Text Arena✍️Creative Writing

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

May 28, 2026
958,507 votes
358 models
Rank Spread
1
15
Anthropic
claude-opus-4-6-thinking
Anthropic · Proprietary
1497±9
5,508$5 / $251M
2
17
gemini-3-pro
Google · Proprietary
1485±8
6,290$2 / $121M
3
19
Anthropic
claude-opus-4-7-thinking
Anthropic · Proprietary
1485±11
3,245$5 / $251M
4
19
Anthropic
claude-opus-4-7
Anthropic · Proprietary
1484±11
3,398$5 / $251M
5
19
gemini-3.1-pro-preview
Google · Proprietary
1483±8
7,005$2 / $121M
6
214
Anthropic
claude-opus-4-6
Anthropic · Proprietary
1477±9
5,665$5 / $251M
7
318
Anthropic
claude-opus-4-5-20251101-thinking-32k
Anthropic · Proprietary
1468±8
5,546$5 / $25200K
8
236
gemini-3.5-flash
Google · Proprietary
1464±17
1,376$1.50 / $91M
9
623
Anthropic
claude-opus-4-5-20251101
Anthropic · Proprietary
1463±7
10,245$5 / $25200K
10
630
grok-4.20-beta1
xAI · Proprietary
1462±10
3,685N/AN/A
11
336
Meta
muse-spark
Meta · Proprietary
1462±14
1,796N/AN/A
12
634
gemini-3-flash
Google · Proprietary
1459±10
4,684$0.50 / $31M
13
637
glm-5.1
Z.ai · MIT
1457±13
2,209$1.40 / $4.40202.8K
14
736
gpt-5.5-instant
OpenAI · Proprietary
1456±10
4,055$5 / $301.1M
15
735
Anthropic
claude-sonnet-4-5-20250929
Anthropic · Proprietary
1455±6
11,254$3 / $15200K
16
742
gpt-5.5-high
OpenAI · Proprietary
1451±12
2,766$5 / $301.1M
17
840
Anthropic
claude-sonnet-4-6
Anthropic · Proprietary
1450±10
4,266$3 / $151M
18
838
gemini-3-flash (thinking-minimal)
Google · Proprietary
1449±7
8,245$0.50 / $31M
19
843
glm-5
Z.ai · MIT
1449±10
3,516$1 / $3.20202.8K
20
743
gpt-5.5
OpenAI · Proprietary
1449±12
2,852$5 / $301.1M
21
843
grok-4.20-beta-0309-reasoning
xAI · Proprietary
1447±9
4,697$2 / $62M
22
845
qwen3.5-max-preview
Alibaba · Proprietary
1447±11
3,016N/AN/A
23
940
Anthropic
claude-sonnet-4-5-20250929-thinking-32k
Anthropic · Proprietary
1446±6
11,650$3 / $15200K
24
944
gpt-5.4-high
OpenAI · Proprietary
1446±10
4,460$2.50 / $151.1M
25
1040
gemini-2.5-pro
Google · Proprietary
1445±5
17,157$1.25 / $101M
26
943
Anthropic
claude-opus-4-1-20250805-thinking-16k
Anthropic · Proprietary
1445±8
6,838$15 / $75200K
27
946
grok-4.20-multi-agent-beta-0309
xAI · Proprietary
1444±9
4,566$2 / $62M
28
662
qwen3.7-max-preview
Alibaba · Proprietary
1443±28
496$1.25 / $3.751M
29
1145
Anthropic
claude-opus-4-1-20250805
Anthropic · Proprietary
1442±6
10,723$15 / $75200K
30
951
ernie-5.1
Baidu · Proprietary
1442±13
2,181N/AN/A
31
1048
gpt-5.4
OpenAI · Proprietary
1441±9
4,580$2.50 / $151.1M
32
951
mimo-v2.5-pro
Xiaomi · MIT
1440±13
2,424$0.43 / $0.871M
33
1051
deepseek-v4-pro
DeepSeek · MIT
1439±12
2,580$0.43 / $0.871M
34
1053
deepseek-v4-pro-thinking
DeepSeek · MIT
1438±13
2,404$0.43 / $0.871M
35
1253
gpt-4.5-preview-2025-02-27
OpenAI · Proprietary
1436±12
2,618$75 / $150128K
36
2052
grok-4.1
xAI · Proprietary
1432±7
9,505N/AN/A
37
975
qwen3.6-max-preview
Alibaba · Proprietary
1432±23
666$1.04 / $6.24262.1K
38
1754
gpt-5.2-chat-latest-20260210
OpenAI · Proprietary
1432±9
5,046$1.75 / $14128K
39
1557
grok-4.3
xAI · Proprietary
1432±12
2,523$1.25 / $2.501M
40
2155
gpt-5.1-high
OpenAI · Proprietary
1430±8
6,061$1.25 / $10400K
41
2056
Anthropic
claude-opus-4-20250514-thinking-16k
Anthropic · Proprietary
1430±9
4,522$15 / $75200K
42
1661
kimi-k2.6
Moonshot · Modified MIT
1429±13
2,279$0.95 / $4262.1K
43
2655
grok-4.1-thinking
xAI · Proprietary
1429±7
9,576N/AN/A
44
2962
ernie-5.0-0110
Baidu · Proprietary
1424±9
5,357N/AN/A
45
3060
chatgpt-4o-latest-20250326
OpenAI · Proprietary
1423±6
11,563$5 / $15128K
46
2972
mimo-v2-pro
Xiaomi · Proprietary
1423±11
3,366$1 / $31M
47
1783
gemma-4-31b
Google · Apache 2.0
1422±19
934$0.14 / $0.40262.1K
48
2579
ernie-5.0-preview-1203
Baidu · Proprietary
1421±15
1,550N/AN/A
49
3072
kimi-k2.5-thinking
Moonshot · Modified MIT
1420±8
5,572$0.60 / $3N/A
50
3475
Anthropic
claude-opus-4-20250514
Anthropic · Proprietary
1417±8
5,485$15 / $75200K
51
3780
gemini-3.1-flash-lite-preview
Google · Proprietary
1414±9
5,375$0.25 / $1.501M
52
4079
grok-4-1-fast-reasoning
xAI · Proprietary
1413±7
8,455$0.20 / $0.502M
53
3982
qwen3.5-397b-a17b
Alibaba · Apache 2.0
1413±9
4,950$0.39 / $2.34262.1K
54
3393
deepseek-v3.2-exp
DeepSeek · MIT
1411±15
1,634$0.27 / $0.41163.8K
55
4183
gpt-5.1
OpenAI · Proprietary
1411±8
6,450$1.25 / $10400K
56
28110
deepseek-v3.1-terminus
DeepSeek · MIT
1408±27
457$0.27 / $0.95163.8K
57
30105
ernie-5.0-preview-1022
Baidu · Proprietary
1407±22
717N/AN/A
58
4393
gpt-5.3-chat-latest
OpenAI · Proprietary
1406±9
4,847$1.75 / $14128K
59
4198
glm-4.7
Z.ai · MIT
1406±13
1,923$0.40 / $1.75202.8K
60
4593
gpt-5.4-mini-high
OpenAI · Proprietary
1405±10
4,166$0.75 / $4.50400K
61
4298
qwen3.6-plus
Alibaba · Proprietary
1405±12
2,560$0.33 / $1.951M
62
41101
deepseek-v3.1-thinking
DeepSeek · MIT
1404±15
1,646$1.23 / $4.94N/A
63
36104
gemma-4-26b-a4b
Google · Apache 2.0
1404±19
943N/AN/A
64
4593
Bytedance
dola-seed-2.0-pro
Bytedance · Proprietary
1404±8
5,880N/AN/A
65
4593
glm-4.6
Z.ai · MIT
1403±9
5,087$0.43 / $1.74202.8K
66
4599
deepseek-v4-flash-thinking
DeepSeek · MIT
1403±12
2,546$0.10 / $0.201M
67
45101
deepseek-v4-flash
DeepSeek · MIT
1402±12
2,545$0.10 / $0.201M
68
4794
gpt-4.1-2025-04-14
OpenAI · Proprietary
1402±8
6,704$2 / $81M
69
45101
mimo-v2.5
Xiaomi · MIT
1400±12
2,523$0.14 / $0.281M
70
4799
grok-3-preview-02-24
xAI · Proprietary
1400±9
4,728$3 / $15131.1K
71
4999
deepseek-v3.2
DeepSeek · MIT
1400±8
6,531$0.25 / $0.38131.1K
72
5599
gemini-2.5-flash
Google · Proprietary
1397±5
17,041$0.30 / $2.501M
73
51101
grok-4-0709
xAI · Proprietary
1397±8
5,457$3 / $15256K
74
52104
Anthropic
claude-sonnet-4-20250514-thinking-32k
Anthropic · Proprietary
1396±9
4,312$3 / $151M
75
45115
deepseek-v3.2-exp-thinking
DeepSeek · MIT
1395±17
1,203$0.27 / $0.41163.8K
76
47114
qwen3-max-2025-09-23
Alibaba · Proprietary
1395±17
1,158$0.78 / $3.90262.1K
77
49109
deepseek-r1-0528
DeepSeek · MIT
1394±13
2,435$0.50 / $2.15163.8K
78
52108
qwen3-max-preview
Alibaba · Proprietary
1394±10
3,755$0.78 / $3.90262.1K
79
55102
kimi-k2-thinking-turbo
Moonshot · Modified MIT
1394±7
8,987$1.15 / $8262.1K
80
55108
Anthropic
claude-3-7-sonnet-20250219-thinking-32k
Anthropic · Proprietary
1392±9
5,201$3 / $15200K
81
55109
gpt-5-chat
OpenAI · Proprietary
1392±10
4,023$1.25 / $10128K
82
55109
deepseek-v3.2-thinking
DeepSeek · MIT
1392±8
6,054$0.25 / $0.38131.1K
83
55109
gpt-5.2
OpenAI · Proprietary
1391±8
7,249$1.75 / $14400K
84
49119
kimi-k2.5-instant
Moonshot · Modified MIT
1391±16
1,273$0.40 / $1.90262.1K
85
55109
deepseek-v3-0324
DeepSeek · MIT
1390±8
6,041$3 / $4.5032.8K
86
53116
deepseek-v3.1
DeepSeek · MIT
1390±13
2,003$1.23 / $4.94N/A
87
55114
longcat-flash-chat-2602-exp
Meituan · Proprietary
1389±11
3,503N/AN/A
88
59112
gpt-5.2-high
OpenAI · Proprietary
1387±8
7,126$1.75 / $14400K
89
61112
Anthropic
claude-haiku-4-5-20251001
Anthropic · Proprietary
1387±6
11,467$1 / $5200K
90
49125
grok-4-fast-chat
xAI · Proprietary
1387±19
941$3 / $15256K
91
45136
deepseek-v3.1-terminus-thinking
DeepSeek · MIT
1385±28
440$0.27 / $0.95163.8K
92
45135
mimo-v2-omni
Xiaomi · Proprietary
1385±27
470$0.40 / $2262.1K
93
61117
Anthropic
claude-sonnet-4-20250514
Anthropic · Proprietary
1384±9
5,001$3 / $151M
94
61119
gemini-2.5-flash-preview-09-2025
Google · Proprietary
1384±9
4,531$0.30 / $2.501M
95
67117
o3-2025-04-16
OpenAI · Proprietary
1383±7
7,709$2 / $8200K
96
55125
kimi-k2-0905-preview
Moonshot · Modified MIT
1382±15
1,506$0.60 / $2.50262.1K
97
61121
grok-4-fast-reasoning
xAI · Proprietary
1382±12
2,519$0.20 / $0.502M
98
67121
o1-2024-12-17
OpenAI · Proprietary
1381±9
4,642$15 / $60200K
99
72117
mistral-medium-2508
Mistral · Proprietary
1381±6
13,462$2.70 / $8.1032K
100
72117
qwen3-235b-a22b-instruct-2507
Alibaba · Apache 2.0
1381±6
13,335$0.26 / $1.06N/A
101
55141
Tencent
hunyuan-t1-20250711
Tencent · Proprietary
1378±24
622N/AN/A
102
75123
mistral-large-3
Mistral · Apache 2.0
1377±8
6,517$0.50 / $1.50N/A
103
45154
Tencent
hunyuan-vision-1.5-thinking
Tencent · Proprietary
1376±36
261N/AN/A
104
77125
Anthropic
claude-3-7-sonnet-20250219
Anthropic · Proprietary
1376±8
5,981$3 / $15200K
105
75129
gpt-5-high
OpenAI · Proprietary
1375±10
4,255$1.25 / $10400K
106
74129
glm-4.5
Z.ai · MIT
1374±11
3,134$0.60 / $2.20131.1K
107
75129
deepseek-r1
DeepSeek · MIT
1374±10
3,289$0.70 / $2.50163.8K
108
63139
qwen3-235b-a22b-thinking-2507
Alibaba · Apache 2.0
1374±18
1,077$0.10 / $0.10262.1K
109
83130
gemini-2.5-flash-lite-preview-06-17-thinking
Google · Proprietary
1371±9
4,188$0.10 / $0.401M
110
83131
kimi-k2-0711-preview
Moonshot · Modified MIT
1370±10
3,444$0.60 / $2.50131.1K
111
85133
qwen3.5-122b-a10b
Alibaba · Apache 2.0
1369±10
4,100$0.26 / $2.08262.1K
112
93130
Anthropic
claude-3-5-sonnet-20241022
Anthropic · Proprietary
1369±6
11,757$3 / $15200K
113
88131
qwen3-235b-a22b-no-thinking
Alibaba · Apache 2.0
1368±9
4,623$0.46 / $1.82131.1K
114
71147
Tencent
hunyuan-hy3-preview
Tencent · tencent-hunyuan-community
1367±20
890$0.29 / $1.17262.1K
115
89139
qwen3-coder-480b-a35b-instruct
Alibaba · Apache 2.0
1366±11
3,280$0.40 / $1.60262.1K
116
93139
o1-preview
OpenAI · Proprietary
1365±10
4,508$15 / $60N/A
117
95139
mistral-medium-2505
Mistral · Proprietary
1364±10
4,080$0.40 / $2131.1K
118
87147
Tencent
hunyuan-turbos-20250416
Tencent · Proprietary
1362±15
1,494N/AN/A
119
85151
qwen3-vl-235b-a22b-instruct
Alibaba · Apache 2.0
1362±17
1,385$0.20 / $0.88262.1K
120
97144
gemini-2.5-flash-lite-preview-09-2025-no-thinking
Google · Proprietary
1361±8
6,508$0.10 / $0.401M
121
98146
minimax-m2.5
MiniMax · Modified MIT
1360±8
5,746$0.15 / $1.15204.8K
122
101146
gemini-1.5-pro-002
Google · Proprietary
1358±7
8,062$3.50 / $10.502.1M
123
101146
mimo-v2-flash (non-thinking)
Xiaomi · MIT
1358±8
6,822$0.10 / $0.30262.1K
124
98147
qwen3.5-27b
Alibaba · Apache 2.0
1358±10
3,887$0.20 / $1.56262.1K
125
101151
minimax-m2.7
MiniMax · Modified MIT
1356±11
3,320$0.26 / $1.20204.8K
126
82167
amazon-nova-experimental-chat-26-01-10
Amazon · Proprietary
1356±25
551N/AN/A
127
104151
qwen2.5-max
Alibaba · Proprietary
1354±9
5,000N/AN/A
128
106154
trinity-large-preview
Arcee AI · Apache 2.0
1351±10
4,357$0.15 / $0.45131K
129
109154
gpt-4.1-mini-2025-04-14
OpenAI · Proprietary
1349±9
5,157$0.40 / $1.601M
130
108154
deepseek-v3
DeepSeek · DeepSeek
1349±10
3,623$1.14 / $4.56N/A
131
111154
gemma-3-27b-it
Google · Gemma
1348±8
6,398$0.08 / $0.16131.1K
132
109161
minimax-m2.1-preview
MiniMax · MIT
1347±12
2,717$0.29 / $0.95204.8K
133
116156
gemini-2.0-flash-001
Google · Proprietary
1346±8
6,286$0.10 / $0.401M
134
115158
Stepfun
step-3.5-flash
StepFun · Apache 2.0
1346±9
5,211$0.09 / $0.30262.1K
135
95184
glm-4.6v
Z.ai · MIT
1345±29
420$0.30 / $0.90131.1K
136
115160
qwen3.5-35b-a3b
Alibaba · Apache 2.0
1345±9
4,271$0.14 / $1262.1K
137
116160
gemini-2.0-flash-lite-preview-02-05
Google · Proprietary
1345±9
4,104$0.07 / $0.301M
138
116160
qwen3.5-flash
Alibaba · Proprietary
1345±10
4,292N/AN/A
139
117163
gemini-advanced-0514
Google · Proprietary
1343±10
7,025N/AN/A
140
97184
amazon-nova-experimental-chat-26-02-10
Amazon · Proprietary
1343±27
457N/AN/A
141
101184
amazon-nova-experimental-chat-12-10
Amazon · Proprietary
1342±24
581N/AN/A
142
111183
qwen3-vl-235b-a22b-thinking
Alibaba · Apache 2.0
1339±18
1,032$0.26 / $2.60131.1K
143
120171
trinity-large-thinking
Arcee AI · Apache 2.0
1338±10
3,756$0.22 / $0.85262.1K
144
123168
o4-mini-2025-04-16
OpenAI · Proprietary
1338±8
5,836$1.10 / $4.40200K
145
117181
mimo-v2-flash (thinking)
Xiaomi · MIT
1338±14
1,709$0.10 / $0.30262.1K
146
126168
gpt-4o-2024-05-13
OpenAI · Proprietary
1337±7
16,599$5 / $15128K
147
122176
gpt-5.4-nano-high
OpenAI · Proprietary
1337±10
4,015$0.20 / $1.25400K
148
110184
Stepfun
step-2-16k-exp-202412
StepFun · Proprietary
1337±21
751N/AN/A
149
126169
Cohere
command-a-03-2025
Cohere · CC-BY-NC-4.0
1336±7
7,623$2.50 / $10256K
150
123181
grok-3-mini-beta
xAI · Proprietary
1335±11
2,761$0.30 / $0.50131.1K
151
111190
gemma-3-12b-it
Google · Gemma
1334±23
600$0.04 / $0.13131.1K
152
108198
llama-3.1-nemotron-ultra-253b-v1
Nvidia · Nvidia Open Model
1332±27
444$0.60 / $1.80131.1K
153
123185
longcat-flash-chat
Meituan · MIT
1330±16
1,382$0.20 / $0.80131.1K
154
126184
grok-3-mini-high
xAI · Proprietary
1329±13
2,062$0.25 / $1.27N/A
155
131184
glm-4.5-air
Z.ai · MIT
1329±10
4,023$0.13 / $0.85131.1K
156
137184
gpt-4o-2024-08-06
OpenAI · Proprietary
1326±8
6,756$2.50 / $10128K
157
133185
gpt-5-mini-high
OpenAI · Proprietary
1326±10
3,561$0.25 / $2400K
158
132188
mistral-small-2506
Mistral · Apache 2.0
1324±13
2,172$0.10 / $0.3032K
159
131191
qwen3-next-80b-a3b-thinking
Alibaba · Apache 2.0
1324±14
1,796$0.10 / $0.78262.1K
160
137187
qwen3-235b-a22b
Alibaba · Apache 2.0
1324±10
3,579$0.46 / $1.82131.1K
161
138185
gemini-1.5-pro-001
Google · Proprietary
1322±8
11,797$3.50 / $10.502.1M
162
139185
gpt-4-turbo-2024-04-09
OpenAI · Proprietary
1322±8
14,396$10 / $30128K
163
138190
qwen3-30b-a3b-instruct-2507
Alibaba · Apache 2.0
1322±11
2,984$0.09 / $0.30262.1K
164
143192
minimax-m1
MiniMax · Apache 2.0
1318±9
4,546$0.40 / $2.201M
165
142198
qwen3-next-80b-a3b-instruct
Alibaba · Apache 2.0
1317±11
3,032$0.09 / $1.10262.1K
166
133206
glm-4-plus-0111
Z.ai · Proprietary
1317±19
918N/AN/A
167
144191
grok-2-2024-08-13
xAI · Proprietary
1317±7
9,339$2 / $10131.1K
168
135203
qwen-plus-0125
Alibaba · Proprietary
1317±18
931$0.40 / $1.20131.1K
169
144205
glm-4.7-flash
Z.ai · MIT
1312±14
1,811$0.06 / $0.40202.8K
170
146200
o3-mini-high
OpenAI · Proprietary
1312±11
3,065$1.10 / $4.40200K
171
138217
intellect-3
Prime Intellect · MIT
1312±22
800$0.20 / $1.10131.1K
172
138221
glm-4.5v
Z.ai · MIT
1311±23
640$0.60 / $1.8065.5K
173
143216
deepseek-v2.5-1210
DeepSeek · DeepSeek
1310±17
1,090N/AN/A
174
131230
nvidia-llama-3.3-nemotron-super-49b-v1.5
Nvidia · Nvidia Open
1309±29
367$0.10 / $0.40131.1K
175
141222
Stepfun
step-3
StepFun · Apache 2.0
1308±21
786$0.57 / $1.4265.5K
176
154204
Meta
llama-4-maverick-17b-128e-instruct
Meta · Llama 4
1307±9
5,185$0.63 / $1.80131.1K
177
144221
gpt-4.1-nano-2025-04-14
OpenAI · Proprietary
1307±18
1,005$0.10 / $0.401M
178
143226
qwen3-32b
Alibaba · Apache 2.0
1305±23
616$0.08 / $0.28131.1K
179
158213
amazon-nova-experimental-chat-11-10
Amazon · Proprietary
1304±10
3,831N/AN/A
180
146224
nvidia-nemotron-3-super-120b-a12b
Nvidia · NVIDIA Open Model
1304±18
1,056N/AN/A
181
159208
Meta
llama-3.1-405b-instruct-fp8
Meta · Llama 3.1 Community
1304±8
8,948$4 / $432.8K
182
162207
Anthropic
claude-3-5-haiku-20241022
Anthropic · Proprietary
1304±6
9,924$0.80 / $4200K
183
160209
Anthropic
claude-3-5-sonnet-20240620
Anthropic · Proprietary
1303±8
12,430$3 / $15200K
184
142231
Tencent
hunyuan-turbos-20250226
Tencent · Proprietary
1303±26
424N/AN/A
185
143230
Tencent
hunyuan-large-2025-02-10
Tencent · Proprietary
1303±24
568N/AN/A
186
143231
Tencent
hunyuan-turbo-0110
Tencent · Proprietary
1302±25
451N/AN/A
187
165213
o3-mini
OpenAI · Proprietary
1301±7
8,186$1.10 / $4.40200K
188
164215
Meta
llama-3.1-405b-instruct-bf16
Meta · Llama 3.1 Community
1301±8
6,512$4 / $432.8K
189
160220
gemma-3n-e4b-it
Google · Gemma
1300±11
2,884$0.06 / $0.1232.8K
190
144234
mercury-2
Inception AI · Proprietary
1300±27
530$0.25 / $0.75128K
191
165218
gemini-1.5-flash-002
Google · Proprietary
1298±9
5,017$0.07 / $0.301M
192
144236
llama-3.3-nemotron-49b-super-v1
Nvidia · Nvidia
1298±27
428N/AN/A
193
165222
01.AI
yi-lightning
01 AI · Proprietary
1298±10
3,781N/AN/A
194
158232
Stepfun
step-1o-turbo-202506
StepFun · Proprietary
1295±19
997N/AN/A
195
167225
qwq-32b
Alibaba · Apache 2.0
1295±10
3,684$0.50 / $116.4K
196
167222
gpt-4o-mini-2024-07-18
OpenAI · Proprietary
1294±7
10,484$0.15 / $0.60128K
197
165231
olmo-3.1-32b-instruct
Ai2 · Apache 2.0
1292±15
1,724$0.20 / $0.6065.5K
198
169225
gemma-2-27b-it
Google · Gemma license
1292±7
11,429$0.65 / $0.658.2K
199
168229
Meta
llama-4-scout-17b-16e-instruct
Meta · Llama
1290±10
3,786$0.40 / $0.708.2K
200
168230
glm-4-plus
Z.ai · Proprietary
1290±10
3,801$0.44 / $1.76204.8K
201
147248
amazon-nova-experimental-chat-10-09
Amazon · Proprietary
1289±32
322N/AN/A
202
165237
minimax-m2
MiniMax · Apache 2.0
1288±20
899$0.26 / $1204.8K
203
177228
Anthropic
claude-3-opus-20240229
Anthropic · Proprietary
1287±7
28,395$15 / $75200K
204
175230
mistral-large-2407
Mistral · Mistral Research
1287±9
6,692$2 / $6131.1K
205
178230
Meta
llama-3.3-70b-instruct
Meta · Llama-3.3
1286±7
8,069$0.10 / $0.32131.1K
206
177231
gpt-4-1106-preview
OpenAI · Proprietary
1286±8
15,576$10 / $30128K
207
175233
qwen3-30b-a3b
Alibaba · Apache 2.0
1285±10
3,366$0.09 / $0.45131.1K
208
173234
qwen-max-0919
Alibaba · Qwen
1285±12
2,358$1.60 / $6.4032.8K
209
165246
Tencent
hunyuan-large-vision
Tencent · Proprietary
1284±24
629N/AN/A
210
172236
gemma-2-9b-it-simpo
Princeton · MIT
1283±15
1,671$0.03 / $0.098.2K
211
170238
magistral-medium-2506
Mistral · Proprietary
1282±17
1,352$2 / $540K
212
174238
amazon-nova-experimental-chat-10-20
Amazon · Proprietary
1281±15
1,547N/AN/A
213
181234
o1-mini
OpenAI · Proprietary
1281±8
7,858$1.10 / $4.40N/A
214
184235
gpt-4-0125-preview
OpenAI · Proprietary
1280±8
13,940$10 / $30128K
215
182236
gpt-oss-120b
OpenAI · Apache 2.0
1278±10
3,953$0.04 / $0.18131.1K
216
175248
llama-3.1-nemotron-70b-instruct
Nvidia · Llama 3.1
1277±19
1,001$1.20 / $1.20131.1K
217
168251
Tencent
hunyuan-standard-2025-02-10
Tencent · Proprietary
1277±24
590N/AN/A
218
188237
mistral-large-2411
Mistral · MRL
1276±9
4,439$2 / $6131.1K
219
171250
gemma-3-4b-it
Google · Gemma
1276±22
666$0.04 / $0.08131.1K
220
180247
nova-2-lite
Amazon · Proprietary
1275±15
1,720$0.30 / $2.501M
221
181246
qwen2.5-plus-1127
Alibaba · Proprietary
1275±14
1,591N/AN/A
222
193240
grok-2-mini-2024-08-13
xAI · Proprietary
1272±8
7,924$2 / $10131.1K
223
191245
mistral-small-3.1-24b-instruct-2503
Mistral · Apache 2.0
1272±10
4,178$0.10 / $0.3032K
224
179251
ling-flash-2.0
Ant Group · MIT
1270±20
842N/AN/A
225
191247
athene-70b-0725
NexusFlow · CC-BY-NC-4.0
1270±11
3,097N/AN/A
226
175257
granite-4.1-8b
IBM · Apache 2.0
1269±26
571$0.05 / $0.10131.1K
227
187252
reka-core-20240904
Reka AI · Proprietary
1267±18
1,037N/AN/A
228
203250
deepseek-v2.5
DeepSeek · DeepSeek
1265±11
3,450N/AN/A
229
204249
gpt-4-0613
OpenAI · Proprietary
1265±8
13,932$30 / $608.2K
230
208250
gemini-1.5-flash-001
Google · Proprietary
1263±8
9,031$0.07 / $0.301M
231
198253
Cohere
command-r-plus-08-2024
Cohere · CC-BY-NC-4.0
1263±15
1,474$2.50 / $10128K
232
190257
olmo-3-32b-think
Ai2 · Apache 2.0
1263±21
867$0.15 / $0.5065.5K
233
187259
llama-3.1-nemotron-51b-instruct
Nvidia · Llama 3.1
1261±26
482N/AN/A
234
202256
jamba-1.5-large
AI21 Labs · Jamba Open
1261±16
1,379$2 / $8256K
235
192257
ring-flash-2.0
Ant Group · MIT
1260±20
888N/AN/A
236
215251
gemma-2-9b-it
Google · Gemma license
1258±7
8,340$0.03 / $0.098.2K
237
215252
Meta
llama-3.1-70b-instruct
Meta · Llama 3.1 Community
1257±8
8,250$0.40 / $0.40131.1K
238
216255
qwen2.5-72b-instruct
Alibaba · Qwen
1254±8
5,684$1.20 / $1.20N/A
239
216256
athene-v2-chat
NexusFlow · NexusFlow
1254±10
3,713N/AN/A
240
216256
gpt-4-0314
OpenAI · Proprietary
1254±10
8,231$30 / $608.2K
241
217255
Meta
llama-3-70b-instruct
Meta · Llama 3 Community
1254±8
22,753$0.51 / $0.748.2K
242
216259
nvidia-nemotron-3-nano-30b-a3b-bf16
Nvidia · NVIDIA Open Model
1250±13
2,349$0.06 / $0.24262.1K
243
211261
gpt-5-nano-high
OpenAI · Proprietary
1248±20
915$0.05 / $0.40400K
244
207266
llama-3.1-tulu-3-70b
Ai2 · Llama 3.1
1247±25
441N/AN/A
245
216261
olmo-3.1-32b-think
Ai2 · Apache 2.0
1246±17
1,370$0.15 / $0.5065.5K
246
227259
Anthropic
claude-3-sonnet-20240229
Anthropic · Proprietary
1245±8
15,592$3 / $15200K
247
212267
ibm-granite-h-small
IBM · Apache 2.0
1244±24
715N/AN/A
248
219263
reka-flash-20240904
Reka AI · Proprietary
1242±18
1,037N/AN/A
249
224263
glm-4-0520
Z.ai · Proprietary
1241±15
1,547N/AN/A
250
223267
gpt-oss-20b
OpenAI · Apache 2.0
1238±18
1,242$0.03 / $0.14131.1K
251
230262
nemotron-4-340b-instruct
Nvidia · NVIDIA Open Model
1238±12
3,152N/AN/A
252
233261
gemini-1.5-flash-8b-001
Google · Proprietary
1238±9
5,031$0.07 / $0.301M
253
233261
amazon-nova-pro-v1.0
Amazon · Proprietary
1237±10
3,944$0.80 / $3.20300K
254
235261
Cohere
command-r-plus
Cohere · CC-BY-NC-4.0
1236±9
11,012$2.50 / $10128K
255
241269
Cohere
c4ai-aya-expanse-32b
Cohere · CC-BY-NC-4.0
1228±10
3,853N/AN/A
256
241271
mistral-small-24b-instruct-2501
Mistral · Apache 2.0
1227±12
2,415$0.05 / $0.0832.8K
257
232281
olmo-2-0325-32b-instruct
Ai2 · Apache-2.0
1224±25
567$0.05 / $0.20128K
258
244272
qwen2-72b-instruct
Alibaba · Qianwen LICENSE
1223±10
5,504$0.90 / $0.9032.8K
259
238281
ministral-8b-2410
Mistral · MRL
1221±22
678$0.10 / $0.10131.1K
260
244272
amazon-nova-lite-v1.0
Amazon · Proprietary
1221±11
3,037$0.06 / $0.24300K
261
221291
mercury
Inception AI · Proprietary
1220±39
298$0.25 / $0.75128K
262
252273
Anthropic
claude-3-haiku-20240307
Anthropic · Proprietary
1215±8
16,718$0.25 / $1.25200K
263
249285
jamba-1.5-mini
AI21 Labs · Jamba Open
1211±16
1,399$0.20 / $0.40256K
264
255280
mistral-large-2402
Mistral · Proprietary
1211±9
9,056$4 / $1232K
265
255280
phi-4
Microsoft · MIT
1210±10
4,062$0.07 / $0.1416.4K
266
252285
Cohere
command-r-08-2024
Cohere · CC-BY-NC-4.0
1209±16
1,421$0.15 / $0.60128K
267
250288
qwen2.5-coder-32b-instruct
Alibaba · Apache 2.0
1207±19
836$0.87 / $0.8732K
268
256287
deepseek-coder-v2
DeepSeek · DeepSeek License
1203±13
2,271$0.14 / $0.28128K
269
256288
gemini-pro-dev-api
Google · Proprietary
1202±14
3,046$0.35 / $1.0532.8K
270
259288
amazon-nova-micro-v1.0
Amazon · Proprietary
1198±11
3,061$0.04 / $0.14128K
271
257291
wizardlm-70b
Microsoft · Llama 2 Community
1198±17
1,779N/AN/A
272
253294
llama-3.1-tulu-3-8b
Ai2 · Llama 3.1
1197±25
472N/AN/A
273
260288
Meta
llama-3-8b-instruct
Meta · Llama 3 Community
1196±8
15,365$0.04 / $0.048.2K
274
260290
Cohere
command-r
Cohere · CC-BY-NC-4.0
1195±10
7,836$0.15 / $0.60128K
275
252299
Tencent
hunyuan-standard-256k
Tencent · Proprietary
1195±29
357N/AN/A
276
260291
mistral-medium
Mistral · Proprietary
1193±11
5,549$2.70 / $8.1032K
277
260291
qwen1.5-110b-chat
Alibaba · Qianwen LICENSE
1193±12
3,677N/AN/A
278
262291
mixtral-8x22b-instruct-v0.1
Mistral · Apache 2.0
1190±9
7,447$0.90 / $0.9065.5K
279
260294
Cohere
c4ai-aya-expanse-8b
Cohere · CC-BY-NC-4.0
1189±15
1,528N/AN/A
280
264291
gpt-3.5-turbo-0125
OpenAI · Proprietary
1188±9
9,694$0.50 / $1.5016.4K
281
264292
qwen1.5-72b-chat
Alibaba · Qianwen LICENSE
1188±10
5,888N/AN/A
282
260299
openchat-3.5
OpenChat · Apache-2.0
1184±18
1,454$0.20 / $0.20N/A
283
260302
gemini-pro
Google · Proprietary
1183±21
953$0.35 / $1.0532.8K
284
266293
gemma-2-2b-it
Google · Gemma license
1183±8
7,094N/AN/A
285
264299
reka-flash-21b-20240226-online
Reka AI · Proprietary
1181±15
2,119N/AN/A
286
271295
Meta
llama-3.1-8b-instruct
Meta · Llama 3.1 Community
1177±8
7,346$0.02 / $0.05131.1K
287
271302
reka-flash-21b-20240226
Reka AI · Proprietary
1174±12
3,490N/AN/A
288
272306
vicuna-33b
LMSYS · Non-commercial
1172±12
4,010$0 / $02K
289
264318
granite-3.1-8b-instruct
IBM · Apache 2.0
1170±27
450N/AN/A
290
266318
zephyr-orpo-141b-A35b-v0.1
HuggingFace · Apache 2.0
1168±23
635N/AN/A
291
279314
dbrx-instruct-preview
Databricks · DBRX LICENSE
1163±12
4,808$0.60 / $0.6032.8K
292
282315
01.AI
yi-1.5-34b-chat
01 AI · Apache-2.0
1159±11
3,602N/AN/A
293
283315
mixtral-8x7b-instruct-v0.1
Mistral · Apache 2.0
1159±9
11,172$0.63 / $0.6332K
294
278321
openhermes-2.5-mistral-7b
NousResearch · Apache-2.0
1157±22
811$0.17 / $0.17N/A
295
283319
01.AI
yi-34b-chat
01 AI · Yi License
1154±14
2,379$0.90 / $0.904.1K
296
283320
gpt-3.5-turbo-1106
OpenAI · Proprietary
1153±15
2,828$1 / $216.4K
297
267328
falcon-180b-chat
TII · Falcon-180B TII License
1153±37
270N/AN/A
298
288319
phi-3-medium-4k-instruct
Microsoft · MIT
1150±11
3,735$0.17 / $0.68N/A
299
289321
gemma-1.1-7b-it
Google · Gemma license
1147±12
3,409$0.03 / $0.098.2K
300
279326
granite-3.1-2b-instruct
IBM · Apache 2.0
1147±29
442N/AN/A
301
288321
openchat-3.5-0106
OpenChat · Apache-2.0
1146±15
1,858N/AN/A
302
286322
tulu-2-dpo-70b
AllenAI/UW · AI2 ImpACT Low-risk
1146±19
1,126N/AN/A
303
286322
Meta
llama-3.2-3b-instruct
Meta · Llama 3.2
1144±20
1,070$0.05 / $0.34131.1K
304
289322
snowflake-arctic-instruct
Snowflake · Apache 2.0
1142±12
4,777N/AN/A
305
289323
wizardlm-13b
Microsoft · Llama 2 Community
1140±18
1,375$0.30 / $0.30N/A
306
288328
solar-10.7b-instruct-v1.0
Upstage AI · CC-BY-NC-4.0
1138±24
698$0.30 / $0.30N/A
307
290323
qwen1.5-14b-chat
Alibaba · Qianwen LICENSE
1137±14
2,391$0.30 / $0.30N/A
308
289326
zephyr-7b-beta
HuggingFace · MIT
1136±16
1,993$0.15 / $0.1516.4K
309
289326
starling-lm-7b-alpha
UC Berkeley · CC-BY-NC-4.0
1136±16
1,701N/AN/A
310
289328
granite-3.0-8b-instruct
IBM · Apache 2.0
1136±21
895N/AN/A
311
289330
nous-hermes-2-mixtral-8x7b-dpo
NousResearch · Apache-2.0
1135±23
616$0.90 / $0.90N/A
312
286334
guanaco-33b
UW · Non-commercial
1135±28
515N/AN/A
313
289330
deepseek-llm-67b-chat
DeepSeek · DeepSeek License
1134±22
789N/AN/A
314
283340
dolphin-2.2.1-mistral-7b
Cognitive Computations · Apache-2.0
1134±33
291$0.50 / $0.5016.4K
315
292326
phi-3-small-8k-instruct
Microsoft · MIT
1133±13
2,400$0.15 / $0.60N/A
316
288340
mpt-30b-chat
MosaicML · CC-BY-NC-SA-4.0
1132±29
452N/AN/A
317
292328
internlm2_5-20b-chat
InternLM · Other
1131±16
1,432$0 / $032.8K
318
294326
qwen1.5-32b-chat
Alibaba · Qianwen LICENSE
1131±13
3,022N/AN/A
319
296329
vicuna-13b
LMSYS · Llama 2 Community
1125±13
3,346$0.30 / $0.30N/A
320
292343
llama2-70b-steerlm-chat
Nvidia · Llama 2 Community
1120±25
604N/AN/A
321
305340
Meta
llama-2-70b-chat
Meta · Llama 2 Community
1112±10
6,376$0.70 / $2.804.1K
322
303343
starling-lm-7b-beta
Nexusflow · Apache-2.0
1108±15
2,376N/AN/A
323
297345
qwq-32b-preview
Alibaba · Apache 2.0
1107±29
454$0.50 / $116.4K
324
310343
mistral-7b-instruct-v0.2
Mistral · Apache-2.0
1104±13
2,952$0.20 / $0.2032.8K
325
305345
qwen-14b-chat
Alibaba · Qianwen LICENSE
1101±21
898N/AN/A
326
300346
zephyr-7b-alpha
HuggingFace · MIT
1101±30
399N/AN/A
327
310345
gemma-7b-it
Google · Gemma license
1100±18
1,345$0.05 / $0.088.2K
328
305345
granite-3.0-2b-instruct
IBM · Apache 2.0
1099±22
916N/AN/A
329
317345
phi-3-mini-4k-instruct-june-2024
Microsoft · MIT
1096±15
1,955$0.13 / $0.524.1K
330
317346
gemma-1.1-2b-it
Google · Gemma license
1092±17
1,486N/AN/A
331
318345
Meta
llama-2-13b-chat
Meta · Llama 2 Community
1091±13
3,296$0.25 / $0.254.1K
332
317346
mistral-7b-instruct
Mistral · Apache 2.0
1091±17
1,689$0.07 / $0.284.1K
333
315346
alpaca-13b
Stanford · Non-commercial
1090±22
954N/AN/A
334
318346
vicuna-7b
LMSYS · Llama 2 Community
1089±18
1,323$0.20 / $0.20N/A
335
317346
stripedhyena-nous-7b
Together AI · Apache 2.0
1089±21
869$0.20 / $0.20N/A
336
318346
palm-2
Google · Proprietary
1087±18
1,576$0.50 / $0.5025.8K
337
318346
Meta
codellama-34b-instruct
Meta · Llama 2 Community
1086±17
1,507$0.35 / $1.4016.4K
338
321346
phi-3-mini-128k-instruct
Microsoft · MIT
1085±14
2,949$0.13 / $0.52N/A
339
318349
Meta
llama-3.2-1b-instruct
Meta · Llama 3.2
1082±21
1,091$0.03 / $0.20131.1K
340
318349
qwen1.5-7b-chat
Alibaba · Qianwen LICENSE
1081±23
701$0.20 / $0.20N/A
341
314349
smollm2-1.7b-instruct
HuggingFace · Apache 2.0
1079±35
341N/AN/A
342
321349
gemma-2b-it
Google · Gemma license
1077±23
696$0.10 / $0.10N/A
343
324349
phi-3-mini-4k-instruct
Microsoft · MIT
1073±13
2,812$0.13 / $0.52N/A
344
324349
Meta
llama-2-7b-chat
Meta · Llama 2 Community
1072±14
2,341$0.15 / $0.154.1K
345
321352
gpt4all-13b-snoozy
Nomic AI · Non-commercial
1062±38
250N/AN/A
346
330351
mpt-7b-chat
MosaicML · CC-BY-NC-SA-4.0
1051±24
683N/AN/A
347
339350
qwen1.5-4b-chat
Alibaba · Qianwen LICENSE
1049±19
1,080$0.10 / $0.10N/A
348
339352
koala-13b
UC Berkeley · Non-commercial
1045±21
1,200N/AN/A
349
339353
chatglm3-6b
Tsinghua · Apache-2.0
1039±23
816N/AN/A
350
345355
oasst-pythia-12b
OpenAssistant · Apache 2.0
1011±21
1,094N/AN/A
351
346355
chatglm2-6b
Tsinghua · Apache-2.0
1003±26
566N/AN/A
352
347355
RWKV-4-Raven-14B
RWKV · Apache 2.0
1003±23
874N/AN/A
353
349355
olmo-7b-instruct
Ai2 · Apache-2.0
1003±20
1,019$0.20 / $0.20N/A
354
350356
fastchat-t5-3b
LMSYS · Apache 2.0
991±24
744N/AN/A
355
350358
dolly-v2-12b
Databricks · MIT
968±28
565N/AN/A
356
354358
chatglm-6b
Tsinghua · Non-commercial
951±25
771N/AN/A
357
355358
Meta
llama-13b
Meta · Non-commercial
932±34
431$0.23 / $0.23N/A
358
355358
Stability
stablelm-tuned-alpha-7b
Stability AI · CC-BY-NC-SA-4.0
931±29
536N/AN/A

Default Leaderboard Plots

Confidence Intervals on Model Strength (via Bootstrapping)

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

Battle Count for Each Combination of Models (without Ties)

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