RankModelProviderScore (0-100)SamplesContextPrice / 1M tokens
1
A
claude-opus-4-7 Anthropic
100.0
6.8K
1M
¥36 / ¥180Input/Output
2
A
claude-opus-4-7-thinking Anthropic
99.2
6.5K
1M
¥36 / ¥180Input/Output
3
A
claude-opus-4-6-thinking Anthropic
98.4
7.1K
1M
¥36 / ¥180Input/Output
4
A
claude-opus-4-6 Anthropic
97.6
8.5K
1M
¥36 / ¥180Input/Output
5
M
muse-spark Meta
96.8
4.5K
-
-
6
G
gemini-3-pro Google
96.0
13.2K
1.05M
¥14.4 / ¥86.4Input/Output
7
G
gemini-3.1-pro-preview Google
95.2
16.8K
1.05M
¥14.4 / ¥86.4Input/Output
8
O
gpt-5.4-high Openai
94.4
5.9K
1.05M
¥18 / ¥108Input/Output
9
O
gpt-5.5 Openai
93.6
4.7K
1.05M
¥36 / ¥216Input/Output
10
O
gpt-5.5-high Openai
92.8
4.2K
1.05M
¥36 / ¥216Input/Output
11
O
gpt-5.4 Openai
92.0
5.6K
1.05M
¥18 / ¥108Input/Output
12
G
gemini-3-flash Google
91.2
21.2K
1.05M
¥3.6 / ¥21.6Input/Output
13
A
claude-sonnet-4-6 Anthropic
90.4
8.9K
1M
¥21.6 / ¥108Input/Output
14
M
kimi-k2.6 Moonshot
89.6
5.6K
262K
¥6.84 / ¥28.8Input/Output
15
B
dola-seed-2.0-pro Bytedance
88.8
8.9K
-
-
16
A
qwen3.7-plus-preview Alibaba
88.0
3.6K
131K
¥3.6 / ¥21.6Input/Output
17
O
gpt-5.2-chat-latest-20260210 Openai
87.2
12.5K
400K
¥12.6 / ¥101Input/Output
18
M
kimi-k2.5-thinking Moonshot
86.4
14.4K
262K
¥4.32 / ¥21.6Input/Output
19
G
gemini-3-flash (thinking-minimal) Google
85.6
19.3K
1.05M
¥3.6 / ¥21.6Input/Output
20
Z
glm-5v-turbo Zai
84.8
7.5K
200K
¥0 / ¥0Input/Output
21
G
gemini-2.5-pro Google
84.0
87.2K
1.05M
¥9 / ¥72Input/Output
22
G
gemma-4-31b Google
83.2
17.3K
262K
¥3.24 / ¥7.2Input/Output
23
A
qwen3.5-397b-a17b Alibaba
82.4
11.8K
262K
¥3.1 / ¥18.6Input/Output
24
G
gemma-4-26b-a4b Google
81.6
10.7K
262K
¥0.94 / ¥2.88Input/Output
25
X
grok-4.20-beta-0309-reasoning Xai
80.8
9.6K
2M
¥14.4 / ¥43.2Input/Output
26
M
kimi-k2.5-instant Moonshot
80.0
3.9K
262K
¥4.32 / ¥21.6Input/Output
27
X
grok-4.20-multi-agent-beta-0309 Xai
79.2
8.9K
2M
¥14.4 / ¥43.2Input/Output
28
G
gemini-2.5-flash-preview-09-2025 Google
78.4
4.7K
1M
¥2.16 / ¥18Input/Output
29
O
gpt-5.1-high Openai
77.6
9.2K
400K
¥9 / ¥72Input/Output
30
B
ernie-5.0-preview-1220 Baidu
76.8
3.2K
128K
¥7.92 / ¥14.4Input/Output
31
O
gpt-5.5-instant Openai
76.0
3.6K
400K
¥9 / ¥72Input/Output
32
A
qwen3-vl-235b-a22b-instruct Alibaba
75.2
12.2K
128K
¥2.16 / ¥8.64Input/Output
33
O
gpt-5.2-high Openai
74.4
15.2K
400K
¥12.6 / ¥101Input/Output
34
O
gpt-5.4-mini-high Openai
73.6
8.6K
400K
¥5.4 / ¥32.4Input/Output
35
O
chatgpt-4o-latest-20250326 Openai
72.8
23.4K
128K
¥18 / ¥72Input/Output
36
MI
mimo-v2.5 Xiaomi
72.0
6.9K
1.05M
¥2.88 / ¥14.4Input/Output
37
G
gemini-3.1-flash-lite-preview Google
71.2
14K
1.05M
¥1.8 / ¥10.8Input/Output
38
X
grok-4.3 Xai
70.4
3.9K
1M
¥9 / ¥18Input/Output
39
A
qwen3.5-122b-a10b Alibaba
69.6
10.1K
262K
¥2.88 / ¥23Input/Output
40
A
qwen3.5-27b Alibaba
68.8
9.4K
262K
¥2.16 / ¥17.3Input/Output
41
G
gemini-2.5-flash Google
68.0
57.5K
1.05M
¥2.16 / ¥18Input/Output
42
O
gpt-5.1 Openai
67.2
10.1K
400K
¥9 / ¥72Input/Output
43
O
gpt-5-chat Openai
66.4
40.8K
400K
¥9 / ¥72Input/Output
44
O
gpt-5.2 Openai
65.6
16.1K
400K
¥12.6 / ¥101Input/Output
45
MI
mimo-v2-omni Xiaomi
64.8
7.5K
262K
¥2.88 / ¥14.4Input/Output
46
O
o3-2025-04-16 Openai
64.0
46.7K
200K
¥14.4 / ¥57.6Input/Output
47
A
qwen-vl-max-2025-08-13 Alibaba
63.2
3.2K
131K
¥1.66 / ¥4.13Input/Output
48
O
gpt-5-high Openai
62.4
35.1K
400K
¥9 / ¥72Input/Output
49
O
gpt-4.1-2025-04-14 Openai
61.6
42.1K
1.05M
¥14.4 / ¥57.6Input/Output
50
X
grok-4-0709 Xai
60.8
32.8K
256K
¥21.6 / ¥108Input/Output
51
A
qwen3-vl-235b-a22b-thinking Alibaba
60.0
2.4K
131K
¥2.06 / ¥8.26Input/Output
52
O
gpt-5-mini-high Openai
59.2
29.6K
400K
¥1.8 / ¥14.4Input/Output
53
G
gemini-2.5-flash-lite-preview-09-2025-no-thinking Google
58.4
4.8K
1.05M
¥0.72 / ¥2.88Input/Output
54
X
grok-4-1-fast-reasoning Xai
57.6
10.6K
2M
¥1.44 / ¥3.6Input/Output
55
O
gpt-5.4-nano-high Openai
56.8
8.6K
400K
¥1.44 / ¥9Input/Output
56
O
gpt-4.5-preview-2025-02-27 Openai
56.0
2.9K
8.19K
¥216 / ¥432Input/Output
57
O
o4-mini-2025-04-16 Openai
55.2
42.4K
200K
¥7.92 / ¥31.7Input/Output
58
A
claude-sonnet-4-20250514-thinking-32k Anthropic
54.4
1.2K
200K
¥21.6 / ¥108Input/Output
59
A
claude-opus-4-20250514-thinking-16k Anthropic
53.6
1.3K
200K
¥108 / ¥540Input/Output
60
G
gemini-2.5-flash-lite-preview-06-17-thinking Google
52.8
36.9K
65.5K
¥0.72 / ¥2.88Input/Output
61
ST
step-1o-turbo-202506 Stepfun
52.0
1.9K
-
-
62
TE
hunyuan-vision-1.5-thinking Tencent
51.2
2.4K
-
-
63
O
gpt-4.1-mini-2025-04-14 Openai
50.4
41.4K
1.05M
¥2.88 / ¥11.5Input/Output
64
TE
hunyuan-large-vision Tencent
49.6
1.3K
-
-
65
ST
step-3 Stepfun
48.8
3.3K
65.5K
¥1.8 / ¥4.68Input/Output
66
A
claude-opus-4-20250514 Anthropic
48.0
2.2K
200K
¥108 / ¥540Input/Output
67
A
claude-sonnet-4-20250514 Anthropic
47.2
1.9K
200K
¥21.6 / ¥108Input/Output
68
MA
mistral-medium-2508 Mistral
46.4
42.2K
262K
¥2.88 / ¥14.4Input/Output
69
A
claude-3-7-sonnet-20250219-thinking-32k Anthropic
45.6
1.5K
-
-
70
O
o1-2024-12-17 Openai
44.8
3.7K
128K
¥108 / ¥432Input/Output
71
Z
glm-4.6v Zai
44.0
2.3K
128K
¥2.16 / ¥6.48Input/Output
72
G
gemma-3-27b-it Google
43.2
17.4K
128K
¥2.15 / ¥2.15Input/Output
73
O
gpt-5-nano-high Openai
42.4
4K
400K
¥0.36 / ¥2.88Input/Output
74
G
gemini-1.5-pro-002 Google
41.6
8.9K
-
-
75
G
gemini-2.0-flash-001 Google
40.8
10.2K
1.05M
¥1.08 / ¥4.32Input/Output
76
MA
mistral-medium-2505 Mistral
40.0
11K
262K
¥2.88 / ¥14.4Input/Output
77
Z
glm-4.5v Zai
39.2
3.3K
64K
¥4.32 / ¥13Input/Output
78
A
qwen2.5-vl-32b-instruct Alibaba
38.4
1.5K
16.4K
¥0.39 / ¥1.57Input/Output
79
A
claude-3-7-sonnet-20250219 Anthropic
37.6
4.6K
200K
¥21.6 / ¥108Input/Output
80
M
llama-4-maverick-17b-128e-instruct Meta
36.8
7.1K
1M
¥1.8 / ¥6.26Input/Output
81
MA
mistral-small-2506 Mistral
36.0
11.2K
262K
¥2.88 / ¥14.4Input/Output
82
G
gemini-1.5-flash-002 Google
35.2
7.2K
2M
¥0.54 / ¥2.2Input/Output
83
MA
mistral-small-3.1-24b-instruct-2503 Mistral
34.4
29.4K
262K
¥2.88 / ¥14.4Input/Output
84
O
gpt-4o-2024-05-13 Openai
33.6
23.3K
128K
¥36 / ¥108Input/Output
85
A
claude-3-5-sonnet-20241022 Anthropic
32.8
10.4K
200K
¥21.6 / ¥108Input/Output
86
ST
step-1o-vision-32k-highres Stepfun
32.0
2.8K
-
-
87
A
claude-3-5-sonnet-20240620 Anthropic
31.2
21.6K
200K
¥21.6 / ¥108Input/Output
88
M
llama-4-scout-17b-16e-instruct Meta
30.4
6.6K
128K
¥1.44 / ¥5.62Input/Output
89
A
qwen2.5-vl-72b-instruct Alibaba
29.6
3.8K
131K
¥16.5 / ¥49.5Input/Output
90
G
gemini-2.0-flash-lite-preview-02-05 Google
28.8
4K
1.05M
¥0.54 / ¥2.16Input/Output
91
A
claude-3-5-haiku-20241022 Anthropic
28.0
1.4K
200K
¥5.76 / ¥28.8Input/Output
92
O
gpt-4-turbo-2024-04-09 Openai
27.2
13.4K
128K
¥72 / ¥216Input/Output
93
MA
pixtral-large-2411 Mistral
26.4
5.4K
128K
¥14.4 / ¥43.2Input/Output
94
G
gemini-1.5-pro-001 Google
25.6
16.7K
-
-
95
AI
molmo-2-8b Allenai
24.8
1.2K
-
-
96
O
gpt-4o-mini-2024-07-18 Openai
24.0
17.3K
128K
¥1.08 / ¥4.32Input/Output
97
O
gpt-4o-2024-08-06 Openai
23.2
3.4K
128K
¥18 / ¥72Input/Output
98
O
gpt-4.1-nano-2025-04-14 Openai
22.4
1.2K
1.05M
¥14.4 / ¥57.6Input/Output
99
A
qwen-vl-max-1119 Alibaba
21.6
1.4K
131K
¥1.66 / ¥4.13Input/Output
100
A
qwen2-vl-72b Alibaba
20.8
5.9K
-
-
101
ST
step-1v-32k Stepfun
20.0
1.5K
32.8K
¥14.8 / ¥69Input/Output
102
G
gemini-1.5-flash-8b-001 Google
19.2
6.2K
2M
¥0.54 / ¥2.2Input/Output
103
A
claude-3-opus-20240229 Anthropic
18.4
15.6K
200K
¥108 / ¥540Input/Output
104
AI
molmo-72b-0924 Allenai
17.6
3K
-
-
105
MA
pixtral-12b-2409 Mistral
16.8
7.5K
128K
¥1.08 / ¥1.08Input/Output
106
G
gemini-1.5-flash-001 Google
16.0
13.3K
2M
¥0.54 / ¥2.2Input/Output
107
UNinternvl2-26b
-
15.2
5.1K
-
-
108
M
llama-3.2-vision-90b-instruct Meta
14.4
8.7K
131K
¥2.48 / ¥2.48Input/Output
109
TE
hunyuan-standard-vision-2024-12-31 Tencent
13.6
809
-
-
110
CO
c4ai-aya-vision-32b Cohere
12.8
847
-
-
111
A
amazon-nova-lite-v1.0 Amazon
12.0
1.9K
300K
¥0.43 / ¥1.73Input/Output
112
A
qwen2-vl-7b-instruct Alibaba
11.2
5.8K
131K
¥2.07 / ¥5.16Input/Output
113
A
claude-3-sonnet-20240229 Anthropic
10.4
12.3K
200K
¥21.6 / ¥108Input/Output
114
A
amazon-nova-pro-v1.0 Amazon
9.6
2.3K
300K
¥5.76 / ¥23Input/Output
115
UNyi-vision
-
8.8
1.2K
-
-
116
M
llama-3.2-vision-11b-instruct Meta
8.0
4.8K
131K
¥2.48 / ¥2.48Input/Output
117
AI
molmo-7b-d-0924 Allenai
7.2
2.8K
-
-
118
A
claude-3-haiku-20240307 Anthropic
6.4
13.4K
200K
¥1.8 / ¥9Input/Output
119
UNinternvl2-4b
-
5.6
3.7K
-
-
120
NV
nvila-internal-15b-v1 Nvidia
4.8
1.1K
-
-
121
UNllava-v1.6-34b
-
4.0
4.5K
-
-
122
Z
cogvlm2-llama3-chat-19b Zai
3.2
2K
-
-
123
UNllava-onevision-qwen2-72b-ov
-
2.4
1.3K
-
-
124
UNminicpm-v-2_6
-
1.6
2K
-
-
125
M
phi-3.5-vision-instruct Microsoft
0.8
2.6K
128K
¥1.15 / ¥4.61Input/Output
126
M
phi-3-vision-128k-instruct Microsoft
0.0
1.4K
128K
¥1.08 / ¥4.32Input/Output
Top model analysisclaude-opus-4-7 why it ranks first
claude-opus-4-7 ranks first with a percent score of 100.0 and 6.8K samples. Use it as the first option for this leaderboard, then compare price, context and availability.
How to chooseDo not only look at rank #1
Start with the leaderboard closest to your task. Compare the top models by score and sample size, then check price, context length, open or closed access, and provider availability.
Related leaderboardsCompare adjacent capabilities