Text Arena🇬🇧English

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

May 1, 2026
3,179,936 votes
356 models
Rank Spread
1
14
Anthropic
claude-opus-4-6-thinking
Anthropic · Proprietary
1517±6
10,158$5 / $251M
2
16
Anthropic
claude-opus-4-7-thinking
Anthropic · Proprietary
1509±10
3,591$5 / $251M
3
15
Anthropic
claude-opus-4-6
Anthropic · Proprietary
1508±6
10,994$5 / $251M
4
19
Anthropic
claude-opus-4-7
Anthropic · Proprietary
1502±9
4,015$5 / $251M
5
214
Meta
muse-spark
Meta · Proprietary
1498±9
4,377N/AN/A
6
316
gemini-3.1-pro-preview
Google · Proprietary
1495±6
12,911$2 / $121M
7
419
gemini-3-pro
Google · Proprietary
1489±5
18,960$2 / $121M
8
431
gpt-5.5-high
OpenAI · Proprietary
1487±12
2,477$5 / $301.1M
9
527
grok-4.20-beta1
xAI · Proprietary
1485±7
8,102N/AN/A
10
526
Anthropic
claude-opus-4-5-20251101-thinking-32k
Anthropic · Proprietary
1484±5
17,042$5 / $25200K
11
529
grok-4.20-beta-0309-reasoning
xAI · Proprietary
1483±7
7,484$2 / $62M
12
532
glm-5.1
Z.ai · MIT
1482±8
5,158$1.40 / $4.40202.8K
13
731
gpt-5.2-chat-latest-20260210
OpenAI · Proprietary
1481±6
10,212$1.75 / $14128K
14
442
ernie-5.1-preview
Baidu · Proprietary
1480±12
2,158N/AN/A
15
542
gpt-5.5
OpenAI · Proprietary
1479±11
2,619$5 / $301.1M
16
732
grok-4.20-multi-agent-beta-0309
xAI · Proprietary
1479±7
7,579$2 / $62M
17
737
gpt-5.4-high
OpenAI · Proprietary
1478±7
7,087$2.50 / $151.1M
18
832
Anthropic
claude-opus-4-5-20251101
Anthropic · Proprietary
1478±5
24,624$5 / $25200K
19
543
deepseek-v4-pro-thinking
DeepSeek · MIT
1477±14
1,744$0.43 / $0.871M
20
643
mimo-v2.5-pro
Xiaomi · MIT
1477±12
2,258$1 / $31M
21
838
Anthropic
claude-sonnet-4-6
Anthropic · Proprietary
1476±7
7,357$3 / $151M
22
838
gemini-3-flash
Google · Proprietary
1476±6
14,119$0.50 / $31M
23
842
qwen3.5-max-preview
Alibaba · Proprietary
1475±8
6,263N/AN/A
24
838
grok-4.1-thinking
xAI · Proprietary
1474±5
24,761N/AN/A
25
1142
Anthropic
claude-sonnet-4-5-20250929-thinking-32k
Anthropic · Proprietary
1472±4
30,976$3 / $15200K
26
943
gpt-5.4
OpenAI · Proprietary
1472±7
7,596$2.50 / $151.1M
27
1142
grok-4.1
xAI · Proprietary
1471±5
26,775N/AN/A
28
1043
glm-5
Z.ai · MIT
1470±6
9,226$1 / $3.20202.8K
29
1046
mimo-v2-pro
Xiaomi · Proprietary
1469±8
6,070$1 / $31M
30
855
deepseek-v4-pro
DeepSeek · MIT
1467±13
1,828$0.43 / $0.871M
31
1643
Anthropic
claude-sonnet-4-5-20250929
Anthropic · Proprietary
1467±4
30,232$3 / $15200K
32
1646
gemini-3-flash (thinking-minimal)
Google · Proprietary
1466±5
18,294$0.50 / $31M
33
861
grok-4.3
xAI · Proprietary
1465±15
1,277$1.25 / $2.501M
34
1651
Bytedance
dola-seed-2.0-pro
Bytedance · Proprietary
1465±6
11,407N/AN/A
35
2048
Anthropic
claude-opus-4-1-20250805-thinking-16k
Anthropic · Proprietary
1464±5
23,573$15 / $75200K
36
1355
kimi-k2.6
Moonshot · Modified MIT
1464±11
2,704$0.95 / $4262.1K
37
2051
gpt-5.1-high
OpenAI · Proprietary
1463±5
18,780$1.25 / $10400K
38
1653
glm-4.7
Z.ai · MIT
1463±8
5,587$0.38 / $1.74202.8K
39
1755
longcat-flash-chat-2602-exp
Meituan · Proprietary
1462±8
5,656N/AN/A
40
1663
gemma-4-31b
Google · Apache 2.0
1460±11
2,564$0.14 / $0.40262.1K
41
2555
kimi-k2.5-thinking
Moonshot · Modified MIT
1460±6
11,372$0.60 / $3N/A
42
2062
qwen3.6-plus
Alibaba · Proprietary
1459±10
3,300$0.33 / $1.951M
43
3055
Anthropic
claude-opus-4-1-20250805
Anthropic · Proprietary
1458±4
36,370$15 / $75200K
44
3061
qwen3.5-397b-a17b
Alibaba · Apache 2.0
1456±6
10,008$0.39 / $2.34262.1K
45
2074
qwen3.6-max-preview
Alibaba · Proprietary
1456±13
1,748$1.04 / $6.24262.1K
46
3066
gpt-5.4-mini-high
OpenAI · Proprietary
1455±8
6,274$0.75 / $4.50400K
47
3364
ernie-5.0-0110
Baidu · Proprietary
1453±6
12,310N/AN/A
48
3367
gpt-5.3-chat-latest
OpenAI · Proprietary
1453±7
9,557$1.75 / $14128K
49
3274
ernie-5.0-preview-1203
Baidu · Proprietary
1451±9
4,593N/AN/A
50
4166
gemini-2.5-pro
Google · Proprietary
1450±3
53,565$1.25 / $101M
51
3282
gemma-4-26b-a4b
Google · Apache 2.0
1449±11
2,513N/AN/A
52
4169
chatgpt-4o-latest-20250326
OpenAI · Proprietary
1448±4
41,168$5 / $15128K
53
3676
gpt-4.5-preview-2025-02-27
OpenAI · Proprietary
1447±7
8,425$75 / $150128K
54
4174
gpt-5.2-high
OpenAI · Proprietary
1447±5
16,691$1.75 / $14400K
55
4174
kimi-k2-thinking-turbo
Moonshot · Modified MIT
1447±5
23,535$1.15 / $8262.1K
56
3585
kimi-k2.5-instant
Moonshot · Modified MIT
1446±10
3,716$0.44 / $2262.1K
57
3394
deepseek-v4-flash-thinking
DeepSeek · MIT
1445±14
1,611$0.14 / $0.281M
58
4479
deepseek-v3.2-thinking
DeepSeek · MIT
1444±5
17,554$0.25 / $0.38131.1K
59
4382
gemini-3.1-flash-lite-preview
Google · Proprietary
1443±6
10,215$0.25 / $1.501M
60
4680
grok-4-1-fast-reasoning
xAI · Proprietary
1443±5
22,404$0.20 / $0.502M
61
4682
gpt-5.1
OpenAI · Proprietary
1442±5
20,128$1.25 / $10400K
62
4191
deepseek-v3.2-exp-thinking
DeepSeek · MIT
1441±9
4,365$0.27 / $0.41163.8K
63
3599
amazon-nova-experimental-chat-26-02-10
Amazon · Proprietary
1441±15
1,567N/AN/A
64
3698
deepseek-v4-flash
DeepSeek · MIT
1441±14
1,597$0.14 / $0.281M
65
4987
gpt-5.2
OpenAI · Proprietary
1440±5
15,614$1.75 / $14400K
66
4198
mimo-v2.5
Xiaomi · MIT
1440±12
2,369$0.40 / $21M
67
4988
qwen3-max-preview
Alibaba · Proprietary
1439±6
12,983$0.78 / $3.90262.1K
68
5090
gpt-5-high
OpenAI · Proprietary
1438±6
15,143$1.25 / $10400K
69
5087
o3-2025-04-16
OpenAI · Proprietary
1438±5
30,165$2 / $8200K
70
4895
deepseek-v3.2-exp
DeepSeek · MIT
1438±8
5,671$0.27 / $0.41163.8K
71
5091
glm-4.6
Z.ai · MIT
1438±5
17,199$0.39 / $1.90204.8K
72
5494
deepseek-v3.2
DeepSeek · MIT
1436±5
20,225$0.25 / $0.38131.1K
73
45107
amazon-nova-experimental-chat-26-01-10
Amazon · Proprietary
1434±14
1,577N/AN/A
74
50102
qwen3-max-2025-09-23
Alibaba · Proprietary
1434±9
4,496$0.78 / $3.90262.1K
75
5598
Anthropic
claude-opus-4-20250514-thinking-16k
Anthropic · Proprietary
1434±6
17,479$15 / $75200K
76
5798
gpt-5-chat
OpenAI · Proprietary
1432±6
15,013$1.25 / $10128K
77
56103
deepseek-r1-0528
DeepSeek · MIT
1432±7
8,890$0.50 / $2.15163.8K
78
55104
deepseek-v3.1-thinking
DeepSeek · MIT
1431±9
5,275$1.23 / $4.94N/A
79
57104
qwen3.5-122b-a10b
Alibaba · Apache 2.0
1431±7
8,361$0.26 / $2.08262.1K
80
55108
grok-4-fast-chat
xAI · Proprietary
1430±10
3,230$3 / $15256K
81
64102
qwen3-235b-a22b-instruct-2507
Alibaba · Apache 2.0
1429±4
40,348$0.26 / $1.06N/A
82
50116
deepseek-v3.1-terminus-thinking
DeepSeek · MIT
1429±14
1,674$0.27 / $0.95163.8K
83
60106
deepseek-v3.1
DeepSeek · MIT
1429±8
6,794$1.23 / $4.94N/A
84
65104
Anthropic
claude-haiku-4-5-20251001
Anthropic · Proprietary
1428±4
30,842$1 / $5200K
85
64104
mistral-large-3
Mistral · Apache 2.0
1428±5
19,259$0.50 / $1.50N/A
86
60108
qwen3-vl-235b-a22b-instruct
Alibaba · Apache 2.0
1428±9
5,647$0.20 / $0.88262.1K
87
54120
Tencent
hunyuan-hy3-preview
Tencent · tencent-hunyuan-community
1427±14
1,619$0.29 / $1.17262.1K
88
63107
qwen3.5-27b
Alibaba · Apache 2.0
1427±7
8,127$0.20 / $1.56262.1K
89
67108
kimi-k2-0711-preview
Moonshot · Modified MIT
1426±6
13,227$0.60 / $2.50131.1K
90
70106
mistral-medium-2508
Mistral · Proprietary
1425±4
39,021$2.70 / $8.1032K
91
69108
Anthropic
claude-opus-4-20250514
Anthropic · Proprietary
1424±5
21,463$15 / $75200K
92
67116
kimi-k2-0905-preview
Moonshot · Modified MIT
1424±8
5,468$0.60 / $2.50262.1K
93
67116
longcat-flash-chat
Meituan · MIT
1424±8
5,373$0.20 / $0.80131.1K
94
61122
ernie-5.0-preview-1022
Baidu · Proprietary
1423±12
2,376N/AN/A
95
60124
deepseek-v3.1-terminus
DeepSeek · MIT
1423±14
1,856$0.27 / $0.95163.8K
96
70115
minimax-m2.5
MiniMax · Modified MIT
1422±6
10,665$0.15 / $1.15196.6K
97
75111
gpt-4.1-2025-04-14
OpenAI · Proprietary
1422±5
25,701$2 / $81M
98
61127
amazon-nova-experimental-chat-12-10
Amazon · Proprietary
1421±14
1,669N/AN/A
99
75116
grok-3-preview-02-24
xAI · Proprietary
1421±5
18,067$3 / $15131.1K
100
70121
minimax-m2.7
MiniMax · Modified MIT
1420±8
5,434$0.30 / $1.20196.6K
101
75120
glm-4.5
Z.ai · MIT
1420±6
11,447$0.60 / $2.20131.1K
102
78116
grok-4-0709
xAI · Proprietary
1420±5
20,252$3 / $15256K
103
74122
gpt-5.4-nano-high
OpenAI · Proprietary
1419±8
6,084$0.20 / $1.25400K
104
82123
mimo-v2-flash (non-thinking)
Xiaomi · MIT
1416±5
16,052$0.09 / $0.29262.1K
105
82124
Anthropic
claude-sonnet-4-20250514-thinking-32k
Anthropic · Proprietary
1416±6
16,804$3 / $151M
106
84126
grok-4-fast-reasoning
xAI · Proprietary
1414±7
9,306$0.20 / $0.502M
107
86128
qwen3.5-35b-a3b
Alibaba · Apache 2.0
1413±7
8,451$0.15 / $1262.1K
108
91124
gemini-2.5-flash
Google · Proprietary
1413±3
53,849$0.30 / $2.501M
109
90128
deepseek-r1
DeepSeek · MIT
1412±6
10,721$0.70 / $2.5064K
110
90128
gemini-2.5-flash-preview-09-2025
Google · Proprietary
1412±5
15,853$0.30 / $2.501M
111
90129
qwen3-next-80b-a3b-instruct
Alibaba · Apache 2.0
1412±6
10,882$0.09 / $1.10262.1K
112
91129
o1-2024-12-17
OpenAI · Proprietary
1411±6
16,316$15 / $60200K
113
91130
Stepfun
step-3.5-flash
StepFun · Apache 2.0
1410±6
10,429$0.10 / $0.30262.1K
114
91131
qwen3.5-flash
Alibaba · Proprietary
1410±7
7,874N/AN/A
115
92132
o1-preview
OpenAI · Proprietary
1409±6
15,891$15 / $60N/A
116
77143
Tencent
hunyuan-vision-1.5-thinking
Tencent · Proprietary
1408±17
1,104N/AN/A
117
99134
qwen3-235b-a22b-no-thinking
Alibaba · Apache 2.0
1407±5
18,634$0.46 / $1.82131.1K
118
100133
deepseek-v3-0324
DeepSeek · MIT
1407±5
23,279$3 / $4.5032.8K
119
97134
mai-1-preview
Microsoft AI · Proprietary
1407±7
8,223N/AN/A
120
97137
mimo-v2-flash (thinking)
Xiaomi · MIT
1405±9
4,929$0.09 / $0.29262.1K
121
97138
qwen3-235b-a22b-thinking-2507
Alibaba · Apache 2.0
1405±9
4,379$0.15 / $1.50131.1K
122
97139
qwen3-vl-235b-a22b-thinking
Alibaba · Apache 2.0
1404±9
3,885$0.26 / $2.60131.1K
123
103138
minimax-m2.1-preview
MiniMax · MIT
1403±7
7,649$0.29 / $0.95196.6K
124
106137
o4-mini-2025-04-16
OpenAI · Proprietary
1403±5
22,999$1.10 / $4.40200K
125
106137
mistral-medium-2505
Mistral · Proprietary
1403±6
16,695$0.40 / $2131.1K
126
108137
Anthropic
claude-3-7-sonnet-20250219-thinking-32k
Anthropic · Proprietary
1402±5
20,340$3 / $15200K
127
111140
qwen3-coder-480b-a35b-instruct
Alibaba · Apache 2.0
1400±6
12,380$0.40 / $1.60262.1K
128
107143
trinity-large-thinking
Arcee AI · Apache 2.0
1399±8
5,055$0.22 / $0.85262.1K
129
113143
trinity-large-preview
Arcee AI · Apache 2.0
1398±7
8,964$0.15 / $0.45131K
130
114143
gpt-5-mini-high
OpenAI · Proprietary
1398±6
12,749$0.25 / $2400K
131
116143
gpt-4.1-mini-2025-04-14
OpenAI · Proprietary
1397±5
19,787$0.40 / $1.601M
132
117143
Anthropic
claude-sonnet-4-20250514
Anthropic · Proprietary
1397±5
19,488$3 / $151M
133
115151
glm-4.7-flash
Z.ai · MIT
1395±8
5,288$0.06 / $0.40202.8K
134
102163
glm-4.6v
Z.ai · MIT
1395±16
1,288$0.30 / $0.90131.1K
135
119151
qwen3-30b-a3b-instruct-2507
Alibaba · Apache 2.0
1393±6
11,063$0.09 / $0.30262.1K
136
119157
Tencent
hunyuan-turbos-20250416
Tencent · Proprietary
1391±8
5,671N/AN/A
137
125156
glm-4.5-air
Z.ai · MIT
1390±6
14,840$0.13 / $0.85131.1K
138
127159
qwen3-235b-a22b
Alibaba · Apache 2.0
1387±6
13,456$0.46 / $1.82131.1K
139
126162
qwen3-next-80b-a3b-thinking
Alibaba · Apache 2.0
1387±8
6,638$0.10 / $0.78131.1K
140
119169
Tencent
hunyuan-t1-20250711
Tencent · Proprietary
1386±13
2,094N/AN/A
141
133161
gemini-2.5-flash-lite-preview-09-2025-no-thinking
Google · Proprietary
1385±5
22,619$0.10 / $0.401M
142
123169
intellect-3
Prime Intellect · MIT
1385±11
2,613$0.20 / $1.10131.1K
143
133162
minimax-m1
MiniMax · Apache 2.0
1385±5
16,880$0.40 / $2.201M
144
133162
Anthropic
claude-3-7-sonnet-20250219
Anthropic · Proprietary
1384±5
23,517$3 / $15200K
145
127169
nvidia-nemotron-3-super-120b-a12b
Nvidia · NVIDIA Open Model
1383±10
3,431N/AN/A
146
133165
qwen2.5-max
Alibaba · Proprietary
1382±5
18,691N/AN/A
147
135165
Anthropic
claude-3-5-sonnet-20241022
Anthropic · Proprietary
1382±4
46,463$3 / $15200K
148
133169
mistral-small-2506
Mistral · Apache 2.0
1381±7
8,517$0.10 / $0.3032K
149
135169
amazon-nova-experimental-chat-11-10
Amazon · Proprietary
1381±6
11,723N/AN/A
150
127173
glm-4.5v
Z.ai · MIT
1381±12
2,385$0.60 / $1.8065.5K
151
135170
o3-mini-high
OpenAI · Proprietary
1379±6
11,130$1.10 / $4.40200K
152
135170
gemini-2.5-flash-lite-preview-06-17-thinking
Google · Proprietary
1379±6
15,773$0.10 / $0.401M
153
135173
amazon-nova-experimental-chat-10-20
Amazon · Proprietary
1378±8
5,554N/AN/A
154
133185
llama-3.1-nemotron-ultra-253b-v1
Nvidia · Nvidia Open Model
1375±15
1,491$0.60 / $1.80131.1K
155
133188
llama-3.3-nemotron-49b-super-v1
Nvidia · Nvidia
1374±16
1,250N/AN/A
156
138175
grok-3-mini-high
xAI · Proprietary
1374±7
8,447$0.30 / $0.50131.1K
157
143173
gemma-3-27b-it
Google · Gemma
1374±5
24,851$0.08 / $0.16131.1K
158
136179
Stepfun
step-3
StepFun · Apache 2.0
1373±10
3,166$0.57 / $1.4265.5K
159
133189
amazon-nova-experimental-chat-10-09
Amazon · Proprietary
1372±15
1,402N/AN/A
160
137180
ling-flash-2.0
Ant Group · MIT
1372±10
3,394N/AN/A
161
137183
minimax-m2
MiniMax · Apache 2.0
1371±10
3,362$0.26 / $1196.6K
162
145178
deepseek-v3
DeepSeek · DeepSeek
1370±6
12,866$1.14 / $4.56N/A
163
145179
grok-3-mini-beta
xAI · Proprietary
1370±6
11,612$0.30 / $0.50131.1K
164
145188
olmo-3.1-32b-instruct
Ai2 · Apache 2.0
1367±8
5,501$0.20 / $0.6065.5K
165
152180
gemini-2.0-flash-001
Google · Proprietary
1367±5
24,787$0.10 / $0.401M
166
143192
qwen3-32b
Alibaba · Apache 2.0
1366±12
2,230$0.08 / $0.2441K
167
138197
mercury-2
Inception AI · Proprietary
1366±16
1,397$0.25 / $0.75128K
168
152181
Cohere
command-a-03-2025
Cohere · CC-BY-NC-4.0
1365±4
28,503$2.50 / $10256K
169
139196
nvidia-llama-3.3-nemotron-super-49b-v1.5
Nvidia · Nvidia Open
1365±14
1,537$0.10 / $0.40131.1K
170
155188
o3-mini
OpenAI · Proprietary
1363±4
30,420$1.10 / $4.40200K
171
152190
nova-2-lite
Amazon · Proprietary
1363±8
5,759$0.30 / $2.501M
172
145200
Tencent
hunyuan-turbos-20250226
Tencent · Proprietary
1362±15
1,310N/AN/A
173
155189
gpt-oss-120b
OpenAI · Apache 2.0
1362±6
14,704$0.04 / $0.18131.1K
174
156189
Meta
llama-3.1-405b-instruct-bf16
Meta · Llama 3.1 Community
1360±5
23,318$4 / $432.8K
175
150205
Tencent
hunyuan-turbo-0110
Tencent · Proprietary
1359±14
1,319N/AN/A
176
157193
qwq-32b
Alibaba · Apache 2.0
1359±6
13,692$0.50 / $116.4K
177
156202
qwen-plus-0125
Alibaba · Proprietary
1356±10
3,425$0.40 / $1.20131.1K
178
162196
Meta
llama-3.1-405b-instruct-fp8
Meta · Llama 3.1 Community
1356±5
32,442$4 / $432.8K
179
163196
gpt-4o-2024-05-13
OpenAI · Proprietary
1356±5
60,226$5 / $15128K
180
161196
gemini-2.0-flash-lite-preview-02-05
Google · Proprietary
1356±5
14,891$0.07 / $0.301M
181
164196
gemini-1.5-pro-002
Google · Proprietary
1356±4
30,133$3.50 / $10.502.1M
182
156206
Stepfun
step-2-16k-exp-202412
StepFun · Proprietary
1355±11
2,781N/AN/A
183
162200
01.AI
yi-lightning
01 AI · Proprietary
1354±7
13,650N/AN/A
184
167198
o1-mini
OpenAI · Proprietary
1354±5
27,352$1.10 / $4.40N/A
185
159207
glm-4-plus-0111
Zhipu · Proprietary
1352±10
3,466N/AN/A
186
164210
ring-flash-2.0
Ant Group · MIT
1349±10
3,471N/AN/A
187
163211
gemma-3-12b-it
Google · Gemma
1349±12
2,330$0.04 / $0.13131.1K
188
142236
molmo-2-8b
Ai2 · Apache 2.0
1348±31
373$0.20 / $0.2036.9K
189
173206
gpt-4o-2024-08-06
OpenAI · Proprietary
1348±5
25,286$2.50 / $10128K
190
164212
olmo-3-32b-think
Ai2 · Apache 2.0
1348±11
2,818$0.15 / $0.5065.5K
191
173206
Anthropic
claude-3-5-sonnet-20240620
Anthropic · Proprietary
1348±4
44,433$3 / $15200K
192
173207
qwen3-30b-a3b
Alibaba · Apache 2.0
1346±6
13,396$0.09 / $0.4541K
193
171211
nvidia-nemotron-3-nano-30b-a3b-bf16
Nvidia · NVIDIA Open Model
1346±8
7,187$0.06 / $0.24262.1K
194
178207
grok-2-2024-08-13
xAI · Proprietary
1346±5
34,362$2 / $10131.1K
195
171216
gpt-5-nano-high
OpenAI · Proprietary
1344±9
4,016$0.05 / $0.40400K
196
180210
Meta
llama-3.3-70b-instruct
Meta · Llama-3.3
1344±4
30,163$0.10 / $0.32131.1K
197
172217
olmo-3.1-32b-think
Ai2 · Apache 2.0
1343±10
3,811$0.15 / $0.5065.5K
198
170221
Tencent
hunyuan-large-2025-02-10
Tencent · Proprietary
1343±12
2,255N/AN/A
199
180213
gemini-advanced-0514
Google · Proprietary
1342±6
26,318N/AN/A
200
182213
Meta
llama-4-scout-17b-16e-instruct
Meta · Llama
1341±6
14,447$0.40 / $0.708.2K
201
183212
gpt-4-turbo-2024-04-09
OpenAI · Proprietary
1341±5
55,116$10 / $30128K
202
183213
Meta
llama-4-maverick-17b-128e-instruct
Meta · Llama 4
1340±5
20,437$0.63 / $1.80131.1K
203
179222
gpt-4.1-nano-2025-04-14
OpenAI · Proprietary
1340±10
3,528$0.10 / $0.401M
204
187220
mistral-large-2407
Mistral · Mistral Research
1336±5
24,863$2 / $6131.1K
205
182228
deepseek-v2.5-1210
DeepSeek · DeepSeek
1336±10
3,776N/AN/A
206
190218
Anthropic
claude-3-5-haiku-20241022
Anthropic · Proprietary
1336±4
37,378$0.80 / $4200K
207
184230
Stepfun
step-1o-turbo-202506
StepFun · Proprietary
1335±9
4,365N/AN/A
208
190232
qwen2.5-plus-1127
Alibaba · Proprietary
1332±8
5,804N/AN/A
209
190232
gpt-oss-20b
OpenAI · Apache 2.0
1331±9
5,060$0.03 / $0.14131.1K
210
194230
athene-v2-chat
NexusFlow · NexusFlow
1331±6
13,676N/AN/A
211
192235
llama-3.1-nemotron-70b-instruct
Nvidia · Llama 3.1
1329±10
3,714$1.20 / $1.20131.1K
212
200232
gemini-1.5-pro-001
Google · Proprietary
1329±5
42,538$3.50 / $10.502.1M
213
201231
gpt-4o-mini-2024-07-18
OpenAI · Proprietary
1329±4
37,772$0.15 / $0.60128K
214
199232
gemma-3n-e4b-it
Google · Gemma
1328±6
10,953$0.06 / $0.1232.8K
215
199233
athene-70b-0725
NexusFlow · CC-BY-NC-4.0
1328±7
11,268N/AN/A
216
199233
qwen-max-0919
Alibaba · Qwen
1327±7
8,347$1.60 / $6.4032.8K
217
196235
magistral-medium-2506
Mistral · Proprietary
1327±9
4,998$2 / $540K
218
183239
mercury
Inception AI · Proprietary
1326±20
945$0.25 / $0.75128K
219
202235
glm-4-plus
Zhipu AI · Proprietary
1325±6
13,191$0.44 / $1.76204.8K
220
204233
Meta
llama-3-70b-instruct
Meta · Llama 3 Community
1325±5
90,553$0.51 / $0.748.2K
221
205234
gpt-4-1106-preview
OpenAI · Proprietary
1325±5
64,698$10 / $30128K
222
205235
gpt-4-0125-preview
OpenAI · Proprietary
1324±5
54,967$10 / $30128K
223
205235
Anthropic
claude-3-opus-20240229
Anthropic · Proprietary
1323±4
108,426$15 / $75200K
224
205236
mistral-small-3.1-24b-instruct-2503
Mistral · Apache 2.0
1322±6
15,947$0.10 / $0.3032K
225
205236
mistral-large-2411
Mistral · MRL
1321±5
16,289$2 / $6131.1K
226
206236
Meta
llama-3.1-70b-instruct
Meta · Llama 3.1 Community
1321±5
29,694$0.40 / $0.40131.1K
227
206236
grok-2-mini-2024-08-13
xAI · Proprietary
1321±5
28,429$2 / $10131.1K
228
202238
Tencent
hunyuan-standard-2025-02-10
Tencent · Proprietary
1319±12
2,312N/AN/A
229
208237
deepseek-v2.5
DeepSeek · DeepSeek
1318±6
12,845N/AN/A
230
203240
llama-3.1-nemotron-51b-instruct
Nvidia · Llama 3.1
1318±14
1,794N/AN/A
231
213238
qwen2.5-72b-instruct
Alibaba · Qwen
1316±5
20,561$1.20 / $1.20N/A
232
209239
jamba-1.5-large
AI21 Labs · Jamba Open
1315±9
4,915$2 / $8256K
233
205240
Tencent
hunyuan-large-vision
Tencent · Proprietary
1314±12
2,752N/AN/A
234
217238
gemini-1.5-flash-002
Google · Proprietary
1314±5
18,364$0.07 / $0.301M
235
216247
gemma-3-4b-it
Google · Gemma
1308±12
2,572$0.04 / $0.08131.1K
236
222249
ibm-granite-h-small
IBM · Apache 2.0
1306±12
2,810N/AN/A
237
228243
amazon-nova-pro-v1.0
Amazon · Proprietary
1305±6
14,188$0.80 / $3.20300K
238
227251
llama-3.1-tulu-3-70b
Ai2 · Llama 3.1
1302±13
1,629N/AN/A
239
231249
gpt-4-0314
OpenAI · Proprietary
1300±6
35,534$30 / $608.2K
240
235250
gemma-2-27b-it
Google · Gemma license
1298±4
41,283$0.65 / $0.658.2K
241
233251
gemma-2-9b-it-simpo
Princeton · MIT
1296±9
5,834$0.03 / $0.098.2K
242
235251
mistral-small-24b-instruct-2501
Mistral · Apache 2.0
1294±7
8,740$0.05 / $0.0832.8K
243
236251
gpt-4-0613
OpenAI · Proprietary
1292±5
57,478$30 / $608.2K
244
235252
reka-core-20240904
Reka AI · Proprietary
1292±9
3,934N/AN/A
245
237252
gemini-1.5-flash-001
Google · Proprietary
1290±5
33,810$0.07 / $0.301M
246
240252
Anthropic
claude-3-sonnet-20240229
Anthropic · Proprietary
1288±5
60,970$3 / $15200K
247
237256
nemotron-4-340b-instruct
Nvidia · NVIDIA Open Model
1288±7
10,292N/AN/A
248
236257
glm-4-0520
Zhipu AI · Proprietary
1288±9
5,169N/AN/A
249
236261
olmo-2-0325-32b-instruct
Ai2 · Apache-2.0
1287±13
2,025$0.05 / $0.20128K
250
236260
qwen2.5-coder-32b-instruct
Alibaba · Apache 2.0
1286±11
2,652$0.87 / $0.8732K
251
239257
Cohere
command-r-plus-08-2024
Cohere · CC-BY-NC-4.0
1286±8
5,305$2.50 / $10128K
252
247261
gemma-2-9b-it
Google · Gemma license
1277±5
29,787$0.03 / $0.098.2K
253
244266
reka-flash-20240904
Reka AI · Proprietary
1275±9
4,032N/AN/A
254
247265
qwen2-72b-instruct
Alibaba · Qianwen LICENSE
1275±6
19,928$0.90 / $0.9032.8K
255
247266
amazon-nova-lite-v1.0
Amazon · Proprietary
1274±6
11,044$0.06 / $0.24300K
256
248266
Cohere
c4ai-aya-expanse-32b
Cohere · CC-BY-NC-4.0
1274±6
14,358N/AN/A
257
247267
jamba-1.5-mini
AI21 Labs · Jamba Open
1271±9
5,087$0.20 / $0.40256K
258
250266
phi-4
Microsoft · MIT
1271±6
14,101$0.07 / $0.1416.4K
259
250266
Cohere
command-r-plus
Cohere · CC-BY-NC-4.0
1271±5
42,376$2.50 / $10128K
260
251266
Anthropic
claude-3-haiku-20240307
Anthropic · Proprietary
1269±5
64,537$0.25 / $1.25200K
261
250270
deepseek-coder-v2
DeepSeek · DeepSeek License
1269±8
8,140$0.14 / $0.28128K
262
253270
gemini-1.5-flash-8b-001
Google · Proprietary
1266±6
18,467$0.07 / $0.301M
263
253270
mistral-large-2402
Mistral · Proprietary
1265±6
36,796$4 / $1232K
264
253270
Meta
llama-3-8b-instruct
Meta · Llama 3 Community
1265±5
61,703$0.03 / $0.048.2K
265
253276
Cohere
command-r-08-2024
Cohere · CC-BY-NC-4.0
1261±8
5,416$0.15 / $0.60128K
266
254280
ministral-8b-2410
Mistral · MRL
1257±12
2,322$0.10 / $0.10131.1K
267
260279
qwen1.5-110b-chat
Alibaba · Qianwen LICENSE
1256±7
13,896N/AN/A
268
261279
amazon-nova-micro-v1.0
Amazon · Proprietary
1255±6
10,991$0.04 / $0.14128K
269
265280
mixtral-8x22b-instruct-v0.1
Mistral · Apache 2.0
1252±6
29,892$0.90 / $0.9065.5K
270
265281
qwen1.5-72b-chat
Alibaba · Qianwen LICENSE
1250±6
25,039N/AN/A
271
265284
01.AI
yi-1.5-34b-chat
01 AI · Apache-2.0
1249±7
12,503N/AN/A
272
261289
granite-3.1-8b-instruct
IBM · Apache 2.0
1248±14
1,737N/AN/A
273
265287
mistral-medium
Mistral · Proprietary
1247±6
23,846$2.70 / $8.1032K
274
265287
gemini-pro-dev-api
Google · Proprietary
1246±9
12,477$0.35 / $1.0532.8K
275
261293
Tencent
hunyuan-standard-256k
Tencent · Proprietary
1245±16
1,278N/AN/A
276
266291
reka-flash-21b-20240226-online
Reka AI · Proprietary
1241±9
8,935N/AN/A
277
265293
gemini-pro
Google · Proprietary
1241±13
5,086$0.35 / $1.0532.8K
278
266294
zephyr-orpo-141b-A35b-v0.1
HuggingFace · Apache 2.0
1239±13
2,702N/AN/A
279
266294
llama-3.1-tulu-3-8b
Ai2 · Llama 3.1
1239±14
1,633N/AN/A
280
271291
Meta
llama-3.1-8b-instruct
Meta · Llama 3.1 Community
1237±5
26,610$0.02 / $0.0516.4K
281
270292
reka-flash-21b-20240226
Reka AI · Proprietary
1237±7
14,444N/AN/A
282
271291
Cohere
command-r
Cohere · CC-BY-NC-4.0
1237±6
29,623$0.15 / $0.60128K
283
268294
granite-3.0-8b-instruct
IBM · Apache 2.0
1237±12
3,296N/AN/A
284
272292
gpt-3.5-turbo-0125
OpenAI · Proprietary
1236±6
39,956$0.50 / $1.5016.4K
285
271294
internlm2_5-20b-chat
InternLM · Other
1234±9
4,966$0 / $032.8K
286
272294
Cohere
c4ai-aya-expanse-8b
Cohere · CC-BY-NC-4.0
1232±9
5,497N/AN/A
287
274294
phi-3-medium-4k-instruct
Microsoft · MIT
1229±7
13,283$0.17 / $0.68N/A
288
274294
mixtral-8x7b-instruct-v0.1
Mistral · Apache 2.0
1229±5
46,298$0.63 / $0.6332K
289
272304
granite-3.1-2b-instruct
IBM · Apache 2.0
1226±14
1,739N/AN/A
290
275297
dbrx-instruct-preview
Databricks · DBRX LICENSE
1225±8
18,053$0.60 / $0.6032.8K
291
275302
Meta
llama-3.2-3b-instruct
Meta · Llama 3.2
1224±10
4,157$0.05 / $0.3480K
292
278302
qwen1.5-32b-chat
Alibaba · Qianwen LICENSE
1223±8
11,877N/AN/A
293
282299
gemma-2-2b-it
Google · Gemma license
1221±5
25,669N/AN/A
294
280307
gpt-3.5-turbo-1106
OpenAI · Proprietary
1219±10
12,878$1 / $216.4K
295
289311
wizardlm-70b
Microsoft · Llama 2 Community
1212±10
6,411N/AN/A
296
289311
phi-3-small-8k-instruct
Microsoft · MIT
1210±8
9,107$0.15 / $0.60N/A
297
290311
01.AI
yi-34b-chat
01 AI · Yi License
1209±8
10,572$0.90 / $0.904.1K
298
291314
qwen1.5-14b-chat
Alibaba · Qianwen LICENSE
1207±9
9,520$0.30 / $0.30N/A
299
293312
gemma-1.1-7b-it
Google · Gemma license
1207±7
12,733$0.03 / $0.098.2K
300
293311
Meta
llama-2-70b-chat
Meta · Llama 2 Community
1207±6
26,045$0.70 / $2.804.1K
301
291314
openchat-3.5-0106
OpenChat · Apache-2.0
1207±9
8,216N/AN/A
302
289315
openhermes-2.5-mistral-7b
NousResearch · Apache-2.0
1206±12
3,857$0.17 / $0.17N/A
303
290317
deepseek-llm-67b-chat
DeepSeek · DeepSeek License
1205±13
3,820N/AN/A
304
291316
tulu-2-dpo-70b
AllenAI/UW · AI2 ImpACT Low-risk
1204±11
5,039N/AN/A
305
294316
starling-lm-7b-beta
Nexusflow · Apache-2.0
1201±9
9,101N/AN/A
306
294318
openchat-3.5
OpenChat · Apache-2.0
1200±11
6,196$0.20 / $0.20N/A
307
295316
snowflake-arctic-instruct
Snowflake · Apache 2.0
1200±8
20,419N/AN/A
308
294319
granite-3.0-2b-instruct
IBM · Apache 2.0
1200±11
3,330N/AN/A
309
295317
vicuna-33b
LMSYS · Non-commercial
1199±7
16,692$0 / $02K
310
295319
starling-lm-7b-alpha
UC Berkeley · CC-BY-NC-4.0
1195±9
7,238N/AN/A
311
299319
phi-3-mini-4k-instruct-june-2024
Microsoft · MIT
1192±8
6,694$0.13 / $0.524.1K
312
295323
nous-hermes-2-mixtral-8x7b-dpo
NousResearch · Apache-2.0
1191±13
3,033$0.90 / $0.90N/A
313
302320
mistral-7b-instruct-v0.2
Mistral · Apache-2.0
1189±8
12,723$0.20 / $0.2032.8K
314
300332
solar-10.7b-instruct-v1.0
Upstage AI · CC-BY-NC-4.0
1184±15
3,277$0.30 / $0.30N/A
315
300334
dolphin-2.2.1-mistral-7b
Cognitive Computations · Apache-2.0
1182±17
1,302$0.50 / $0.5016.4K
316
303334
mpt-30b-chat
MosaicML · CC-BY-NC-SA-4.0
1181±14
2,056N/AN/A
317
306334
llama2-70b-steerlm-chat
Nvidia · Llama 2 Community
1178±14
2,751N/AN/A
318
308336
qwq-32b-preview
Alibaba · Apache 2.0
1176±15
1,783$0.50 / $116.4K
319
313334
Meta
llama-2-13b-chat
Meta · Llama 2 Community
1172±8
13,860$0.25 / $0.254.1K
320
313335
phi-3-mini-4k-instruct
Microsoft · MIT
1172±8
10,322$0.13 / $0.52N/A
321
312336
wizardlm-13b
Microsoft · Llama 2 Community
1171±10
5,508$0.30 / $0.30N/A
322
309338
falcon-180b-chat
TII · Falcon-180B TII License
1170±19
1,047N/AN/A
323
314336
zephyr-7b-beta
HuggingFace · MIT
1167±10
8,764$0.15 / $0.1516.4K
324
314336
gemma-7b-it
Google · Gemma license
1167±11
5,689$0.05 / $0.088.2K
325
314336
Meta
llama-3.2-1b-instruct
Meta · Llama 3.2
1165±10
4,320$0.03 / $0.2060K
326
314336
palm-2
Google · Proprietary
1165±10
6,912$0.50 / $0.5025.8K
327
314338
qwen1.5-7b-chat
Alibaba · Qianwen LICENSE
1163±11
3,243$0.20 / $0.20N/A
328
314337
phi-3-mini-128k-instruct
Microsoft · MIT
1162±9
12,596$0.13 / $0.52N/A
329
315337
vicuna-13b
LMSYS · Llama 2 Community
1161±8
14,788$0.30 / $0.30N/A
330
314338
Meta
codellama-34b-instruct
Meta · Llama 2 Community
1160±10
5,804$0.35 / $1.4016.4K
331
313340
smollm2-1.7b-instruct
HuggingFace · Apache 2.0
1159±19
1,111N/AN/A
332
314340
zephyr-7b-alpha
HuggingFace · MIT
1158±17
1,415N/AN/A
333
315339
guanaco-33b
UW · Non-commercial
1156±13
2,352N/AN/A
334
319340
qwen-14b-chat
Alibaba · Qianwen LICENSE
1152±12
3,849N/AN/A
335
314341
Meta
codellama-70b-instruct
Meta · Llama 2 Community
1152±22
695$0.70 / $2.8016.4K
336
320340
stripedhyena-nous-7b
Together AI · Apache 2.0
1151±12
3,987$0.20 / $0.20N/A
337
326340
Meta
llama-2-7b-chat
Meta · Llama 2 Community
1146±8
10,259$0.15 / $0.154.1K
338
328340
mistral-7b-instruct
Mistral · Apache 2.0
1142±10
7,073$0.07 / $0.284.1K
339
331341
gemma-1.1-2b-it
Google · Gemma license
1138±10
5,934N/AN/A
340
332342
vicuna-7b
LMSYS · Llama 2 Community
1132±10
5,577$0.20 / $0.20N/A
341
338345
gemma-2b-it
Google · Gemma license
1118±13
3,028$0.10 / $0.10N/A
342
340348
olmo-7b-instruct
Ai2 · Apache-2.0
1110±13
4,043$0.20 / $0.20N/A
343
341348
qwen1.5-4b-chat
Alibaba · Qianwen LICENSE
1105±11
4,756$0.10 / $0.10N/A
344
341348
koala-13b
UC Berkeley · Non-commercial
1098±11
5,711N/AN/A
345
341348
gpt4all-13b-snoozy
Nomic AI · Non-commercial
1094±17
1,388N/AN/A
346
342348
alpaca-13b
Stanford · Non-commercial
1091±12
4,750N/AN/A
347
342348
mpt-7b-chat
MosaicML · CC-BY-NC-SA-4.0
1086±13
3,278N/AN/A
348
342348
chatglm3-6b
Tsinghua · Apache-2.0
1085±13
3,600N/AN/A
349
349351
RWKV-4-Raven-14B
RWKV · Apache 2.0
1058±13
3,997N/AN/A
350
349351
chatglm2-6b
Tsinghua · Apache-2.0
1055±15
2,059N/AN/A
351
349351
oasst-pythia-12b
OpenAssistant · Apache 2.0
1049±12
5,212N/AN/A
352
352353
fastchat-t5-3b
LMSYS · Apache 2.0
1022±13
3,442N/AN/A
353
352354
chatglm-6b
Tsinghua · Non-commercial
1014±14
4,055N/AN/A
354
353356
dolly-v2-12b
Databricks · MIT
993±15
2,765N/AN/A
355
354356
Meta
llama-13b
Meta · Non-commercial
982±17
1,953$0.23 / $0.23N/A
356
354356
Stability
stablelm-tuned-alpha-7b
Stability AI · CC-BY-NC-SA-4.0
975±14
2,707N/AN/A

Default Leaderboard Plots

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)

Confidence Intervals on Model Strength (via Bootstrapping)