🇨🇳Chinese

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
397,955 votes
306 models
Rank Spread
1
116
Anthropic
claude-opus-4-6
Anthropic · Proprietary
1557±24
632$5 / $251M
2
123
grok-4.20-beta1
xAI · Proprietary
1554±36
269N/AN/A
3
118
Anthropic
claude-opus-4-6-thinking
Anthropic · Proprietary
1552±25
601$5 / $251M
4
121
gemini-3.1-pro-preview
Google · Proprietary
1543±21
824$2 / $121M
5
136
qwen3.5-max-preview
Alibaba · Proprietary
1537±35
296N/AN/A
6
132
glm-5
Z.ai · MIT
1533±26
550$1 / $3.20202.8K
7
125
gemini-3-pro
Google · Proprietary
1529±14
2,157$2 / $121M
8
136
kimi-k2.5-thinking
Moonshot · Modified MIT
1526±23
684$0.60 / $3N/A
9
131
gemini-3-flash
Google · Proprietary
1523±15
1,555$0.50 / $31M
10
142
gpt-5.2-chat-latest-20260210
OpenAI · Proprietary
1522±25
568$1.75 / $14128K
11
145
gpt-5.4-high
OpenAI · Proprietary
1520±30
420$2.50 / $151.1M
12
147
grok-4.20-beta-0309-reasoning
xAI · Proprietary
1519±30
353$2 / $62M
13
147
gpt-5.4
OpenAI · Proprietary
1518±28
448$2.50 / $151.1M
14
160
gpt-5.4-mini-high
OpenAI · Proprietary
1514±39
229$0.75 / $4.50400K
15
442
grok-4.1
xAI · Proprietary
1508±13
2,619N/AN/A
16
154
Anthropic
claude-sonnet-4-6
Anthropic · Proprietary
1506±29
443$3 / $151M
17
164
grok-4.20-multi-agent-beta-0309
xAI · Proprietary
1504±31
367$2 / $62M
18
545
grok-4.1-thinking
xAI · Proprietary
1504±13
2,302N/AN/A
19
259
qwen3.5-397b-a17b
Alibaba · Apache 2.0
1504±28
477$0.39 / $2.34262.1K
20
352
ernie-5.0-0110
Baidu · Proprietary
1502±20
912N/AN/A
21
261
gpt-5.3-chat-latest
OpenAI · Proprietary
1501±26
544$1.75 / $14128K
22
552
gemini-3-flash (thinking-minimal)
Google · Proprietary
1500±17
1,366$0.50 / $31M
23
649
gpt-5.1-high
OpenAI · Proprietary
1499±14
2,056$1.25 / $10400K
24
747
gemini-2.5-pro
Google · Proprietary
1499±9
5,454$1.25 / $101M
25
652
Anthropic
claude-opus-4-5-20251101-thinking-32k
Anthropic · Proprietary
1498±14
1,860$5 / $25200K
26
853
Anthropic
claude-opus-4-5-20251101
Anthropic · Proprietary
1492±14
2,117$5 / $25200K
27
668
glm-4.7
Z.ai · MIT
1491±22
709$0.39 / $1.75202.8K
28
863
qwen3-max-preview
Alibaba · Proprietary
1490±15
1,553$0.78 / $3.90262.1K
29
384
ernie-5.0-preview-1022
Baidu · Proprietary
1489±34
287N/AN/A
30
387
mimo-v2-pro
Xiaomi · Proprietary
1488±35
270$1 / $31M
31
487
gemma-4-31b
Google · Apache 2.0
1487±33
294$0.14 / $0.40262.1K
32
688
grok-4-fast-chat
xAI · Proprietary
1483±32
362$3 / $15256K
33
1068
glm-4.6
Z.ai · MIT
1483±15
1,706$0.39 / $1.90204.8K
34
693
gemma-4-26b-a4b
Google · Apache 2.0
1481±34
292N/AN/A
35
885
ernie-5.0-preview-1203
Baidu · Proprietary
1480±25
552N/AN/A
36
888
qwen3.5-27b
Alibaba · Apache 2.0
1479±28
454$0.20 / $1.56262.1K
37
1472
Anthropic
claude-sonnet-4-5-20250929-thinking-32k
Anthropic · Proprietary
1478±12
2,576$3 / $15200K
38
1277
gpt-5.1
OpenAI · Proprietary
1478±14
2,056$1.25 / $10400K
39
1084
deepseek-v3.2-exp
DeepSeek · MIT
1478±23
641$0.27 / $0.41163.8K
40
1084
deepseek-v3.1-thinking
DeepSeek · MIT
1477±21
880$1.23 / $4.94N/A
41
1284
gpt-5.2
OpenAI · Proprietary
1476±19
1,109$1.75 / $14400K
42
699
kimi-k2.5-instant
Moonshot · Modified MIT
1476±38
243$0.38 / $1.72262.1K
43
1091
qwen3.5-35b-a3b
Alibaba · Apache 2.0
1475±27
494$0.16 / $1.30262.1K
44
1877
qwen3-235b-a22b-instruct-2507
Alibaba · Apache 2.0
1474±10
4,093$0.26 / $1.06N/A
45
1781
kimi-k2-thinking-turbo
Moonshot · Modified MIT
1473±13
2,212$1.15 / $8262.1K
46
1881
Anthropic
claude-sonnet-4-5-20250929
Anthropic · Proprietary
1472±12
2,584$3 / $15200K
47
1289
gemini-3.1-flash-lite-preview
Google · Proprietary
1472±22
739$0.25 / $1.501M
48
1785
gpt-5.2-high
OpenAI · Proprietary
1471±16
1,374$1.75 / $14400K
49
1094
qwen3.5-122b-a10b
Alibaba · Apache 2.0
1471±27
466$0.26 / $2.08262.1K
50
2384
chatgpt-4o-latest-20250326
OpenAI · Proprietary
1467±10
4,204$5 / $15128K
51
1889
deepseek-v3.1
DeepSeek · MIT
1467±18
1,117$1.23 / $4.94N/A
52
2584
Anthropic
claude-opus-4-1-20250805
Anthropic · Proprietary
1465±10
3,922$15 / $75200K
53
10101
deepseek-v3.2-exp-thinking
DeepSeek · MIT
1465±32
320$0.27 / $0.41163.8K
54
2387
o3-2025-04-16
OpenAI · Proprietary
1465±11
3,036$2 / $8200K
55
1499
qwen3.5-flash
Alibaba · Proprietary
1463±26
486N/AN/A
56
2293
deepseek-v3.2-thinking
DeepSeek · MIT
1463±15
1,556$0.26 / $0.38163.8K
57
2490
grok-4-1-fast-reasoning
xAI · Proprietary
1462±14
1,955$0.20 / $0.502M
58
2889
Anthropic
claude-opus-4-1-20250805-thinking-16k
Anthropic · Proprietary
1461±12
2,637$15 / $75200K
59
2793
deepseek-v3.2
DeepSeek · MIT
1460±14
1,959$0.26 / $0.38163.8K
60
2399
gpt-4.5-preview-2025-02-27
OpenAI · Proprietary
1457±20
907$75 / $150128K
61
2895
gpt-5-high
OpenAI · Proprietary
1456±16
1,637$1.25 / $10400K
62
21105
qwen3-vl-235b-a22b-instruct
Alibaba · Apache 2.0
1455±27
505$0.20 / $0.88262.1K
63
23101
kimi-k2-0905-preview
Moonshot · Modified MIT
1454±22
743$0.60 / $2.50262.1K
64
28100
qwen3-next-80b-a3b-instruct
Alibaba · Apache 2.0
1454±17
1,223$0.09 / $1.10262.1K
65
3099
kimi-k2-0711-preview
Moonshot · Modified MIT
1453±15
1,596$0.60 / $2.50131.1K
66
31100
gpt-5-chat
OpenAI · Proprietary
1449±15
1,700$1.25 / $10128K
67
30103
deepseek-r1-0528
DeepSeek · MIT
1448±19
1,020$0.45 / $2.15163.8K
68
33101
gemini-2.5-flash-preview-09-2025
Google · Proprietary
1448±16
1,453$0.30 / $2.501M
69
31102
mimo-v2-flash (non-thinking)
Xiaomi · MIT
1448±17
1,342$0.09 / $0.29262.1K
70
33100
Anthropic
claude-opus-4-20250514-thinking-16k
Anthropic · Proprietary
1447±14
1,927$15 / $75200K
71
23115
qwen3-235b-a22b-thinking-2507
Alibaba · Apache 2.0
1447±29
419$0.15 / $1.50131.1K
72
35100
Anthropic
claude-opus-4-20250514
Anthropic · Proprietary
1446±12
2,448$15 / $75200K
73
43100
gemini-2.5-flash
Google · Proprietary
1445±9
5,255$0.30 / $2.501M
74
30110
grok-4-fast-reasoning
xAI · Proprietary
1444±22
727$0.20 / $0.502M
75
35108
glm-4.5
Z.ai · MIT
1442±17
1,371$0.60 / $2.20131.1K
76
31115
Stepfun
step-3.5-flash
StepFun · Apache 2.0
1441±23
656$0.10 / $0.30262.1K
77
28121
qwen3-max-2025-09-23
Alibaba · Proprietary
1441±30
362$0.78 / $3.90262.1K
78
26126
qwen3-vl-235b-a22b-thinking
Alibaba · Apache 2.0
1440±35
302$0.26 / $2.60131.1K
79
46108
qwen3-235b-a22b-no-thinking
Alibaba · Apache 2.0
1439±14
2,018$0.46 / $1.82131.1K
80
43111
qwen3-30b-a3b-instruct-2507
Alibaba · Apache 2.0
1438±16
1,363$0.09 / $0.30262.1K
81
31122
glm-4.7-flash
Z.ai · MIT
1437±28
443$0.06 / $0.40202.8K
82
48110
grok-3-preview-02-24
xAI · Proprietary
1436±14
1,765$3 / $15131.1K
83
26135
amazon-nova-experimental-chat-26-02-10
Amazon · Proprietary
1436±39
216N/AN/A
84
33125
Tencent
hunyuan-turbos-20250416
Tencent · Proprietary
1435±28
471N/AN/A
85
35122
minimax-m2.5
MiniMax · Modified MIT
1434±24
626$0.12 / $0.99196.6K
86
53111
grok-4-0709
xAI · Proprietary
1434±13
2,048$3 / $15256K
87
52115
mistral-large-3
Mistral · Apache 2.0
1433±15
1,659$0.50 / $1.50N/A
88
56115
o1-2024-12-17
OpenAI · Proprietary
1430±14
1,780$15 / $60200K
89
53121
deepseek-r1
DeepSeek · MIT
1429±18
1,151$0.70 / $2.5064K
90
30140
minimax-m2.7
MiniMax · Proprietary
1428±39
233$0.30 / $1.20204.8K
91
58115
mistral-medium-2508
Mistral · Proprietary
1428±10
3,773$2.70 / $8.1032K
92
41131
mimo-v2-flash (thinking)
Xiaomi · MIT
1428±27
450$0.09 / $0.29262.1K
93
58116
Anthropic
claude-haiku-4-5-20251001
Anthropic · Proprietary
1428±12
2,637$1 / $5200K
94
33142
Tencent
hunyuan-t1-20250711
Tencent · Proprietary
1423±37
261N/AN/A
95
31150
gpt-5.4-nano-high
OpenAI · Proprietary
1421±43
193$0.20 / $1.25400K
96
57134
longcat-flash-chat
Meituan · MIT
1421±23
690$0.20 / $0.80131.1K
97
58135
minimax-m2.1-preview
MiniMax · MIT
1418±21
844$0.27 / $0.95196.6K
98
72127
gpt-4.1-2025-04-14
OpenAI · Proprietary
1416±12
2,520$2 / $81M
99
62138
qwen3-next-80b-a3b-thinking
Alibaba · Apache 2.0
1415±22
735$0.10 / $0.78131.1K
100
73130
deepseek-v3-0324
DeepSeek · MIT
1415±12
2,511$3 / $4.5032.8K
101
72131
Anthropic
claude-sonnet-4-20250514-thinking-32k
Anthropic · Proprietary
1414±14
1,839$3 / $151M
102
71136
o3-mini-high
OpenAI · Proprietary
1413±17
1,181$1.10 / $4.40200K
103
73134
glm-4.5-air
Z.ai · MIT
1413±15
1,653$0.13 / $0.85131.1K
104
51151
amazon-nova-experimental-chat-12-10
Amazon · Proprietary
1413±36
240N/AN/A
105
73136
gpt-5-mini-high
OpenAI · Proprietary
1411±17
1,381$0.25 / $2400K
106
79138
gemini-2.5-flash-lite-preview-09-2025-no-thinking
Google · Proprietary
1407±13
2,238$0.10 / $0.401M
107
79138
Anthropic
claude-sonnet-4-20250514
Anthropic · Proprietary
1407±13
2,248$3 / $151M
108
75140
qwen3-coder-480b-a35b-instruct
Alibaba · Apache 2.0
1406±17
1,371$0.40 / $1.60262.1K
109
79139
gemini-2.5-flash-lite-preview-06-17-thinking
Google · Proprietary
1406±15
1,711$0.10 / $0.401M
110
67153
glm-4-plus-0111
Zhipu · Proprietary
1403±30
387N/AN/A
111
85140
o4-mini-2025-04-16
OpenAI · Proprietary
1401±12
2,339$1.10 / $4.40200K
112
58157
Tencent
hunyuan-turbo-0110
Tencent · Proprietary
1400±39
208N/AN/A
113
85143
qwen2.5-max
Alibaba · Proprietary
1398±13
1,956N/AN/A
114
84148
amazon-nova-experimental-chat-11-10
Amazon · Proprietary
1398±18
1,189N/AN/A
115
85150
qwen3-235b-a22b
Alibaba · Apache 2.0
1395±16
1,266$0.46 / $1.82131.1K
116
85151
mai-1-preview
Microsoft AI · Proprietary
1394±18
1,041N/AN/A
117
89148
Anthropic
claude-3-7-sonnet-20250219-thinking-32k
Anthropic · Proprietary
1394±13
1,995$3 / $15200K
118
70161
Stepfun
step-3
StepFun · Apache 2.0
1394±38
235$0.57 / $1.4265.5K
119
93150
gemini-2.0-flash-001
Google · Proprietary
1390±12
2,400$0.10 / $0.401M
120
75161
Tencent
hunyuan-large-2025-02-10
Tencent · Proprietary
1389±33
295N/AN/A
121
92152
mistral-medium-2505
Mistral · Proprietary
1389±15
1,674$0.40 / $2131.1K
122
77163
minimax-m2
MiniMax · Apache 2.0
1388±33
297$0.26 / $1196.6K
123
89157
grok-3-mini-high
xAI · Proprietary
1387±22
727$0.30 / $0.50131.1K
124
79163
ling-flash-2.0
Ant Group · MIT
1387±32
312N/AN/A
125
95153
minimax-m1
MiniMax · Apache 2.0
1386±14
1,863$0.40 / $2.201M
126
96153
o1-preview
OpenAI · Proprietary
1386±12
2,763$15 / $60N/A
127
95156
qwq-32b
Alibaba · Apache 2.0
1384±16
1,364$0.15 / $0.58131.1K
128
99155
gpt-4.1-mini-2025-04-14
OpenAI · Proprietary
1383±13
2,067$0.40 / $1.601M
129
101155
Anthropic
claude-3-7-sonnet-20250219
Anthropic · Proprietary
1382±13
2,224$3 / $15200K
130
87167
gpt-5-nano-high
OpenAI · Proprietary
1380±30
387$0.05 / $0.40400K
131
85172
intellect-3
Prime Intellect · MIT
1380±34
309$0.20 / $1.10131.1K
132
89171
ring-flash-2.0
Ant Group · MIT
1377±31
331N/AN/A
133
92170
qwen-plus-0125
Alibaba · Proprietary
1376±27
459$0.40 / $1.20131.1K
134
101159
grok-3-mini-beta
xAI · Proprietary
1376±18
1,073$0.30 / $0.50131.1K
135
105157
gpt-oss-120b
OpenAI · Apache 2.0
1376±15
1,665$0.04 / $0.19131.1K
136
92173
trinity-large
Arcee AI · Apache 2.0
1374±29
475N/AN/A
137
108157
gemma-3-27b-it
Google · Gemma
1374±13
2,334$0.08 / $0.16131.1K
138
110157
gemini-1.5-pro-002
Google · Proprietary
1373±10
4,444$3.50 / $10.502.1M
139
108163
qwen3-30b-a3b
Alibaba · Apache 2.0
1371±17
1,273$0.08 / $0.2841K
140
110163
deepseek-v3
DeepSeek · DeepSeek
1370±15
1,450$1.14 / $4.56N/A
141
110163
gemini-2.0-flash-lite-preview-02-05
Google · Proprietary
1369±15
1,508$0.07 / $0.301M
142
90183
Tencent
hunyuan-turbos-20250226
Tencent · Proprietary
1367±39
203N/AN/A
143
95180
Stepfun
step-2-16k-exp-202412
StepFun · Proprietary
1366±34
328N/AN/A
144
118160
Anthropic
claude-3-5-sonnet-20241022
Anthropic · Proprietary
1366±8
6,615$6 / $30200K
145
91184
qwen3-32b
Alibaba · Apache 2.0
1365±39
187$0.08 / $0.2441K
146
117167
01.AI
yi-lightning
01 AI · Proprietary
1363±12
2,736N/AN/A
147
104181
Tencent
hunyuan-standard-2025-02-10
Tencent · Proprietary
1361±31
340N/AN/A
148
121167
o3-mini
OpenAI · Proprietary
1361±10
3,392$1.10 / $4.40200K
149
112176
nvidia-nemotron-3-nano-30b-a3b-bf16
Nvidia · NVIDIA Open Model
1359±21
882$0.06 / $0.24262.1K
150
123173
Cohere
command-a-03-2025
Cohere · CC-BY-NC-4.0
1357±11
3,093$2.50 / $10256K
151
112181
amazon-nova-experimental-chat-10-20
Amazon · Proprietary
1356±24
616N/AN/A
152
110183
Stepfun
step-1o-turbo-202506
StepFun · Proprietary
1355±27
464N/AN/A
153
110182
deepseek-v2.5-1210
DeepSeek · DeepSeek
1355±26
446N/AN/A
154
121180
mistral-small-2506
Mistral · Apache 2.0
1352±20
839$0.10 / $0.3032K
155
115189
gpt-oss-20b
OpenAI · Apache 2.0
1351±27
495$0.03 / $0.11131.1K
156
129175
o1-mini
OpenAI · Proprietary
1350±10
4,309$1.10 / $4.40N/A
157
108209
glm-4.5v
Z.ai · MIT
1346±42
174$0.60 / $1.8065.5K
158
133178
gemini-advanced-0514
Google · Proprietary
1345±11
5,932N/AN/A
159
124191
nova-2-lite
Amazon · Proprietary
1345±23
702$0.30 / $2.501M
160
138176
Anthropic
claude-3-5-sonnet-20240620
Anthropic · Proprietary
1344±9
8,100$6 / $30200K
161
133181
glm-4-plus
Zhipu AI · Proprietary
1343±13
2,427$0.44 / $1.76204.8K
162
141181
grok-2-2024-08-13
xAI · Proprietary
1341±9
5,317$2 / $10131.1K
163
141181
gemini-1.5-pro-001
Google · Proprietary
1341±10
8,912$3.50 / $10.502.1M
164
143181
gpt-4o-2024-05-13
OpenAI · Proprietary
1338±8
11,416$5 / $15128K
165
129203
olmo-3.1-32b-instruct
Ai2 · Apache 2.0
1334±26
541$0.20 / $0.6065.5K
166
142195
athene-v2-chat
NexusFlow · NexusFlow
1334±14
1,781N/AN/A
167
141195
gemma-3n-e4b-it
Google · Gemma
1333±17
1,224$0.02 / $0.0432.8K
168
146195
Meta
llama-4-maverick-17b-128e-instruct
Meta · Llama 4
1331±13
2,166$0.63 / $1.80131.1K
169
146195
deepseek-v2.5
DeepSeek · DeepSeek
1330±13
2,242N/AN/A
170
138203
qwen2.5-plus-1127
Alibaba · Proprietary
1330±23
621N/AN/A
171
147195
gpt-4o-2024-08-06
OpenAI · Proprietary
1329±10
3,778$2.50 / $10128K
172
152195
Anthropic
claude-3-opus-20240229
Anthropic · Proprietary
1324±8
23,348$15 / $75200K
173
149198
gemini-1.5-flash-002
Google · Proprietary
1324±11
2,980$0.07 / $0.301M
174
150198
qwen2.5-72b-instruct
Alibaba · Qwen
1322±11
3,329$1.20 / $1.20N/A
175
150199
Meta
llama-3.1-405b-instruct-bf16
Meta · Llama 3.1 Community
1322±11
3,105$4 / $432.8K
176
130219
gpt-4.1-nano-2025-04-14
OpenAI · Proprietary
1321±36
246$0.10 / $0.401M
177
131224
Tencent
hunyuan-large-vision
Tencent · Proprietary
1320±37
255N/AN/A
178
162203
gpt-4-turbo-2024-04-09
OpenAI · Proprietary
1316±9
10,827$10 / $30128K
179
162204
Anthropic
claude-3-5-haiku-20241022
Anthropic · Proprietary
1315±10
4,189$0.80 / $4200K
180
162204
gpt-4o-mini-2024-07-18
OpenAI · Proprietary
1315±9
5,768$0.15 / $0.60128K
181
138229
olmo-3-32b-think
Ai2 · Apache 2.0
1315±38
274$0.15 / $0.5065.5K
182
162207
gpt-4-1106-preview
OpenAI · Proprietary
1314±10
9,150$10 / $30128K
183
163206
Meta
llama-3.1-405b-instruct-fp8
Meta · Llama 3.1 Community
1314±9
5,226$4 / $432.8K
184
158213
Meta
llama-4-scout-17b-16e-instruct
Meta · Llama
1313±15
1,640$0.40 / $0.708.2K
185
164210
gpt-4-0125-preview
OpenAI · Proprietary
1312±10
11,382$10 / $30128K
186
138233
ibm-granite-h-small
IBM · Apache 2.0
1312±40
225N/AN/A
187
164211
grok-2-mini-2024-08-13
xAI · Proprietary
1311±10
4,510$2 / $10131.1K
188
162214
qwen-max-0919
Alibaba · Qwen
1311±15
1,421$1.60 / $6.4032.8K
189
144233
llama-3.3-nemotron-49b-super-v1
Nvidia · Nvidia
1307±39
211N/AN/A
190
161224
reka-core-20240904
Reka AI · Proprietary
1305±23
598N/AN/A
191
162224
llama-3.1-nemotron-70b-instruct
Nvidia · Llama 3.1
1304±21
723$1.20 / $1.20131.1K
192
170215
mistral-large-2407
Mistral · Mistral Research
1303±10
3,933$2 / $6131.1K
193
164218
glm-4-0520
Zhipu AI · Proprietary
1303±17
1,227N/AN/A
194
170219
athene-70b-0725
NexusFlow · CC-BY-NC-4.0
1300±15
1,678N/AN/A
195
172217
qwen2-72b-instruct
Alibaba · Qianwen LICENSE
1300±11
4,078$0.90 / $0.9032.8K
196
149236
llama-3.1-tulu-3-70b
Ai2 · Llama 3.1
1298±36
224N/AN/A
197
176216
gemma-2-27b-it
Google · Gemma license
1298±9
6,872$0.65 / $0.658.2K
198
164232
reka-flash-20240904
Reka AI · Proprietary
1298±23
607N/AN/A
199
173220
mistral-large-2411
Mistral · MRL
1297±13
1,914$2 / $6131.1K
200
178219
gemini-1.5-flash-001
Google · Proprietary
1295±10
7,043$0.07 / $0.301M
201
159236
Tencent
hunyuan-standard-256k
Tencent · Proprietary
1295±33
305N/AN/A
202
170232
Cohere
command-r-plus-08-2024
Cohere · CC-BY-NC-4.0
1293±20
845$2.50 / $10128K
203
182226
Meta
llama-3.3-70b-instruct
Meta · Llama-3.3
1291±11
3,421$0.10 / $0.32131.1K
204
179230
amazon-nova-pro-v1.0
Amazon · Proprietary
1291±14
1,627$0.80 / $3.20300K
205
180232
deepseek-coder-v2
DeepSeek · DeepSeek License
1289±15
1,712$0.14 / $0.28128K
206
173234
gemma-2-9b-it-simpo
Princeton · MIT
1289±21
753$0.03 / $0.098.2K
207
180232
mistral-small-3.1-24b-instruct-2503
Mistral · Apache 2.0
1288±15
1,723$0.10 / $0.3032K
208
183232
nemotron-4-340b-instruct
Nvidia · NVIDIA Open Model
1288±13
2,402N/AN/A
209
184232
gpt-4-0314
OpenAI · Proprietary
1286±12
5,849$30 / $608.2K
210
185233
qwen1.5-72b-chat
Alibaba · Qianwen LICENSE
1282±12
4,167N/AN/A
211
173242
magistral-medium-2506
Mistral · Proprietary
1282±28
565$2 / $540K
212
173243
olmo-3.1-32b-think
Ai2 · Apache 2.0
1281±28
510$0.15 / $0.5065.5K
213
178241
qwen2.5-coder-32b-instruct
Alibaba · Apache 2.0
1281±25
528$0.87 / $0.8732K
214
186235
qwen1.5-110b-chat
Alibaba · Qianwen LICENSE
1279±13
2,906N/AN/A
215
188234
Meta
llama-3.1-70b-instruct
Meta · Llama 3.1 Community
1277±10
4,846$0.40 / $0.40131.1K
216
183242
jamba-1.5-large
AI21 Labs · Jamba Open
1276±22
675$2 / $8256K
217
192234
Anthropic
claude-3-sonnet-20240229
Anthropic · Proprietary
1276±9
15,648$3 / $15200K
218
181247
llama-3.1-nemotron-51b-instruct
Nvidia · Llama 3.1
1275±28
403N/AN/A
219
189236
01.AI
yi-1.5-34b-chat
01 AI · Apache-2.0
1273±13
2,868N/AN/A
220
187239
amazon-nova-lite-v1.0
Amazon · Proprietary
1273±16
1,284$0.06 / $0.24300K
221
193236
gemini-1.5-flash-8b-001
Google · Proprietary
1272±11
2,914$0.07 / $0.301M
222
193236
Cohere
c4ai-aya-expanse-32b
Cohere · CC-BY-NC-4.0
1271±12
2,375N/AN/A
223
193243
phi-4
Microsoft · MIT
1267±15
1,503$0.07 / $0.1416.4K
224
198239
Cohere
command-r-plus
Cohere · CC-BY-NC-4.0
1267±10
10,474$2.50 / $10128K
225
193246
mistral-small-24b-instruct-2501
Mistral · Apache 2.0
1266±18
1,054$0.05 / $0.0832.8K
226
197243
qwen1.5-32b-chat
Alibaba · Qianwen LICENSE
1266±13
3,241N/AN/A
227
205243
gemma-2-9b-it
Google · Gemma license
1263±9
4,980$0.03 / $0.098.2K
228
196248
Cohere
command-r-08-2024
Cohere · CC-BY-NC-4.0
1261±20
834$0.15 / $0.60128K
229
199248
amazon-nova-micro-v1.0
Amazon · Proprietary
1260±16
1,281$0.04 / $0.14128K
230
211248
gpt-4-0613
OpenAI · Proprietary
1256±10
8,540$30 / $608.2K
231
196250
ministral-8b-2410
Mistral · MRL
1255±26
478$0.10 / $0.10131.1K
232
208250
01.AI
yi-34b-chat
01 AI · Yi License
1250±18
1,219$0.90 / $0.904.1K
233
219249
Anthropic
claude-3-haiku-20240307
Anthropic · Proprietary
1248±9
16,707$0.25 / $1.25200K
234
212250
internlm2_5-20b-chat
InternLM · Other
1247±19
959$0 / $032.8K
235
197262
olmo-2-0325-32b-instruct
Ai2 · Apache-2.0
1241±37
229$0.05 / $0.20128K
236
222250
qwen1.5-14b-chat
Alibaba · Qianwen LICENSE
1240±14
3,152$0.30 / $0.30N/A
237
197263
qwq-32b-preview
Alibaba · Apache 2.0
1238±40
206$0.15 / $0.58131.1K
238
227250
Cohere
command-r
Cohere · CC-BY-NC-4.0
1237±11
8,202$0.15 / $0.60128K
239
226251
reka-flash-21b-20240226-online
Reka AI · Proprietary
1236±15
2,015N/AN/A
240
217256
Cohere
c4ai-aya-expanse-8b
Cohere · CC-BY-NC-4.0
1234±23
618N/AN/A
241
226253
gemini-pro-dev-api
Google · Proprietary
1234±18
1,867$0.35 / $1.0532.8K
242
199264
deepseek-llm-67b-chat
DeepSeek · DeepSeek License
1234±42
211N/AN/A
243
219263
qwen1.5-7b-chat
Alibaba · Qianwen LICENSE
1227±29
417$0.20 / $0.20N/A
244
231255
reka-flash-21b-20240226
Reka AI · Proprietary
1226±14
2,774N/AN/A
245
217269
llama-3.1-tulu-3-8b
Ai2 · Llama 3.1
1221±37
238N/AN/A
246
217271
granite-3.1-8b-instruct
IBM · Apache 2.0
1218±40
211N/AN/A
247
232264
jamba-1.5-mini
AI21 Labs · Jamba Open
1217±22
711$0.20 / $0.40256K
248
220271
gemini-pro
Google · Proprietary
1216±38
236$0.35 / $1.0532.8K
249
237263
mixtral-8x22b-instruct-v0.1
Mistral · Apache 2.0
1210±11
5,655$0.90 / $0.9065.5K
250
238263
mistral-large-2402
Mistral · Proprietary
1209±11
7,840$4 / $1232K
251
238263
gpt-3.5-turbo-0125
OpenAI · Proprietary
1208±10
7,558$0.50 / $1.5016.4K
252
228272
granite-3.1-2b-instruct
IBM · Apache 2.0
1207±39
231N/AN/A
253
226276
qwen-14b-chat
Alibaba · Qianwen LICENSE
1205±43
195N/AN/A
254
239264
Meta
llama-3.1-8b-instruct
Meta · Llama 3.1 Community
1203±10
4,400$0.02 / $0.0516.4K
255
241264
Meta
llama-3-70b-instruct
Meta · Llama 3 Community
1201±9
15,885$0.51 / $0.748.2K
256
239268
phi-3-medium-4k-instruct
Microsoft · MIT
1201±13
2,819$0.17 / $0.68N/A
257
241269
gemma-2-2b-it
Google · Gemma license
1198±11
3,790N/AN/A
258
241271
mistral-medium
Mistral · Proprietary
1195±14
3,014$2.70 / $8.1032K
259
241276
zephyr-orpo-141b-A35b-v0.1
HuggingFace · Apache 2.0
1186±23
657N/AN/A
260
242279
granite-3.0-2b-instruct
IBM · Apache 2.0
1179±23
759N/AN/A
261
247276
openchat-3.5-0106
OpenChat · Apache-2.0
1179±18
1,525N/AN/A
262
251274
dbrx-instruct-preview
Databricks · DBRX LICENSE
1177±13
5,019$0.60 / $0.6032.8K
263
251276
snowflake-arctic-instruct
Snowflake · Apache 2.0
1177±14
3,128N/AN/A
264
251276
starling-lm-7b-beta
Nexusflow · Apache-2.0
1176±15
2,863N/AN/A
265
241283
openchat-3.5
OpenChat · Apache-2.0
1176±32
322$0.20 / $0.20N/A
266
252276
gemma-1.1-7b-it
Google · Gemma license
1175±13
3,219$0.03 / $0.098.2K
267
240289
chatglm3-6b
Tsinghua · Apache-2.0
1168±43
189N/AN/A
268
241287
chatglm-6b
Tsinghua · Non-commercial
1166±39
267N/AN/A
269
257278
Meta
llama-3-8b-instruct
Meta · Llama 3 Community
1166±10
10,757$0.03 / $0.048.2K
270
251284
granite-3.0-8b-instruct
IBM · Apache 2.0
1165±24
701N/AN/A
271
254286
gpt-3.5-turbo-1106
OpenAI · Proprietary
1160±25
708$1 / $216.4K
272
259283
mixtral-8x7b-instruct-v0.1
Mistral · Apache 2.0
1153±10
8,285$0.63 / $0.6332K
273
254291
wizardlm-70b
Microsoft · Llama 2 Community
1152±33
334N/AN/A
274
259286
phi-3-small-8k-instruct
Microsoft · MIT
1150±14
2,376$0.15 / $0.60N/A
275
258287
vicuna-13b
LMSYS · Llama 2 Community
1146±20
1,178$0.30 / $0.30N/A
276
258288
qwen1.5-4b-chat
Alibaba · Qianwen LICENSE
1146±20
1,028$0.10 / $0.10N/A
277
267291
gemma-1.1-2b-it
Google · Gemma license
1137±18
1,291N/AN/A
278
265292
starling-lm-7b-alpha
UC Berkeley · CC-BY-NC-4.0
1137±22
858N/AN/A
279
266291
gemma-7b-it
Google · Gemma license
1136±20
1,049$0.05 / $0.088.2K
280
267292
vicuna-33b
LMSYS · Non-commercial
1133±17
1,385$0 / $02K
281
267295
Meta
llama-3.2-3b-instruct
Meta · Llama 3.2
1128±26
721$0.05 / $0.3480K
282
270293
phi-3-mini-128k-instruct
Microsoft · MIT
1124±16
2,016$0.13 / $0.52N/A
283
269293
phi-3-mini-4k-instruct-june-2024
Microsoft · MIT
1124±18
1,172$0.13 / $0.524.1K
284
267296
wizardlm-13b
Microsoft · Llama 2 Community
1119±34
287$0.30 / $0.30N/A
285
265298
openhermes-2.5-mistral-7b
NousResearch · Apache-2.0
1118±42
205$0.17 / $0.17N/A
286
274295
phi-3-mini-4k-instruct
Microsoft · MIT
1112±14
2,296$0.13 / $0.52N/A
287
270301
tulu-2-dpo-70b
AllenAI/UW · AI2 ImpACT Low-risk
1103±36
274N/AN/A
288
275298
gemma-2b-it
Google · Gemma license
1100±25
598$0.10 / $0.10N/A
289
279296
mistral-7b-instruct-v0.2
Mistral · Apache-2.0
1100±15
1,998$0.20 / $0.2032.8K
290
281299
Meta
llama-2-13b-chat
Meta · Llama 2 Community
1092±19
1,161$0.25 / $0.254.1K
291
272302
mpt-7b-chat
MosaicML · CC-BY-NC-SA-4.0
1087±43
178N/AN/A
292
276301
vicuna-7b
LMSYS · Llama 2 Community
1086±34
335$0.20 / $0.20N/A
293
276301
Meta
codellama-34b-instruct
Meta · Llama 2 Community
1085±39
249$0.35 / $1.4016.4K
294
285301
Meta
llama-2-70b-chat
Meta · Llama 2 Community
1082±13
3,619$0.70 / $2.804.1K
295
283301
olmo-7b-instruct
Ai2 · Apache-2.0
1079±24
722$0.20 / $0.20N/A
296
283302
palm-2
Google · Proprietary
1071±35
355$0.50 / $0.5025.8K
297
287302
Meta
llama-2-7b-chat
Meta · Llama 2 Community
1061±20
956$0.15 / $0.154.1K
298
287303
zephyr-7b-beta
HuggingFace · MIT
1046±31
373$0.15 / $0.1516.4K
299
289303
Meta
llama-3.2-1b-instruct
Meta · Llama 3.2
1046±28
674$0.03 / $0.2060K
300
290303
mistral-7b-instruct
Mistral · Apache 2.0
1038±34
274$0.07 / $0.284.1K
301
290304
RWKV-4-Raven-14B
RWKV · Apache 2.0
1031±41
218N/AN/A
302
298305
koala-13b
UC Berkeley · Non-commercial
999±33
374N/AN/A
303
295306
dolly-v2-12b
Databricks · MIT
995±49
177N/AN/A
304
301306
fastchat-t5-3b
LMSYS · Apache 2.0
955±41
224N/AN/A
305
302306
oasst-pythia-12b
OpenAssistant · Apache 2.0
939±35
321N/AN/A
306
303306
alpaca-13b
Stanford · Non-commercial
912±42
263N/AN/A

Default Leaderboard Plots

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

Confidence Intervals on Model Strength (via Bootstrapping)

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

Battle Count for Each Combination of Models (without Ties)