Text Arena🌶️Hard Prompts

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

Apr 19, 2026
2,221,778 votes
342 models
Rank Spread
1
14
Anthropic
claude-opus-4-6-thinking
Anthropic · Proprietary
1535±6
10,469$5 / $251M
2
14
Anthropic
claude-opus-4-6
Anthropic · Proprietary
1530±6
11,385$5 / $251M
3
16
Anthropic
claude-opus-4-7-thinking
Anthropic · Proprietary
1527±12
2,311$5 / $251M
4
18
Anthropic
claude-opus-4-7
Anthropic · Proprietary
1520±11
2,867$5 / $251M
5
38
gemini-3.1-pro-preview
Google · Proprietary
1515±6
13,488$2 / $121M
6
314
Meta
muse-spark
Meta · Proprietary
1510±10
3,370N/AN/A
7
418
gpt-5.4-high
OpenAI · Proprietary
1505±8
6,986$2.50 / $151.1M
8
415
gemini-3-pro
Google · Proprietary
1505±5
22,484$2 / $121M
9
619
Anthropic
claude-opus-4-5-20251101-thinking-32k
Anthropic · Proprietary
1500±5
19,807$5 / $25200K
10
619
grok-4.20-beta-0309-reasoning
xAI · Proprietary
1500±7
7,151$2 / $62M
11
620
Anthropic
claude-sonnet-4-6
Anthropic · Proprietary
1499±8
6,773$3 / $151M
12
620
gpt-5.2-chat-latest-20260210
OpenAI · Proprietary
1498±6
10,666$1.75 / $14128K
13
620
grok-4.20-beta1
xAI · Proprietary
1497±7
7,015N/AN/A
14
619
Anthropic
claude-opus-4-5-20251101
Anthropic · Proprietary
1497±5
27,185$5 / $25200K
15
822
gemini-3-flash
Google · Proprietary
1493±6
16,600$0.50 / $31M
16
728
qwen3.5-max-preview
Alibaba · Proprietary
1492±8
5,863N/AN/A
17
828
gpt-5.4
OpenAI · Proprietary
1491±7
7,426$2.50 / $151.1M
18
831
glm-5.1
Z.ai · MIT
1489±9
4,566$1.05 / $3.50202.8K
19
931
grok-4.20-multi-agent-beta-0309
xAI · Proprietary
1488±7
7,341$2 / $62M
20
1231
Bytedance
dola-seed-2.0-pro
Bytedance · Proprietary
1486±6
12,256N/AN/A
21
1531
Anthropic
claude-sonnet-4-5-20250929-thinking-32k
Anthropic · Proprietary
1485±4
33,425$3 / $15200K
22
1536
gpt-5.4-mini-high
OpenAI · Proprietary
1481±8
5,715$2.50 / $151.1M
23
1635
Anthropic
claude-sonnet-4-5-20250929
Anthropic · Proprietary
1481±4
32,650$3 / $15200K
24
1636
grok-4.1-thinking
xAI · Proprietary
1481±5
26,814N/AN/A
25
1636
Anthropic
claude-opus-4-1-20250805-thinking-16k
Anthropic · Proprietary
1480±5
24,746$15 / $75200K
26
1636
gemini-3-flash (thinking-minimal)
Google · Proprietary
1480±5
20,315$0.50 / $31M
27
1639
glm-5
Z.ai · MIT
1478±6
9,371$1 / $3.20202.8K
28
1836
Anthropic
claude-opus-4-1-20250805
Anthropic · Proprietary
1478±4
38,954$15 / $75200K
29
1842
gpt-5.3-chat-latest
OpenAI · Proprietary
1477±7
9,788$1.75 / $14128K
30
1843
mimo-v2-pro
Xiaomi · Proprietary
1475±8
6,270$1 / $31M
31
2240
grok-4.1
xAI · Proprietary
1475±5
28,914N/AN/A
32
2243
gpt-5.1-high
OpenAI · Proprietary
1474±5
21,764$1.25 / $10400K
33
1646
gemma-4-31b
Google · Apache 2.0
1474±10
3,308$0.14 / $0.40262.1K
34
2243
kimi-k2.5-thinking
Moonshot · Modified MIT
1474±6
12,869$0.60 / $3N/A
35
2345
ernie-5.0-0110
Baidu · Proprietary
1471±6
13,746N/AN/A
36
2255
qwen3.6-plus
Alibaba · Proprietary
1466±11
2,476$0.33 / $1.951M
37
2951
gpt-5.2
OpenAI · Proprietary
1465±5
16,839$1.75 / $14400K
38
3152
gpt-5.2-high
OpenAI · Proprietary
1465±5
18,332$1.75 / $14400K
39
3052
qwen3.5-397b-a17b
Alibaba · Apache 2.0
1464±6
10,168$0.39 / $2.34262.1K
40
2855
ernie-5.0-preview-1203
Baidu · Proprietary
1464±8
5,216N/AN/A
41
2854
glm-4.7
Z.ai · MIT
1464±8
6,604$0.38 / $1.74202.8K
42
2860
gemma-4-26b-a4b
Google · Apache 2.0
1462±10
3,240N/AN/A
43
2958
kimi-k2.5-instant
Moonshot · Modified MIT
1462±9
4,544$0.44 / $2262.1K
44
3553
gemini-2.5-pro
Google · Proprietary
1460±3
54,381$1.25 / $101M
45
3458
qwen3-max-preview
Alibaba · Proprietary
1459±6
13,581$0.78 / $3.90262.1K
46
3464
longcat-flash-chat-2602-exp
Meituan · Proprietary
1457±9
4,884N/AN/A
47
3658
chatgpt-4o-latest-20250326
OpenAI · Proprietary
1456±4
38,369$5 / $15128K
48
3661
gpt-5.1
OpenAI · Proprietary
1456±5
23,600$1.25 / $10400K
49
3663
Anthropic
claude-opus-4-20250514-thinking-16k
Anthropic · Proprietary
1455±6
16,412$15 / $75200K
50
3964
kimi-k2-thinking-turbo
Moonshot · Modified MIT
1452±5
26,296$1.15 / $8262.1K
51
3678
amazon-nova-experimental-chat-26-02-10
Amazon · Proprietary
1451±13
1,938N/AN/A
52
4667
qwen3-235b-a22b-instruct-2507
Alibaba · Apache 2.0
1449±4
43,145$0.26 / $1.06N/A
53
4370
gpt-5-chat
OpenAI · Proprietary
1448±6
15,226$1.25 / $10128K
54
4074
qwen3-max-2025-09-23
Alibaba · Proprietary
1448±8
4,885$0.78 / $3.90262.1K
55
4370
gemini-3.1-flash-lite-preview
Google · Proprietary
1448±6
10,686$0.25 / $1.501M
56
4175
deepseek-v3.2-exp
DeepSeek · MIT
1448±8
6,475$0.27 / $0.41163.8K
57
3685
amazon-nova-experimental-chat-26-01-10
Amazon · Proprietary
1447±13
1,861N/AN/A
58
4670
deepseek-v3.2
DeepSeek · MIT
1447±5
23,342$0.25 / $0.38131.1K
59
4378
deepseek-v3.2-exp-thinking
DeepSeek · MIT
1446±9
4,699$0.27 / $0.41163.8K
60
4774
gpt-5-high
OpenAI · Proprietary
1446±6
15,004$1.25 / $10400K
61
4873
deepseek-v3.2-thinking
DeepSeek · MIT
1445±5
20,102$0.25 / $0.38131.1K
62
3689
deepseek-v3.1-terminus-thinking
DeepSeek · MIT
1445±14
1,680$0.21 / $0.79163.8K
63
5178
glm-4.6
Z.ai · MIT
1443±5
19,117$0.39 / $1.90204.8K
64
5179
grok-4-1-fast-reasoning
xAI · Proprietary
1442±5
24,607$0.20 / $0.502M
65
4988
qwen3-vl-235b-a22b-instruct
Alibaba · Apache 2.0
1441±9
5,730$0.20 / $0.88262.1K
66
4889
gpt-4.5-preview-2025-02-27
OpenAI · Proprietary
1441±10
3,445$75 / $150128K
67
5285
o3-2025-04-16
OpenAI · Proprietary
1440±5
25,760$2 / $8200K
68
5189
deepseek-v3.1-thinking
DeepSeek · MIT
1437±9
5,155$1.23 / $4.94N/A
69
5588
Anthropic
claude-haiku-4-5-20251001
Anthropic · Proprietary
1437±4
33,600$1 / $5200K
70
5291
kimi-k2-0905-preview
Moonshot · Modified MIT
1436±8
5,590$0.60 / $2.50262.1K
71
5689
Anthropic
claude-opus-4-20250514
Anthropic · Proprietary
1435±5
19,185$15 / $75200K
72
5597
deepseek-r1-0528
DeepSeek · MIT
1433±8
6,958$0.50 / $2.15163.8K
73
52102
grok-4-fast-chat
xAI · Proprietary
1433±11
3,164$3 / $15256K
74
5598
deepseek-v3.1
DeepSeek · MIT
1433±8
6,814$1.23 / $4.94N/A
75
5996
glm-4.5
Z.ai · MIT
1433±6
11,213$0.60 / $2.20131.1K
76
5896
qwen3.5-122b-a10b
Alibaba · Apache 2.0
1433±7
8,279$0.26 / $2.08262.1K
77
6393
mistral-large-3
Mistral · Apache 2.0
1432±5
22,260$0.50 / $1.50N/A
78
6299
kimi-k2-0711-preview
Moonshot · Modified MIT
1431±6
12,219$0.60 / $2.50131.1K
79
6397
gpt-4.1-2025-04-14
OpenAI · Proprietary
1431±5
22,194$2 / $81M
80
6399
Anthropic
claude-sonnet-4-20250514-thinking-32k
Anthropic · Proprietary
1431±6
15,635$3 / $151M
81
6597
mistral-medium-2508
Mistral · Proprietary
1429±4
41,658$2.70 / $8.1032K
82
63105
minimax-m2.7
MiniMax · Modified MIT
1428±8
5,258$0.30 / $1.20196.6K
83
59108
ernie-5.0-preview-1022
Baidu · Proprietary
1428±11
2,547N/AN/A
84
65104
minimax-m2.5
MiniMax · Modified MIT
1427±6
11,163$0.15 / $1.20196.6K
85
63106
longcat-flash-chat
Meituan · MIT
1427±8
5,590$0.20 / $0.80131.1K
86
65105
grok-3-preview-02-24
xAI · Proprietary
1426±6
10,698$3 / $15131.1K
87
63114
deepseek-v3.1-terminus
DeepSeek · MIT
1424±13
1,933$0.21 / $0.79163.8K
88
59120
Tencent
hunyuan-vision-1.5-thinking
Tencent · Proprietary
1422±17
1,092N/AN/A
89
73109
qwen3-235b-a22b-no-thinking
Alibaba · Apache 2.0
1421±6
16,585$0.46 / $1.82131.1K
90
73110
qwen3-next-80b-a3b-instruct
Alibaba · Apache 2.0
1421±6
11,912$0.09 / $1.10262.1K
91
72111
qwen3.5-27b
Alibaba · Apache 2.0
1421±7
8,116$0.20 / $1.56262.1K
92
75110
gemini-2.5-flash-preview-09-2025
Google · Proprietary
1421±5
17,510$0.30 / $2.501M
93
78110
grok-4-0709
xAI · Proprietary
1420±5
19,662$3 / $15256K
94
81109
gemini-2.5-flash
Google · Proprietary
1420±3
53,445$0.30 / $2.501M
95
71114
gpt-5.4-nano-high
OpenAI · Proprietary
1420±8
5,290$2.50 / $151.1M
96
71116
qwen3-vl-235b-a22b-thinking
Alibaba · Apache 2.0
1419±9
4,051$0.26 / $2.60131.1K
97
67120
amazon-nova-experimental-chat-12-10
Amazon · Proprietary
1418±13
1,861N/AN/A
98
73116
deepseek-r1
DeepSeek · MIT
1418±9
4,116$0.70 / $2.5064K
99
72116
qwen3-235b-a22b-thinking-2507
Alibaba · Apache 2.0
1418±9
3,849$0.13 / $0.60262.1K
100
78116
o1-2024-12-17
OpenAI · Proprietary
1418±8
6,453$15 / $60200K
101
81113
Anthropic
claude-sonnet-4-20250514
Anthropic · Proprietary
1417±6
17,688$3 / $151M
102
81116
qwen3.5-flash
Alibaba · Proprietary
1417±7
8,602N/AN/A
103
82116
Anthropic
claude-3-7-sonnet-20250219-thinking-32k
Anthropic · Proprietary
1416±6
13,860$3 / $15200K
104
83120
qwen3-coder-480b-a35b-instruct
Alibaba · Apache 2.0
1414±6
11,654$0.40 / $1.60262.1K
105
82120
mimo-v2-flash (thinking)
Xiaomi · MIT
1414±8
6,006$0.09 / $0.29262.1K
106
86119
mimo-v2-flash (non-thinking)
Xiaomi · MIT
1413±5
18,089$0.09 / $0.29262.1K
107
85120
grok-4-fast-reasoning
xAI · Proprietary
1413±6
9,921$0.20 / $0.502M
108
86120
qwen3.5-35b-a3b
Alibaba · Apache 2.0
1412±7
8,519$0.16 / $1.30262.1K
109
87120
Stepfun
step-3.5-flash
StepFun · Apache 2.0
1411±6
11,557$0.10 / $0.30262.1K
110
89122
minimax-m2.1-preview
MiniMax · MIT
1409±7
9,076$0.29 / $0.95196.6K
111
93121
deepseek-v3-0324
DeepSeek · MIT
1408±5
18,717$3 / $4.5032.8K
112
92122
qwen3-30b-a3b-instruct-2507
Alibaba · Apache 2.0
1408±6
11,083$0.09 / $0.30262.1K
113
96124
o4-mini-2025-04-16
OpenAI · Proprietary
1405±5
19,534$1.10 / $4.40200K
114
94127
mai-1-preview
Microsoft AI · Proprietary
1405±7
7,996N/AN/A
115
102128
gpt-5-mini-high
OpenAI · Proprietary
1402±6
12,819$0.25 / $2400K
116
102128
gpt-4.1-mini-2025-04-14
OpenAI · Proprietary
1402±6
16,259$0.40 / $1.601M
117
102131
trinity-large-preview
Arcee AI · Apache 2.0
1402±7
8,815N/AN/A
118
103129
mistral-medium-2505
Mistral · Proprietary
1401±6
13,748$0.40 / $2131.1K
119
96131
o3-mini-high
OpenAI · Proprietary
1401±9
4,386$1.10 / $4.40200K
120
93139
Tencent
hunyuan-t1-20250711
Tencent · Proprietary
1399±13
1,976N/AN/A
121
111132
Anthropic
claude-3-7-sonnet-20250219
Anthropic · Proprietary
1397±6
15,281$3 / $15200K
122
113131
Anthropic
claude-3-5-sonnet-20241022
Anthropic · Proprietary
1397±4
27,300$3 / $15200K
123
110135
o1-preview
OpenAI · Proprietary
1396±8
8,496$15 / $60N/A
124
114135
amazon-nova-experimental-chat-11-10
Amazon · Proprietary
1394±6
13,662N/AN/A
125
114139
qwen3-235b-a22b
Alibaba · Apache 2.0
1392±6
10,498$0.46 / $1.82131.1K
126
113144
Tencent
hunyuan-turbos-20250416
Tencent · Proprietary
1391±10
3,916N/AN/A
127
115139
glm-4.5-air
Z.ai · MIT
1391±6
14,897$0.13 / $0.85131.1K
128
118139
gemini-2.5-flash-lite-preview-09-2025-no-thinking
Google · Proprietary
1391±5
25,081$0.10 / $0.401M
129
118145
glm-4.7-flash
Z.ai · MIT
1387±8
6,531$0.06 / $0.40202.8K
130
122145
qwen2.5-max
Alibaba · Proprietary
1385±6
9,678N/AN/A
131
121146
qwen3-next-80b-a3b-thinking
Alibaba · Apache 2.0
1385±8
6,695$0.10 / $0.78131.1K
132
114156
glm-4.6v
Z.ai · MIT
1384±15
1,494$0.30 / $0.90131.1K
133
124149
gemini-2.5-flash-lite-preview-06-17-thinking
Google · Proprietary
1381±6
14,587$0.10 / $0.401M
134
124149
minimax-m1
MiniMax · Apache 2.0
1381±5
15,842$0.40 / $2.201M
135
122154
nvidia-nemotron-3-super-120b-a12b
Nvidia · NVIDIA Open Model
1381±9
4,035N/AN/A
136
124159
Stepfun
step-3
StepFun · Apache 2.0
1378±11
3,013$0.57 / $1.4265.5K
137
128155
grok-3-mini-high
xAI · Proprietary
1377±7
7,574$0.30 / $0.50131.1K
138
124162
glm-4.5v
Z.ai · MIT
1376±12
2,398$0.60 / $1.8065.5K
139
128157
mistral-small-2506
Mistral · Apache 2.0
1375±7
7,822$0.10 / $0.3032K
140
117170
llama-3.1-nemotron-ultra-253b-v1
Nvidia · Nvidia Open Model
1374±21
713$0.60 / $1.80131.1K
141
128164
intellect-3
Prime Intellect · MIT
1374±11
2,742$0.20 / $1.10131.1K
142
129161
amazon-nova-experimental-chat-10-20
Amazon · Proprietary
1373±8
5,958N/AN/A
143
134161
o3-mini
OpenAI · Proprietary
1370±5
20,114$1.10 / $4.40200K
144
132164
grok-3-mini-beta
xAI · Proprietary
1370±7
9,629$0.30 / $0.50131.1K
145
131166
minimax-m2
MiniMax · Apache 2.0
1369±10
3,702$0.26 / $1196.6K
146
134164
Cohere
command-a-03-2025
Cohere · CC-BY-NC-4.0
1368±5
23,806$2.50 / $10256K
147
122177
Tencent
hunyuan-turbos-20250226
Tencent · Proprietary
1368±23
531N/AN/A
148
128171
qwen3-32b
Alibaba · Apache 2.0
1368±16
1,207$0.08 / $0.2441K
149
132167
ling-flash-2.0
Ant Group · MIT
1366±10
3,450N/AN/A
150
135165
gemma-3-27b-it
Google · Gemma
1365±5
17,880$0.08 / $0.16131.1K
151
137167
gpt-oss-120b
OpenAI · Apache 2.0
1363±6
14,774$0.04 / $0.19131.1K
152
128188
llama-3.3-nemotron-49b-super-v1
Nvidia · Nvidia
1361±24
510N/AN/A
153
132177
nvidia-llama-3.3-nemotron-super-49b-v1.5
Nvidia · Nvidia Open
1361±15
1,438$0.10 / $0.40131.1K
154
139169
o1-mini
OpenAI · Proprietary
1361±6
13,899$1.10 / $4.40N/A
155
139169
gemini-2.0-flash-001
Google · Proprietary
1361±5
14,138$0.10 / $0.401M
156
138171
nova-2-lite
Amazon · Proprietary
1360±8
6,487$0.30 / $2.501M
157
141170
Anthropic
claude-3-5-sonnet-20240620
Anthropic · Proprietary
1359±6
23,249$3 / $15200K
158
134177
mercury-2
Inception AI · Proprietary
1359±14
1,756$0.25 / $0.75128K
159
134179
amazon-nova-experimental-chat-10-09
Amazon · Proprietary
1358±15
1,419N/AN/A
160
142171
qwq-32b
Alibaba · Apache 2.0
1357±6
8,826$0.15 / $0.58131.1K
161
142178
gpt-5-nano-high
OpenAI · Proprietary
1354±10
3,820$0.05 / $0.40400K
162
138186
qwen-plus-0125
Alibaba · Proprietary
1353±14
1,481$0.40 / $1.20131.1K
163
146179
olmo-3.1-32b-instruct
Ai2 · Apache 2.0
1351±8
6,455$0.20 / $0.6065.5K
164
145182
ring-flash-2.0
Ant Group · MIT
1351±10
3,578N/AN/A
165
149177
gemini-1.5-pro-002
Google · Proprietary
1351±6
14,853$3.50 / $10.502.1M
166
147180
deepseek-v3
DeepSeek · DeepSeek
1350±8
5,408$1.14 / $4.56N/A
167
134201
Tencent
hunyuan-turbo-0110
Tencent · Proprietary
1349±23
496N/AN/A
168
149182
gemini-2.0-flash-lite-preview-02-05
Google · Proprietary
1348±7
6,186$0.07 / $0.301M
169
153185
qwen3-30b-a3b
Alibaba · Apache 2.0
1346±6
10,701$0.08 / $0.2841K
170
156185
Anthropic
claude-3-5-haiku-20241022
Anthropic · Proprietary
1343±5
23,782$0.80 / $4200K
171
136214
molmo-2-8b
Ai2 · Apache 2.0
1341±28
438$0.20 / $0.2036.9K
172
156190
01.AI
yi-lightning
01 AI · Proprietary
1341±8
6,961N/AN/A
173
156190
Meta
llama-3.1-405b-instruct-bf16
Meta · Llama 3.1 Community
1340±6
10,652$4 / $432.8K
174
151204
Stepfun
step-2-16k-exp-202412
StepFun · Proprietary
1339±15
1,221N/AN/A
175
160192
Meta
llama-4-maverick-17b-128e-instruct
Meta · Llama 4
1338±6
15,999$0.63 / $1.80131.1K
176
163194
gpt-4o-2024-05-13
OpenAI · Proprietary
1337±5
32,416$5 / $15128K
177
164197
Meta
llama-3.1-405b-instruct-fp8
Meta · Llama 3.1 Community
1335±6
16,228$4 / $432.8K
178
161204
Stepfun
step-1o-turbo-202506
StepFun · Proprietary
1334±10
3,707N/AN/A
179
166200
athene-v2-chat
NexusFlow · NexusFlow
1333±7
6,517N/AN/A
180
156209
gpt-4.1-nano-2025-04-14
OpenAI · Proprietary
1333±14
1,669$0.10 / $0.401M
181
156214
gemma-3-12b-it
Google · Gemma
1332±18
977$0.04 / $0.13131.1K
182
166204
magistral-medium-2506
Mistral · Proprietary
1332±8
5,663$2 / $540K
183
156217
Tencent
hunyuan-large-2025-02-10
Tencent · Proprietary
1330±19
889N/AN/A
184
170204
Meta
llama-4-scout-17b-16e-instruct
Meta · Llama
1329±6
13,001$0.40 / $0.708.2K
185
164214
deepseek-v2.5-1210
DeepSeek · DeepSeek
1329±13
1,790N/AN/A
186
170206
nvidia-nemotron-3-nano-30b-a3b-bf16
Nvidia · NVIDIA Open Model
1329±7
8,162$0.06 / $0.24262.1K
187
168211
olmo-3-32b-think
Ai2 · Apache 2.0
1328±11
3,037$0.15 / $0.5065.5K
188
173205
Anthropic
claude-3-opus-20240229
Anthropic · Proprietary
1327±5
55,074$15 / $75200K
189
172207
gemini-1.5-pro-001
Google · Proprietary
1327±6
22,512$3.50 / $10.502.1M
190
172207
gpt-4o-2024-08-06
OpenAI · Proprietary
1326±6
12,655$2.50 / $10128K
191
169213
qwen2.5-plus-1127
Alibaba · Proprietary
1326±11
2,671N/AN/A
192
174207
grok-2-2024-08-13
xAI · Proprietary
1326±6
17,283$2 / $10131.1K
193
166217
glm-4-plus-0111
Zhipu · Proprietary
1325±14
1,468N/AN/A
194
173209
gemini-advanced-0514
Google · Proprietary
1325±7
14,100N/AN/A
195
174214
gpt-oss-20b
OpenAI · Apache 2.0
1323±9
4,800$0.03 / $0.14131.1K
196
175214
deepseek-v2.5
DeepSeek · DeepSeek
1321±8
6,869N/AN/A
197
177214
Meta
llama-3.3-70b-instruct
Meta · Llama-3.3
1320±5
17,023$0.12 / $0.38131.1K
198
169221
mercury
Inception AI · Proprietary
1320±19
1,034$0.25 / $0.75128K
199
176214
mistral-large-2407
Mistral · Mistral Research
1319±6
12,682$2 / $6131.1K
200
175217
glm-4-plus
Zhipu AI · Proprietary
1319±8
7,067$0.44 / $1.76204.8K
201
177214
mistral-small-3.1-24b-instruct-2503
Mistral · Apache 2.0
1319±6
14,709$0.10 / $0.3032K
202
175220
qwen-max-0919
Alibaba · Qwen
1318±9
4,447$1.60 / $6.4032.8K
203
177217
qwen2.5-72b-instruct
Alibaba · Qwen
1317±6
10,545$1.20 / $1.20N/A
204
182217
gpt-4-turbo-2024-04-09
OpenAI · Proprietary
1316±6
28,310$10 / $30128K
205
186220
mistral-large-2411
Mistral · MRL
1313±7
6,954$2 / $6131.1K
206
186220
gemma-3n-e4b-it
Google · Gemma
1313±7
8,565$0.06 / $0.1232.8K
207
183221
athene-70b-0725
NexusFlow · CC-BY-NC-4.0
1312±9
5,448N/AN/A
208
189220
gpt-4o-mini-2024-07-18
OpenAI · Proprietary
1311±5
18,259$0.15 / $0.60128K
209
188220
gpt-4-1106-preview
OpenAI · Proprietary
1311±6
26,242$10 / $30128K
210
174228
Tencent
hunyuan-standard-2025-02-10
Tencent · Proprietary
1311±19
873N/AN/A
211
181223
llama-3.1-nemotron-70b-instruct
Nvidia · Llama 3.1
1310±13
1,953$1.20 / $1.20131.1K
212
198222
gpt-4-0125-preview
OpenAI · Proprietary
1306±6
25,575$10 / $30128K
213
190224
olmo-3.1-32b-think
Ai2 · Apache 2.0
1306±10
4,378$0.15 / $0.5065.5K
214
202222
grok-2-mini-2024-08-13
xAI · Proprietary
1304±6
14,208$2 / $10131.1K
215
198224
gpt-4-0314
OpenAI · Proprietary
1304±8
13,935$30 / $608.2K
216
189231
Tencent
hunyuan-large-vision
Tencent · Proprietary
1303±13
2,172N/AN/A
217
188233
qwen2.5-coder-32b-instruct
Alibaba · Apache 2.0
1303±15
1,386$0.87 / $0.8732K
218
203224
gemini-1.5-flash-002
Google · Proprietary
1303±7
9,262$0.07 / $0.301M
219
203224
amazon-nova-pro-v1.0
Amazon · Proprietary
1302±7
6,300$0.80 / $3.20300K
220
198231
ibm-granite-h-small
IBM · Apache 2.0
1300±11
2,992N/AN/A
221
208228
Meta
llama-3.1-70b-instruct
Meta · Llama 3.1 Community
1298±6
14,981$0.40 / $0.40131.1K
222
217238
gemini-1.5-flash-001
Google · Proprietary
1288±6
18,228$0.07 / $0.301M
223
213242
deepseek-coder-v2
DeepSeek · DeepSeek License
1287±10
4,439$0.14 / $0.28128K
224
217238
gpt-4-0613
OpenAI · Proprietary
1287±7
23,040$30 / $608.2K
225
217243
mistral-small-24b-instruct-2501
Mistral · Apache 2.0
1284±10
3,569$0.05 / $0.0832.8K
226
210246
gemma-3-4b-it
Google · Gemma
1284±17
1,092$0.04 / $0.08131.1K
227
216243
jamba-1.5-large
AI21 Labs · Jamba Open
1283±12
2,372$2 / $8256K
228
222243
gemma-2-27b-it
Google · Gemma license
1281±5
20,494$0.65 / $0.658.2K
229
222243
Anthropic
claude-3-sonnet-20240229
Anthropic · Proprietary
1281±6
30,725$3 / $15200K
230
212249
llama-3.1-nemotron-51b-instruct
Nvidia · Llama 3.1
1280±17
1,002N/AN/A
231
219245
reka-core-20240904
Reka AI · Proprietary
1280±12
2,145N/AN/A
232
221243
nemotron-4-340b-instruct
Nvidia · NVIDIA Open Model
1280±9
5,577N/AN/A
233
222243
Meta
llama-3-70b-instruct
Meta · Llama 3 Community
1278±6
45,956$0.51 / $0.748.2K
234
222244
phi-4
Microsoft · MIT
1277±8
5,747$0.07 / $0.1416.4K
235
221246
glm-4-0520
Zhipu AI · Proprietary
1277±11
2,970N/AN/A
236
219251
llama-3.1-tulu-3-70b
Ai2 · Llama 3.1
1273±19
779N/AN/A
237
224249
qwen2-72b-instruct
Alibaba · Qianwen LICENSE
1272±7
10,780$0.90 / $0.9032.8K
238
222250
gemma-2-9b-it-simpo
Princeton · MIT
1272±11
2,554$0.03 / $0.098.2K
239
224249
amazon-nova-lite-v1.0
Amazon · Proprietary
1271±8
4,913$0.06 / $0.24300K
240
224249
Cohere
c4ai-aya-expanse-32b
Cohere · CC-BY-NC-4.0
1270±8
7,233N/AN/A
241
219253
Tencent
hunyuan-standard-256k
Tencent · Proprietary
1270±21
700N/AN/A
242
225251
reka-flash-20240904
Reka AI · Proprietary
1266±11
2,289N/AN/A
243
232250
Anthropic
claude-3-haiku-20240307
Anthropic · Proprietary
1264±6
33,698$0.25 / $1.25200K
244
224263
olmo-2-0325-32b-instruct
Ai2 · Apache-2.0
1261±20
789$0.05 / $0.20128K
245
233252
mistral-large-2402
Mistral · Proprietary
1260±7
17,187$4 / $1232K
246
231254
Cohere
command-r-plus-08-2024
Cohere · CC-BY-NC-4.0
1260±11
2,822$2.50 / $10128K
247
235253
gemini-1.5-flash-8b-001
Google · Proprietary
1258±7
9,654$0.07 / $0.301M
248
239253
gemma-2-9b-it
Google · Gemma license
1256±6
14,756$0.03 / $0.098.2K
249
235258
Cohere
command-r-08-2024
Cohere · CC-BY-NC-4.0
1255±10
2,976$0.15 / $0.60128K
250
235267
ministral-8b-2410
Mistral · MRL
1250±15
1,257$0.10 / $0.10131.1K
251
241259
Cohere
command-r-plus
Cohere · CC-BY-NC-4.0
1250±6
22,394$2.50 / $10128K
252
243266
qwen1.5-110b-chat
Alibaba · Qianwen LICENSE
1245±9
7,695N/AN/A
253
244266
amazon-nova-micro-v1.0
Amazon · Proprietary
1244±8
4,859$0.04 / $0.14128K
254
248267
mixtral-8x22b-instruct-v0.1
Mistral · Apache 2.0
1242±7
14,707$0.90 / $0.9065.5K
255
248270
qwen1.5-72b-chat
Alibaba · Qianwen LICENSE
1238±8
10,854N/AN/A
256
248273
jamba-1.5-mini
AI21 Labs · Jamba Open
1236±12
2,350$0.20 / $0.40256K
257
250272
mistral-medium
Mistral · Proprietary
1234±9
8,650$2.70 / $8.1032K
258
249274
reka-flash-21b-20240226-online
Reka AI · Proprietary
1234±11
4,506N/AN/A
259
250274
reka-flash-21b-20240226
Reka AI · Proprietary
1232±9
7,446N/AN/A
260
250276
gemini-pro-dev-api
Google · Proprietary
1230±11
4,515$0.35 / $1.0532.8K
261
247278
granite-3.1-8b-instruct
IBM · Apache 2.0
1229±20
798N/AN/A
262
251276
Cohere
c4ai-aya-expanse-8b
Cohere · CC-BY-NC-4.0
1229±11
2,576N/AN/A
263
248278
gemini-pro
Google · Proprietary
1228±18
1,407$0.35 / $1.0532.8K
264
255275
gpt-3.5-turbo-0125
OpenAI · Proprietary
1227±7
18,544$0.50 / $1.5016.4K
265
251278
gpt-3.5-turbo-1106
OpenAI · Proprietary
1226±13
3,846$1 / $216.4K
266
255277
01.AI
yi-1.5-34b-chat
01 AI · Apache-2.0
1224±8
6,679N/AN/A
267
253278
internlm2_5-20b-chat
InternLM · Other
1224±11
2,597$0 / $032.8K
268
250280
llama-3.1-tulu-3-8b
Ai2 · Llama 3.1
1222±20
728N/AN/A
269
256278
Meta
llama-3.1-8b-instruct
Meta · Llama 3.1 Community
1222±6
13,535$0.02 / $0.0516.4K
270
256278
qwen1.5-32b-chat
Alibaba · Qianwen LICENSE
1219±9
6,072N/AN/A
271
258278
Meta
llama-3-8b-instruct
Meta · Llama 3 Community
1218±6
30,221$0.03 / $0.048.2K
272
251282
granite-3.1-2b-instruct
IBM · Apache 2.0
1218±19
832N/AN/A
273
257279
dbrx-instruct-preview
Databricks · DBRX LICENSE
1215±9
8,865$0.60 / $0.6032.8K
274
255282
zephyr-orpo-141b-A35b-v0.1
HuggingFace · Apache 2.0
1214±17
1,240N/AN/A
275
260279
Cohere
command-r
Cohere · CC-BY-NC-4.0
1213±7
15,124$0.15 / $0.60128K
276
261280
phi-3-medium-4k-instruct
Microsoft · MIT
1211±8
6,823$0.17 / $0.68N/A
277
264280
mixtral-8x7b-instruct-v0.1
Mistral · Apache 2.0
1209±7
19,541$0.63 / $0.6332K
278
263293
granite-3.0-8b-instruct
IBM · Apache 2.0
1201±15
1,666N/AN/A
279
271292
qwen1.5-14b-chat
Alibaba · Qianwen LICENSE
1199±11
4,910$0.30 / $0.30N/A
280
273296
starling-lm-7b-beta
Nexusflow · Apache-2.0
1193±11
4,525N/AN/A
281
276295
gemma-1.1-7b-it
Google · Gemma license
1192±9
6,987$0.03 / $0.098.2K
282
278299
phi-3-small-8k-instruct
Microsoft · MIT
1187±10
5,229$0.15 / $0.60N/A
283
276302
tulu-2-dpo-70b
AllenAI/UW · AI2 ImpACT Low-risk
1186±16
1,419N/AN/A
284
278300
openchat-3.5-0106
OpenChat · Apache-2.0
1185±11
3,435N/AN/A
285
278300
snowflake-arctic-instruct
Snowflake · Apache 2.0
1184±9
9,592N/AN/A
286
278299
gemma-2-2b-it
Google · Gemma license
1184±6
12,322N/AN/A
287
278302
01.AI
yi-34b-chat
01 AI · Yi License
1182±11
3,838$0.90 / $0.904.1K
288
278307
openhermes-2.5-mistral-7b
NousResearch · Apache-2.0
1179±17
1,139$0.17 / $0.17N/A
289
278308
granite-3.0-2b-instruct
IBM · Apache 2.0
1176±15
1,740N/AN/A
290
278311
openchat-3.5
OpenChat · Apache-2.0
1174±16
1,663$0.20 / $0.20N/A
291
280307
phi-3-mini-4k-instruct-june-2024
Microsoft · MIT
1174±11
3,155$0.13 / $0.524.1K
292
278311
deepseek-llm-67b-chat
DeepSeek · DeepSeek License
1174±19
1,120N/AN/A
293
280311
wizardlm-70b
Microsoft · Llama 2 Community
1171±15
1,752N/AN/A
294
279312
qwq-32b-preview
Alibaba · Apache 2.0
1168±19
852$0.15 / $0.58131.1K
295
282311
Meta
llama-3.2-3b-instruct
Meta · Llama 3.2
1167±13
2,216$0.05 / $0.3480K
296
282311
starling-lm-7b-alpha
UC Berkeley · CC-BY-NC-4.0
1166±13
2,471N/AN/A
297
286311
vicuna-33b
LMSYS · Non-commercial
1162±10
5,071$0 / $02K
298
288312
Meta
llama-2-70b-chat
Meta · Llama 2 Community
1158±8
9,650$0.70 / $2.804.1K
299
278323
Meta
codellama-70b-instruct
Meta · Llama 2 Community
1158±31
306$0.70 / $2.8016.4K
300
284318
solar-10.7b-instruct-v1.0
Upstage AI · CC-BY-NC-4.0
1156±20
932$0.30 / $0.30N/A
301
281321
mpt-30b-chat
MosaicML · CC-BY-NC-SA-4.0
1156±27
434N/AN/A
302
288316
mistral-7b-instruct-v0.2
Mistral · Apache-2.0
1155±10
5,150$0.20 / $0.2032.8K
303
282323
dolphin-2.2.1-mistral-7b
Cognitive Computations · Apache-2.0
1154±28
359$0.50 / $0.5016.4K
304
288318
gemma-7b-it
Google · Gemma license
1152±14
2,267$0.05 / $0.088.2K
305
290316
phi-3-mini-4k-instruct
Microsoft · MIT
1152±10
5,872$0.13 / $0.52N/A
306
286324
smollm2-1.7b-instruct
HuggingFace · Apache 2.0
1149±25
572N/AN/A
307
288318
qwen1.5-7b-chat
Alibaba · Qianwen LICENSE
1149±16
1,333$0.20 / $0.20N/A
308
291320
palm-2
Google · Proprietary
1145±16
1,605$0.50 / $0.5025.8K
309
288324
llama2-70b-steerlm-chat
Nvidia · Llama 2 Community
1144±21
787N/AN/A
310
291325
qwen-14b-chat
Alibaba · Qianwen LICENSE
1140±19
1,006N/AN/A
311
299323
Meta
llama-2-13b-chat
Meta · Llama 2 Community
1137±10
4,475$0.25 / $0.254.1K
312
299324
gemma-1.1-2b-it
Google · Gemma license
1136±12
3,183N/AN/A
313
299326
Meta
codellama-34b-instruct
Meta · Llama 2 Community
1131±15
1,540$0.35 / $1.4016.4K
314
301326
vicuna-13b
LMSYS · Llama 2 Community
1130±11
3,971$0.30 / $0.30N/A
315
301326
phi-3-mini-128k-instruct
Microsoft · MIT
1128±11
6,167$0.13 / $0.52N/A
316
299326
nous-hermes-2-mixtral-8x7b-dpo
NousResearch · Apache-2.0
1128±18
1,066$0.90 / $0.90N/A
317
291329
falcon-180b-chat
TII · Falcon-180B TII License
1125±35
231N/AN/A
318
297329
zephyr-7b-alpha
HuggingFace · MIT
1121±30
333N/AN/A
319
304328
zephyr-7b-beta
HuggingFace · MIT
1115±14
2,220$0.15 / $0.1516.4K
320
309328
Meta
llama-3.2-1b-instruct
Meta · Llama 3.2
1113±13
2,247$0.03 / $0.2060K
321
304328
wizardlm-13b
Microsoft · Llama 2 Community
1113±17
1,278$0.30 / $0.30N/A
322
306328
mistral-7b-instruct
Mistral · Apache 2.0
1113±15
1,917$0.07 / $0.284.1K
323
306328
gemma-2b-it
Google · Gemma license
1110±18
1,191$0.10 / $0.10N/A
324
312329
stripedhyena-nous-7b
Together AI · Apache 2.0
1106±17
1,237$0.20 / $0.20N/A
325
305331
guanaco-33b
UW · Non-commercial
1103±26
517N/AN/A
326
313329
vicuna-7b
LMSYS · Llama 2 Community
1103±17
1,258$0.20 / $0.20N/A
327
317329
Meta
llama-2-7b-chat
Meta · Llama 2 Community
1095±11
3,289$0.15 / $0.154.1K
328
317330
qwen1.5-4b-chat
Alibaba · Qianwen LICENSE
1093±14
2,075$0.10 / $0.10N/A
329
327334
olmo-7b-instruct
Ai2 · Apache-2.0
1067±17
1,462$0.20 / $0.20N/A
330
322336
gpt4all-13b-snoozy
Nomic AI · Non-commercial
1062±30
347N/AN/A
331
328335
chatglm3-6b
Tsinghua · Apache-2.0
1058±20
999N/AN/A
332
329338
koala-13b
UC Berkeley · Non-commercial
1032±18
1,250N/AN/A
333
329338
mpt-7b-chat
MosaicML · CC-BY-NC-SA-4.0
1030±22
714N/AN/A
334
329338
chatglm2-6b
Tsinghua · Apache-2.0
1026±27
490N/AN/A
335
330338
oasst-pythia-12b
OpenAssistant · Apache 2.0
1020±19
1,153N/AN/A
336
331339
RWKV-4-Raven-14B
RWKV · Apache 2.0
1015±21
876N/AN/A
337
332339
alpaca-13b
Stanford · Non-commercial
1006±20
1,057N/AN/A
338
332339
chatglm-6b
Tsinghua · Non-commercial
998±22
848N/AN/A
339
336341
dolly-v2-12b
Databricks · MIT
970±25
615N/AN/A
340
339342
Stability
stablelm-tuned-alpha-7b
Stability AI · CC-BY-NC-SA-4.0
941±25
575N/AN/A
341
339342
fastchat-t5-3b
LMSYS · Apache 2.0
936±22
797N/AN/A
342
340342
Meta
llama-13b
Meta · Non-commercial
915±31
430$0.23 / $0.23N/A

Default Leaderboard Plots

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

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)