Best LLM Models
/
Best LLMs for Coding
🤖
Agent
💬
Text
💻
Coding
🌐
Open source
🎨
Image
🎬
Video
Share
English
English
简体中文
繁體中文
العربية
Français
Deutsch
Light
Best LLM for coding on the Arena Text coding ladder. Human preference battles, not HumanEval.
All labs
Anthropic
OpenAI
Grok
Zhipu
DeepSeek
Google
Kimi
Alibaba
More labs
Unknown
Meta
Mistral
NVIDIA
Tencent
Amazon
IBM
Microsoft
Xiaomi
Ai2
Cohere
MiniMax
StepFun
Baidu
Ant Group
Inception
Meituan
Thinky
Upstage
ByteDance
reflection
#
Model
Score
Votes
Price
Context
1
Gemini 4 Argon (High)
1551.6
2,385
$4
/
$10
1049k
2
Claude Fable 5 (High)
1550.6
11,336
$10
/
$50
1M
3
Claude Opus 4.7 (High)
1550.5
18,580
$5
/
$25
1M
04
Claude Opus 5.5 (High)
1548.0
2,314
$4
/
$20
1M
05
Claude Opus 4.6
1547.2
24,319
$5
/
$25
1M
06
Claude Opus 4.6 (High)
1546.9
21,519
$5
/
$25
1M
07
Claude Opus 4.7
1546.3
18,781
$5
/
$25
1M
08
Muse Wonder (Max)
1544.7
1,469
$5
/
$25
1049k
09
GPT-6 Astra (Max)
1543.1
3,156
$10
/
$50
1050k
10
Muse Spark 1.2 (xHigh)
1541.3
2,687
$1.25
/
$4.25
1049k
11
Kimi K3 (Max)
1539.1
8,871
$3
/
$15
1049k
12
MiMo-V2.6-Pro
1537.6
1,102
$0.435
/
$0.87
1049k
13
Claude Fable 5.1 (Max)
1537.5
3,237
$10
/
$50
1M
14
GPT-6.1 Sol (Max)
1537.2
1,641
$2
/
$10
1050k
15
Muse Spark 1.3 (Max)
1535.8
5,259
$1.25
/
$4.25
1049k
16
Claude Opus 5 (High)
1533.9
18,182
$5
/
$25
1M
17
GPT-5.6 Sol (xHigh)
1533.6
11,350
$5
/
$30
1050k
18
Claude Opus 4.8 (High)
1533.3
17,411
$5
/
$25
1M
19
Muse Spark 1.1
1532.7
12,696
$1.25
/
$4.25
1049k
20
Claude Opus 4.5 (High, 32K, 20251101)
1530.2
7,783
$5
/
$25
200k
21
Claude Opus 4.8
1529.2
18,082
$5
/
$25
1M
22
Muse Spark
1528.8
3,942
—
—
23
Claude Opus 5 (Max)
1528.3
8,586
$5
/
$25
1M
24
Claude Sonnet 4.6
1528.2
19,726
$3
/
$15
1M
25
Gemini 3.8 Flash (High)
1528.1
11,350
$0.75
/
$3.75
1049k
26
Claude Sonnet 5.5 (xHigh)
1528.0
2,117
$2
/
$10
1M
27
GLM-5.3-Flash
1525.0
9,720
$0.15
/
$0.5
1M
28
Qwen3.7-Max-Preview
1524.1
1,165
$2.7
/
$8.05
1M
29
Qwen3.8-Max
1524.1
8,333
$2
/
$6
262k
30
DeepSeek-V4.1-Flash-20260910 (Max)
1523.3
3,760
$0.15
/
$0.6
1M
31
Claude Opus 4.5 (20251101)
1522.5
17,965
$5
/
$25
200k
32
Gemini 3.1 Pro Preview
1521.6
35,768
$2
/
$12
1049k
33
GLM-5.3 (Max)
1521.0
5,965
$1.4
/
$4.4
1M
34
GPT-5.4 (High)
1520.6
17,590
$2.5
/
$15
1050k
35
MiMo-V2.5-Pro
1520.5
20,881
$1
/
$3
1049k
36
Gemini 3.7 Flash (High)
1520.2
8,211
$0.75
/
$3.75
1049k
37
Claude Sonnet 5 (High)
1519.7
13,777
$2
/
$10
1M
38
GPT-6 Sol (Max)
1519.4
3,371
$2
/
$10
1050k
39
GPT-5.5 (High)
1518.9
19,144
$5
/
$30
1050k
40
Claude Sonnet 4.5 (High, 32K, 20250929)
1518.6
19,932
$3
/
$15
1M
41
Gemini 3.6 Flash (High)
1518.1
10,357
$1.5
/
$7.5
1049k
42
GPT-5.6 Terra (xHigh)
1517.8
12,237
$2
/
$12
1050k
43
Gemini 3 Pro
1517.2
8,807
$2
/
$12
1049k
44
Kimi K2.6
1515.6
11,097
$0.95
/
$4
262k
45
GPT-5.2 Chat (20260210)
1514.6
9,626
$1.75
/
$14
128k
46
GLM-5.2 (Max)
1514.3
13,954
$1.4
/
$4.4
1M
47
Dola Seed 2.0 Pro
1513.8
22,061
$0.63
/
$3.79
256k
48
Grok 4.5
1513.7
11,106
$2
/
$6
500k
49
GPT-5.5 Instant
1513.4
7,912
$5
/
$30
1050k
50
Qwen3.5-Max-Preview
1512.8
6,364
—
—
51
GLM-5.1
1512.5
17,686
$1.4
/
$4.4
200k
52
Claude Sonnet 4.5 (20250929)
1512.1
19,758
$3
/
$15
1M
53
Qwen3.6-Max-Preview
1511.7
1,617
$1.27
/
$7.61
240k
54
ERNIE 5.1
1511.6
10,918
$0.75
/
$3
119k
55
GPT-5.4
1511.2
18,934
$2.5
/
$15
1050k
56
Claude Opus 4.1 (Thinking 16K, 20250805)
1511.1
9,918
$15
/
$75
200k
57
MiMo-V2.6-Flash
1510.8
3,232
$0.14
/
$0.28
1049k
58
Grok 4.20 Beta (Reasoning, 0309)
1510.5
18,360
$1.25
/
$2.5
2M
59
GPT-5.5
1510.5
20,052
$5
/
$30
1050k
60
Grok 4.6 (High)
1509.7
7,973
$2
/
$6
500k
61
Grok 4.20 Multi-Agent Beta (0309)
1508.4
18,012
$1.25
/
$2.5
2M
62
Gemini 3.5 Flash (High)
1508.0
13,851
$1.5
/
$9
1049k
63
Grok 4.20 Beta 1
1507.7
7,489
$1.25
/
$2.5
2M
64
Step 5 Preview
1507.4
2,331
$1
/
$2.7
1024k
65
GPT-6 Luna (Max)
1506.6
16,451
$0.1
/
$0.5
1050k
66
Gemini 3.5 Flash (Medium)
1506.0
13,613
$1.5
/
$9
1049k
67
Gemini 3 Flash
1505.5
6,587
$0.5
/
$3
1M
68
DeepSeek-V4-Pro (High, 20260813)
1504.8
2,804
$1
/
$2.5
1049k
69
Claude Opus 4.1 (20250805)
1504.6
15,680
$15
/
$75
200k
70
Kimi K2.5 (Instant)
1504.1
1,870
$0.627
/
$3.3
262k
71
Beam 1.0 501B A23B
1503.5
1,011
$0.25
/
$1
1049k
72
MiMo-V2-Pro
1503.1
7,266
$1
/
$3
1049k
73
Hy3
1502.9
3,589
$0.132
/
$0.528
262k
74
Gemma 4 31B
1502.4
1,416
$0.144
/
$0.42
262k
75
Kimi K2.5 (Thinking)
1502.1
20,771
$0.627
/
$3.3
262k
76
GPT-5.6 Luna (xHigh)
1501.9
11,215
$0.2
/
$1.2
1050k
77
Gemini 3.5 Flash-Lite
1501.6
9,922
$0.3
/
$2.5
1049k
78
LongCat-Flash-Chat Exp (2602)
1501.2
8,154
—
131k
79
DeepSeek V4 Pro
1500.6
17,142
$0.66
/
$1.98
1M
80
Qwen 3.7 Plus
1500.5
12,179
$0.4
/
$1.6
1M
81
Grok 4.1 (Thinking)
1499.8
15,412
$2
/
$10
200k
82
Qwen3.8 27B
1499.4
7,134
$0.5
/
$3
1M
83
Claude Opus 4 (Thinking 16K, 20250514)
1498.3
6,595
$13
/
$64
193k
84
Mistral Large 4
1497.9
2,345
$0.68
/
$2.09
1049k
85
GLM-5
1497.8
7,627
$1
/
$3.2
205k
86
GPT-5.3 Chat
1497.2
9,173
$1.75
/
$14
128k
87
Qwen 3.6 Plus
1495.9
14,679
$0.5
/
$3
1M
88
MiniMax-M3
1495.6
18,951
$0.3
/
$1.2
1049k
89
GPT-5.4 mini (High)
1494.5
17,237
$0.75
/
$4.5
400k
90
Inkling
1493.4
11,839
$1
/
$4.05
1049k
91
Grok 4.7 (xHigh)
1493.3
3,213
$2
/
$6
500k
92
Grok 4.1
1492.3
16,016
$2
/
$10
200k
93
GPT-5.1 (High)
1491.8
8,408
$1.25
/
$10
400k
94
Qwen3.5 397B-A17B
1491.6
27,099
$0.6
/
$3.6
262k
95
MiMo-V2.5
1490.9
13,661
$0.4
/
$2
1049k
96
Gemini 3 Flash (Minimal)
1489.7
23,971
$0.5
/
$3
1M
97
ERNIE 5.0 (0110)
1489.6
8,958
$0.84
/
$3.37
128k
98
GPT-5.2 (High)
1489.1
12,235
$1.75
/
$14
400k
99
MiMo-V2-Omni
1488.2
5,893
—
—
100
DeepSeek-V4-Pro Preview (High)
1488.2
16,004
$1
/
$2.5
1049k
101
GLM-5V-Turbo
1488.1
2,941
$1.2
/
$4
200k
102
Grok 4.3
1487.6
19,940
$1.25
/
$2.5
1M
103
amazon-nova-experimental-chat (26-02-10)
1486.7
881
—
—
104
Kimi K2 Thinking Turbo
1486.4
15,272
$0.575
/
$2.3
262k
105
Claude Haiku 5.5 (High)
1485.4
1,370
$0.1
/
$0.5
1M
106
DeepSeek V4 Flash
1484.1
15,295
$0.22
/
$0.66
1M
107
GLM-4.7
1483.8
2,481
$0.6
/
$2.2
205k
108
Gemma 4 26B A4B
1482.5
1,443
$0.05
/
$0.29
262k
109
GPT-5.2
1482.0
22,115
$1.75
/
$14
400k
110
Claude Haiku 4.5 (20251001)
1481.7
39,183
$1
/
$5
200k
111
amazon-nova-experimental-chat (26-01-10)
1481.7
778
—
—
112
Qwen3-Max-Preview
1480.3
5,366
$0.86956522
/
$3.47826087
256k
113
MiniMax-M2.7
1480.1
24,774
$0.3
/
$1.2
205k
114
DeepSeek-V4-Flash Preview (High)
1479.6
15,240
$0.39
/
$1.56
1M
115
Muse Glimmer
1478.4
1,117
—
—
116
Mistral Medium 3.5
1477.8
3,297
$1.5
/
$7.5
262k
117
GPT-5.1
1475.7
9,352
$1.25
/
$10
400k
118
DeepSeek-V3.2 (Thinking)
1475.5
8,880
$0.62
/
$1.85
164k
119
DeepSeek-V3.2-Exp (Thinking)
1474.5
1,929
$0.28
/
$0.42
164k
120
Claude Sonnet 4 (Thinking 32K, 20250514)
1474.2
6,344
$2.6
/
$13
983k
121
NVIDIA-Nemotron-3-Ultra-550B-A55B (NVFP4)
1473.1
3,187
$0.625
/
$3.125
256k
122
Qwen3-Max (2025-09-23)
1473.0
2,030
$1.2
/
$6
262k
123
ERNIE-5.0-Preview (1203)
1472.0
1,995
$0.84
/
$3.37
128k
124
Qwen3-235B-A22B-Instruct (2507)
1471.7
21,728
$0.13
/
$0.6
262k
125
Meituan/Longcat-Flash-Chat
1471.5
2,209
—
131k
126
Mistral Large 3
1471.1
21,836
$0.5
/
$1.5
262k
127
GPT-5 (High)
1471.0
6,398
$1.25
/
$10
400k
128
Inkling Small
1470.7
9,560
$0.45
/
$1.2
524k
129
DeepSeek V3.2
1469.6
10,913
$0.293
/
$0.4395
128k
130
Kimi K2 Preview (0905)
1467.5
2,232
$0.57
/
$2.3
256k
131
DeepSeek-V3.2-Exp
1467.0
2,550
$0.22
/
$0.33
163k
132
ChatGPT-4o Latest (20250326)
1466.7
15,871
$4.5
/
$14
128k
133
Claude Opus 4 (20250514)
1464.6
7,828
$13
/
$64
193k
134
Gemini 2.5 Pro
1464.3
26,939
$1.25
/
$10
1M
135
DeepSeek-R1 (0528)
1464.0
2,690
$3
/
$7
164k
136
Qwen3 VL 235B A22B Instruct
1462.7
2,311
$0.2
/
$0.88
262k
137
Grok 4.1 Fast (Reasoning)
1461.4
13,907
$0.2
/
$0.5
2M
138
GPT-5 Chat
1461.4
5,986
$1.1
/
$9
128k
139
Solar Pro 4
1461.4
6,256
$0.3
/
$1.2
524k
140
GPT-5.4 nano (High)
1460.3
17,657
$0.2
/
$1.25
400k
141
o3 (2025-04-16)
1460.3
11,581
$2
/
$8
200k
142
Kimi K2 Preview (0711)
1459.5
5,193
$0.57
/
$2.3
256k
143
DeepSeek-V3.1-Terminus (Thinking)
1459.1
632
$0.27
/
$1
128k
144
Qwen3.5 122B A10B (Alibaba Cloud)
1458.5
8,175
$0.4
/
$3.2
262k
145
GLM-4.6
1457.9
7,598
$0.6
/
$2.2
205k
146
GPT-4.5 Preview (2025-02-27)
1457.8
1,939
$2.5
/
$15
1050k
147
Gemini 3.1 Flash-Lite Preview
1457.6
17,850
$0.25
/
$1.5
1049k
148
Grok 4 Fast (Non-Reasoning)
1457.1
1,183
$0.2
/
$0.5
2M
149
NVIDIA-Nemotron-3.5-Super-VL-120B-A12B (NVFP4)
1457.0
997
$0.15
/
$0.5
1049k
150
Qwen3 Coder
1456.7
4,808
$1.058
/
$5.15775
262k
151
GPT-4.1 (2025-04-14)
1455.8
9,245
$2
/
$8
1048k
152
DeepSeek-V3.1 (Thinking)
1455.0
1,874
$0.2
/
$0.8
75k
153
GLM-4.5
1454.5
4,739
$0.6
/
$2.2
131k
154
Mistral Medium 3.1 (2508)
1453.4
21,550
$0.4
/
$2
262k
155
Hy3 preview
1452.6
2,054
$0.17
/
$0.566661
256k
156
Claude 3.7 Sonnet (Thinking 32K, 20250219)
1452.0
6,135
$3
/
$15
200k
157
Qwen3 VL 235B A22B Thinking
1451.8
1,638
$0.98
/
$3.95
131k
158
Qwen3.5 27B (Alibaba Cloud)
1451.5
7,939
$0.3
/
$2.4
262k
159
Step 3.5 Flash
1449.1
15,189
$0.1
/
$0.3
256k
160
Claude Sonnet 4 (20250514)
1448.8
7,307
$2.6
/
$13
983k
161
DeepSeek V3.1
1447.3
2,603
$0.27
/
$1
164k
162
MiMo-V2-Flash (Non-Thinking)
1447.0
12,449
$0.1
/
$0.3
256k
163
MiniMax M2.5
1446.3
11,339
$0.3
/
$1.2
205k
164
Qwen3 Next 80B A3B Instruct
1444.3
4,811
$0.15
/
$1.2
262k
165
Qwen3-235B-A22B (Non-Thinking)
1444.3
6,913
$0.0875
/
$0.35
262k
166
DeepSeek-R1
1443.8
2,317
$1.35
/
$5.4
128k
167
Trinity Large Preview
1442.9
7,981
$0
/
$0
131k
168
Grok 3 Preview (02-24)
1442.2
5,359
$3
/
$15
131k
169
Qwen3-235B-A22B-Thinking (2507)
1441.6
1,591
$0.3
/
$2.9
262k
170
DeepSeek: DeepSeek V3.1 Terminus
1440.0
770
$0.27
/
$1
164k
171
Grok 4 Fast (Reasoning)
1438.7
3,938
$0.2
/
$0.5
2M
172
MiniMax-M2.1 Preview
1437.5
3,480
$0.27
/
$1.1
205k
173
Qwen3-30B-A3B-Instruct (2507)
1437.4
4,613
—
—
174
Hunyuan Vision 1.5 Thinking
1436.2
419
—
—
175
Claude 3.5 Sonnet (20241022)
1435.6
14,908
—
200k
176
Qwen 3.5 Flash
1435.5
17,730
$0.1
/
$0.4
1M
177
Grok 4 (0709)
1435.0
8,036
$3
/
$15
256k
178
Qwen3.5 35B A3B (Alibaba Cloud)
1434.4
8,386
$0.25
/
$2
262k
179
o3-mini (High)
1434.2
2,596
$1.1
/
$4.4
200k
180
amazon-nova-experimental-chat (12-10)
1433.7
724
—
—
181
o4-mini (2025-04-16)
1433.0
8,647
$1.1
/
$4.4
200k
182
GPT-4.1 mini (2025-04-14)
1432.8
6,821
$0.4
/
$1.6
1048k
183
o1 (2024-12-17)
1432.6
3,973
$15
/
$60
200k
184
MiMo-V2-Flash (Thinking)
1432.4
2,487
$0.1
/
$0.3
256k
185
Mistral Medium 3 (2505)
1432.3
5,840
$0.4
/
$2
128k
186
ERNIE-5.0-Preview (1022)
1432.0
932
$0.84
/
$3.37
128k
187
GPT-5 mini (High)
1431.8
5,515
$0.25
/
$2
400k
188
Qwen3-235B-A22B
1431.5
4,322
$0.29
/
$2.86
128k
189
Claude 3.7 Sonnet (20250219)
1431.3
7,074
$3
/
$15
200k
190
DeepSeek-V3 (0324)
1427.8
8,333
$0.89
/
$0.89
64k
191
Gemini 2.5 Flash Preview (09-2025)
1427.1
6,913
$0.15
/
$0.6
1049k
192
NVIDIA-Nemotron-3.5-Lightning-30B-A3B (NVFP4)
1426.7
5,538
$0.07
/
$0.2
262k
193
GLM-4.5-Air
1426.6
6,098
$0.2
/
$1.1
131k
194
Gemini 2.5 Flash
1423.6
26,359
$0.3
/
$2.5
1M
195
GLM-4.7-Flash
1422.9
2,794
$0
/
$0
200k
196
Qwen3 Next 80B A3B Thinking
1421.1
2,666
$0.15
/
$1.2
262k
197
amazon-nova-experimental-chat (11-10)
1420.0
5,513
—
—
198
OpenAI o3-mini
1416.4
9,399
$1.1
/
$4.4
200k
199
MiniMax: MiniMax M1
1416.2
6,400
$0.55
/
$2.2
1M
200
o1
1415.3
5,123
$15
/
$60
200k
201
GLM-4.6V
1415.2
543
$0.3
/
$0.9
128k
202
INTELLECT-3
1415.0
1,004
—
—
203
Trinity Large Thinking
1412.6
8,541
—
—
204
Mistral Small 3.2 (2506)
1411.3
3,337
$0.075
/
$0.2
128k
205
amazon-nova-experimental-chat (10-20)
1410.0
2,337
—
—
206
inclusionAI/Ling-flash-2.0
1409.3
1,543
$0.14
/
$0.57
131k
207
Step-3
1409.3
1,213
—
—
208
Nemotron 3 Super 120B A12B
1407.0
1,882
$0.3
/
$2.4
262k
209
Qwen3 32B
1406.0
513
$0.36
/
$0.87
41k
210
Llama 3.3 Nemotron Super 49B v1.5
1402.8
653
$0.4
/
$0.4
131k
211
GLM-4.5V
1402.5
965
$0.6
/
$1.8
64k
212
Qwen2.5-Max
1401.4
5,089
$1.5997
/
$6.392
32k
213
Hunyuan T1 (20250711)
1400.6
806
$0
/
$0
131k
214
Granite 4.2 30B
1399.5
851
—
—
215
Claude 3.5 Sonnet (20240620)
1399.2
13,607
—
200k
216
Hunyuan TurboS (20250226)
1398.6
275
$0
/
$0
131k
217
Gemini 2.5 Flash-Lite Preview (Non-Thinking, 09-2025)
1397.5
9,855
$0.15
/
$0.6
1049k
218
Hunyuan TurboS (20250416)
1394.3
1,764
$0
/
$0
131k
219
Amazon Nova 2 Lite
1392.6
2,580
$0.3
/
$2.5
1M
220
Grok 3 Mini (High)
1392.5
3,163
$0.3
/
$0.5
131k
221
Mercury 2
1391.5
800
$0.25
/
$0.75
128k
222
amazon-nova-experimental-chat (10-09)
1391.4
543
—
—
223
Llama 3.1 Nemotron Ultra 253B v1
1390.6
367
$0
/
$0
128k
224
Ring-flash-2.0
1389.9
1,507
—
—
225
GPT OSS 120B
1389.2
6,410
$0.15
/
$0.6
131k
226
Command A (03-2025)
1388.6
10,235
$2.5
/
$10
256k
227
Magistral Medium (2506)
1387.0
2,244
$2
/
$5
262k
228
DeepSeek V3
1386.7
3,280
$0.27
/
$1.1
164k
229
Grok 3 Mini Beta
1386.4
4,095
$0.3
/
$0.5
131k
230
OpenAI: o1-mini
1385.6
8,478
$1.1
/
$4.4
128k
231
Claude 3.5 Haiku (20241022)
1385.5
11,143
$0.8
/
$4
200k
232
GPT-5 nano (High)
1384.7
1,665
$0.05
/
$0.4
400k
233
Qwen3-30B-A3B
1384.6
4,504
$0.11
/
$1.08
128k
234
QwQ 32B
1382.6
4,017
$0.4
/
$0.4
33k
235
MiniMax M2
1382.6
1,548
$0.3
/
$1.2
204k
236
Gemini 2.5 Flash-Lite Preview (Thinking, 06-17)
1382.4
5,979
$0.15
/
$0.6
1049k
237
Olmo 3.1 32B Instruct
1382.2
2,461
—
—
238
Granite 4.2 3B
1379.0
833
—
—
239
Qwen-Plus (0125)
1378.5
893
$0.4
/
$1.2
131k
240
Llama 3.1 405B Instruct (BF16)
1376.2
6,249
—
—
241
DeepSeek-V2.5 (1210)
1373.6
1,079
—
—
242
GPT-4.1 nano (2025-04-14)
1372.9
807
$0.1
/
$0.4
1048k
243
Llama 4 Maverick 17B 128E Instruct
1372.4
6,938
$0.35
/
$1.15
524k
244
Step-2 16K Exp (202412)
1370.2
737
—
—
245
Hunyuan Turbo (0110)
1370.2
299
—
—
246
Granite 4.2 8B
1369.9
828
$0.06
/
$0.25
131k
247
Llama 3.1 405B Instruct (FP8)
1368.9
9,714
—
—
248
GPT-4o (2024-05-13)
1368.8
19,526
$2.5
/
$10
128k
249
Athene V2 Chat
1368.4
4,019
—
—
250
Yi Lightning
1368.4
4,316
—
—
251
GPT OSS 20B
1368.3
2,112
$0.07
/
$0.25
131k
252
DeepSeek-V2.5
1367.5
4,252
—
—
253
Hunyuan Large (2025-02-10)
1365.6
519
—
—
254
Mercury
1364.8
412
—
—
255
Gemini 2.0 Flash (001)
1363.3
6,960
$0.1
/
$0.42
990k
256
Llama 4 Scout 17B 16E Instruct
1362.5
5,229
$0.2
/
$0.78
128k
257
Llama 3.3 Nemotron Super 49B v1
1361.7
286
$0.15
/
$0.15
128k
258
NVIDIA-Nemotron-3-Nano-30B-A3B (BF16)
1360.9
3,332
$0.075
/
$0.3
128k
259
Mistral Small 3.1 24B Instruct (2503)
1360.7
6,112
$0.351
/
$0.555
128k
260
Olmo 3 32B Think
1360.0
1,042
—
—
261
GPT-4o (2024-08-06)
1359.6
7,318
$2.5
/
$10
128k
262
Hunyuan Large Vision
1358.1
957
—
—
263
Grok 2 (2024-08-13)
1357.6
10,368
—
—
264
Gemma 3 27B IT
1357.5
8,024
$0.23
/
$0.38
131k
265
Qwen2.5-Plus (1127)
1356.1
1,553
—
—
266
Gemini 1.5 Pro (002)
1356.0
9,175
—
—
267
Claude 3 Opus (20240229)
1355.1
33,748
—
—
268
Qwen2.5 72B Instruct
1354.7
6,688
$0.36
/
$0.4
33k
269
Mistral Large 2 (2407)
1353.5
7,589
$2
/
$6
128k
270
Granite 4.1 8B
1352.5
1,097
—
—
271
Qwen-Max (0919)
1352.2
2,756
$1.6
/
$6.4
33k
272
GLM-4-Plus
1351.5
4,449
—
—
273
Step-1o Turbo (202506)
1351.0
1,494
—
—
274
Athene 70B (0725)
1349.3
3,122
—
—
275
GPT-4o mini (2024-07-18)
1347.6
10,928
$0.15
/
$0.6
128k
276
GPT-4 Turbo (2024-04-09)
1346.8
17,104
$10
/
$30
128k
277
Gemini 1.5 Pro (001)
1346.1
12,747
—
—
278
Mistral Large (2411)
1345.7
4,212
$2
/
$6
128k
279
Llama 3.3 70B Instruct
1345.7
8,735
$0.72
/
$0.72
128k
280
Amazon Nova Pro 1.0
1342.5
3,853
$0.8
/
$3.2
300k
281
Gemini 2.0 Flash-Lite Preview (02-05)
1342.3
3,474
$0.075
/
$0.3
2M
282
DeepSeek-Coder-V2
1342.0
2,671
—
—
283
Qwen2.5 Coder 32B Instruct
1341.8
873
$0.66
/
$1
33k
284
Olmo 3.1 32B Think
1340.8
1,554
—
—
285
GPT-4 Turbo Preview (1106)
1340.2
15,605
$10
/
$30
128k
286
Gemini Advanced (0514)
1336.5
8,138
—
—
287
Grok 2 mini (2024-08-13)
1334.1
8,652
—
—
288
Llama 3.1 70B Instruct
1333.0
9,389
$0.72
/
$0.72
128k
289
GPT-4 Turbo Preview (0125)
1331.7
15,289
$10
/
$30
128k
290
Hunyuan Standard (2025-02-10)
1330.9
549
—
—
291
Granite-4.0-H-Small
1330.3
1,287
$0.0636
/
$0.265
131k
292
GLM-4-Plus (0111)
1330.0
894
—
—
293
GPT-4 (0314)
1329.8
8,306
$30
/
$60
8k
294
Llama 3.1 Nemotron 70B Instruct
1327.7
1,312
$0
/
$0
128k
295
Claude 3 Sonnet (20240229)
1318.1
18,888
—
—
296
Gemini 1.5 Flash (002)
1316.0
5,892
—
—
297
Gemma 3 12B IT
1315.7
543
$0.09
/
$0.29
131k
298
Reka Core (20240904)
1315.2
1,216
—
—
299
GPT-4 (0613)
1314.4
13,719
$30
/
$60
8k
300
Llama 3.1 Nemotron 51B Instruct
1312.0
665
—
—
301
Mistral Small 24B Instruct (2501)
1311.9
2,083
—
—
302
Jamba 1.5 Large
1311.8
1,440
—
—
303
GLM-4 (0520)
1308.9
1,718
—
—
304
Gemini 1.5 Flash (001)
1308.7
10,680
—
—
305
Nemotron-4 340B Instruct
1308.6
3,254
—
—
306
Llama 3.1 Tulu 3 70B
1307.8
450
—
—
307
Gemma 3n E4B IT
1306.9
3,488
—
—
308
Llama 3 70B Instruct
1306.0
28,126
—
—
309
Microsoft: Phi 4
1305.7
3,305
$0.056
/
$0.112
16k
310
Amazon Nova Lite 1.0
1305.4
3,060
$0.06
/
$0.24
300k
311
Gemma 2 27B IT
1303.9
12,088
$0.65
/
$0.65
8k
312
Claude 3 Haiku (20240307)
1301.1
20,898
$0.25
/
$1.25
200k
313
Hunyuan Standard 256K
1300.2
497
—
—
314
Qwen2-72B-Instruct
1297.2
6,249
—
—
315
Mistral Large (2402)
1295.5
10,418
$2
/
$6
128k
316
Aya Expanse 32B
1292.1
4,685
$0.5
/
$1.5
128k
317
Reka Flash (20240904)
1291.6
1,207
—
—
318
Amazon Nova Micro 1.0
1288.2
2,981
$0.035
/
$0.14
128k
319
Granite 3.1 8B Instruct
1288.2
478
—
—
320
Command R (08-2024)
1281.4
1,783
$0.15
/
$0.6
128k
321
Command R+ (08-2024)
1280.2
1,675
$0.15
/
$0.6
128k
322
Qwen1.5-110B-Chat
1279.6
4,763
—
—
323
OLMo 2 32B Instruct (0325)
1279.5
427
—
—
324
Reka Flash 21B (Online, 20240226)
1278.1
2,879
—
—
325
Mixtral 8x22B Instruct v0.1
1277.6
8,780
$2
/
$6
66k
326
Qwen1.5-72B-Chat
1275.2
6,370
—
—
327
GPT-3.5 Turbo (0125)
1274.8
11,130
$0.5
/
$1.5
16k
328
Ministral 8B (2410)
1274.1
838
$0.15
/
$0.15
262k
329
Gemma 3 4B IT
1273.4
605
$0.04
/
$0.08
131k
330
Command R+
1273.0
13,937
$0.15
/
$0.6
128k
331
Gemini 1.5 Flash-8B (001)
1271.2
6,069
—
—
332
Gemma 2 9B IT SimPO
1270.6
1,471
—
—
333
Gemma 2 9B IT
1269.7
8,921
$0.01
/
$0.03
8k
334
Reka Flash 21B (20240226)
1267.2
4,748
—
—
335
Jamba 1.5 Mini
1264.3
1,352
—
—
336
Mistral Medium
1262.6
5,149
$0.44
/
$2.2
131k
337
GPT-3.5 Turbo (1106)
1262.4
2,121
$0.5
/
$1.5
16k
338
Qwen1.5-32B-Chat
1262.2
3,930
—
—
339
Llama 3.1 8B Instruct
1259.4
8,582
$0.22
/
$0.22
128k
340
Aya Expanse 8B
1254.9
1,567
—
—
341
Llama 3 8B Instruct
1253.1
18,374
—
—
342
Llama 3.1 Tulu 3 8B
1252.6
476
—
—
343
DBRX Instruct Preview
1251.3
5,502
—
—
344
Granite 3.1 2B Instruct
1249.0
508
—
—
345
InternLM2.5 20B Chat
1248.7
1,684
—
—
346
Gemini Pro
1248.6
678
—
—
347
Yi 1.5 34B Chat
1248.4
3,841
—
—
348
Zephyr ORPO 141B A35B v0.1
1245.2
831
—
—
349
Command R
1243.4
9,645
$0.15
/
$0.6
128k
350
Granite 3.0 8B Instruct
1240.5
1,108
—
—
351
Qwen1.5-14B-Chat
1239.7
3,208
—
—
352
Mixtral 8x7B Instruct v0.1
1239.7
11,784
$0.488
/
$0.758
32k
353
Gemini Pro (Dev API)
1239.3
2,681
—
—
354
Starling LM 7B Beta
1235.6
2,948
—
—
355
Phi-3 Medium 4K Instruct
1231.3
3,973
—
—
356
OpenChat 3.5 (0106)
1229.9
2,005
—
—
357
Snowflake Arctic Instruct
1224.7
5,734
—
—
358
DeepSeek LLM 67B Chat
1218.2
649
—
—
359
Gemma 1.1 7B IT
1215.7
4,332
—
—
360
Tulu 2 DPO 70B
1215.1
805
—
—
361
Qwen1.5-7B-Chat
1209.6
772
—
—
362
Granite 3.0 2B Instruct
1209.6
1,134
—
—
363
Starling LM 7B Alpha
1207.6
1,397
—
—
364
Yi 34B Chat
1205.6
2,345
—
—
365
Phi-3 Small 8K Instruct
1205.0
3,219
—
—
366
OpenChat 3.5
1202.6
971
—
—
367
Qwen-14B-Chat
1197.7
599
—
—
368
Phi-3 Mini 4K Instruct (June 2024)
1197.0
1,841
—
—
369
Vicuna 33B
1193.6
2,866
—
—
370
WizardLM 70B
1193.5
988
—
—
371
Gemma 2 2B IT
1191.6
7,298
—
—
372
Phi-3 Mini 4K Instruct
1187.5
3,449
—
—
373
OpenHermes 2.5 Mistral 7B
1186.7
589
—
—
374
Mistral 7B Instruct v0.2
1185.9
3,114
$0.159
/
$0.219
32k
375
SOLAR 10.7B Instruct v1.0
1183.6
482
—
—
376
Llama 2 70B Chat
1179.2
5,717
—
—
377
Llama 3.2 3B Instruct
1176.5
1,351
$0.02
/
$0.02
16k
378
Nous Hermes 2 Mixtral 8x7B DPO
1175.7
575
—
—
379
QwQ 32B
1173.7
566
$0.4
/
$0.4
33k
380
Gemma 1.1 2B IT
1170.6
1,963
—
—
381
MPT 30B Chat
1168.0
258
—
—
382
Zephyr 7B Alpha
1166.9
201
—
—
383
Gemma 7B IT
1166.6
1,381
—
—
384
Vicuna 13B
1163.4
2,389
—
—
385
Llama 2 13B Chat
1162.6
2,626
—
—
386
SmolLM2 1.7B Instruct
1160.1
352
—
—
387
Code Llama 34B Instruct
1159.5
853
—
—
388
Phi-3 Mini 128K Instruct
1154.6
3,886
—
—
389
PaLM 2
1153.1
917
—
—
390
Zephyr 7B Beta
1152.8
1,250
—
—
391
WizardLM 13B
1151.8
735
—
—
392
Llama 3.2 1B Instruct
1149.3
1,346
$0.027
/
$0.201
60k
393
Llama 2 70B SteerLM Chat
1145.7
467
—
—
394
Mistral 7B Instruct
1144.7
1,032
—
—
395
Gemma 2B IT
1135.7
742
—
—
396
Vicuna 7B
1131.8
726
—
—
397
Qwen1.5-4B-Chat
1131.6
1,283
—
—
398
StripedHyena Nous 7B
1127.5
704
—
—
399
Guanaco 33B
1113.8
263
—
—
400
OLMo 7B Instruct
1107.4
772
—
—
401
Llama 2 7B Chat
1103.1
1,956
—
—
402
ChatGLM3 6B
1090.3
535
—
—
403
Koala 13B
1066.2
747
—
—
404
MPT 7B Chat
1066.1
397
—
—
405
RWKV-4 Raven 14B
1059.6
505
—
—
406
OpenAssistant Pythia 12B
1050.2
714
—
—
407
ChatGLM 6B
1035.8
551
—
—
408
ChatGLM2 6B
1030.7
293
—
—
409
StableLM Tuned Alpha 7B
1004.9
363
—
—
410
Alpaca 13B
999.0
626
—
—
411
Dolly 2.0 12B
962.2
396
—
—
412
FastChat-T5 3B
907.9
428
—
—
413
LLaMA 13B
882.6
304
—
—
Best LLM Models