1
A
claude-opus-4-7-thinking
claude-opus-4-7-thinkingAnthropic
100.0
5.3K
1M
¥36 / ¥180Input/Output
Code · Web Development · Overall Leaderboard
Ranking for Web Development / Overall, based on public preference data.
Overall model ranking guide
Ranking for Web Development / Overall, based on public preference data.
claude-opus-4-7-thinkingclaude-opus-4-7claude-opus-4-6-thinkingqwen3.7-max-20260517claude-opus-4-6
2
Aclaude-opus-4-7
claude-opus-4-7Anthropic
98.8
4.9K
1M
¥36 / ¥180Input/Output
3
Aclaude-opus-4-6-thinking
claude-opus-4-6-thinkingAnthropic
97.5
7.9K
1M
¥36 / ¥180Input/Output
4
A
qwen3.7-max-20260517
qwen3.7-max-20260517Alibaba
96.3
1.5K
1M
¥18 / ¥54Input/Output
5
Aclaude-opus-4-6
claude-opus-4-6Anthropic
95.0
8.9K
1M
¥36 / ¥180Input/Output
6
Z
glm-5.1
glm-5.1Zai
93.8
3.6K
200K
¥0 / ¥0Input/Output
7
Aclaude-sonnet-4-6
claude-sonnet-4-6Anthropic
92.5
11.1K
1M
¥21.6 / ¥108Input/Output
8
M
kimi-k2.6
kimi-k2.6Moonshot
91.3
4K
262K
¥6.84 / ¥28.8Input/Output
9
M
muse-spark
muse-sparkMeta
90.0
1.6K
-
-
10
G
gemini-3.5-flash
gemini-3.5-flashGoogle
88.8
2.2K
1.05M
¥10.8 / ¥64.8Input/Output
11
O
gpt-5.5-xhigh (codex-harness)
gpt-5.5-xhigh (codex-harness)Openai
87.5
4.1K
400K
¥9 / ¥72Input/Output
12
Aclaude-opus-4-5-20251101-thinking-32k
claude-opus-4-5-20251101-thinking-32kAnthropic
86.3
13.1K
200K
¥108 / ¥540Input/Output
13
Aqwen3.6-max-preview
qwen3.6-max-previewAlibaba
85.0
2.5K
246K
¥9.5 / ¥56.9Input/Output
14
Ogpt-5.5-high (codex-harness)
gpt-5.5-high (codex-harness)Openai
83.8
4.3K
400K
¥9 / ¥72Input/Output
15
MI
mimo-v2.5-pro
mimo-v2.5-proXiaomi
82.5
4.7K
1.05M
¥7.2 / ¥21.6Input/Output
16
Aclaude-opus-4-5-20251101
claude-opus-4-5-20251101Anthropic
81.3
15.3K
200K
¥36 / ¥180Input/Output
17
D
deepseek-v4-pro-thinking
deepseek-v4-pro-thinkingDeepseek
80.0
4K
1M
¥3.13 / ¥6.26Input/Output
18
Aqwen3.6-plus
qwen3.6-plusAlibaba
78.8
6.1K
1M
¥3.6 / ¥21.6Input/Output
19
Ogpt-5.4-high (codex-harness)
gpt-5.4-high (codex-harness)Openai
77.5
1.5K
400K
¥9 / ¥72Input/Output
20
Ggemini-3.1-pro-preview
gemini-3.1-pro-previewGoogle
76.3
10.3K
1.05M
¥14.4 / ¥86.4Input/Output
21
Ogpt-5.5 (codex-harness)
gpt-5.5 (codex-harness)Openai
75.0
4.1K
400K
¥9 / ¥72Input/Output
22
Zglm-4.7
glm-4.7Zai
73.8
4.9K
205K
¥0 / ¥0Input/Output
23
MImimo-v2.5
mimo-v2.5Xiaomi
72.5
3.7K
1.05M
¥2.88 / ¥14.4Input/Output
24
Ggemini-3-pro
gemini-3-proGoogle
71.3
17.2K
1.05M
¥14.4 / ¥86.4Input/Output
25
Ogpt-5.4-medium (codex-harness)
gpt-5.4-medium (codex-harness)Openai
70.0
1.4K
400K
¥9 / ¥72Input/Output
26
Ggemini-3-flash
gemini-3-flashGoogle
68.8
13.3K
1.05M
¥3.6 / ¥21.6Input/Output
27
Zglm-5
glm-5Zai
67.5
6.6K
205K
¥7.2 / ¥23Input/Output
28
MImimo-v2-pro
mimo-v2-proXiaomi
66.3
6.8K
1.05M
¥7.2 / ¥21.6Input/Output
29
Mkimi-k2.5-thinking
kimi-k2.5-thinkingMoonshot
65.0
10.7K
262K
¥4.32 / ¥21.6Input/Output
30
Mkimi-k2.5-instant
kimi-k2.5-instantMoonshot
63.8
3.6K
262K
¥4.32 / ¥21.6Input/Output
31
Ogpt-5.3-codex (codex-harness)
gpt-5.3-codex (codex-harness)Openai
62.5
3K
400K
¥9 / ¥72Input/Output
32
Ogpt-5.2
gpt-5.2Openai
61.3
1.5K
400K
¥12.6 / ¥101Input/Output
33
Ogpt-5.4-mini-high
gpt-5.4-mini-highOpenai
60.0
5.5K
400K
¥5.4 / ¥32.4Input/Output
34
M
minimax-m2.7
minimax-m2.7Minimax
58.8
6.3K
205K
¥0 / ¥0Input/Output
35
X
grok-4.20-beta-0309-reasoning
grok-4.20-beta-0309-reasoningXai
57.5
7.2K
2M
¥14.4 / ¥43.2Input/Output
36
Ogpt-5-medium
gpt-5-mediumOpenai
56.3
3.8K
400K
¥9 / ¥72Input/Output
37
Aqwen3.5-397b-a17b
qwen3.5-397b-a17bAlibaba
55.0
9.7K
262K
¥3.1 / ¥18.6Input/Output
38
Mminimax-m2.1-preview
minimax-m2.1-previewMinimax
53.8
9.3K
205K
¥0 / ¥0Input/Output
39
Ogpt-5.1-medium
gpt-5.1-mediumOpenai
52.5
6.1K
400K
¥9 / ¥72Input/Output
40
Ogpt-5.4
gpt-5.4Openai
51.3
239
1.05M
¥18 / ¥108Input/Output
41
Aclaude-sonnet-4-5-20250929-thinking-32k
claude-sonnet-4-5-20250929-thinking-32kAnthropic
50.0
15.7K
200K
¥21.6 / ¥108Input/Output
42
Ggemini-3-flash (thinking-minimal)
gemini-3-flash (thinking-minimal)Google
48.8
16.4K
1.05M
¥3.6 / ¥21.6Input/Output
43
Aclaude-sonnet-4-5-20250929
claude-sonnet-4-5-20250929Anthropic
47.5
18.4K
200K
¥21.6 / ¥108Input/Output
44
Aclaude-opus-4-1-20250805
claude-opus-4-1-20250805Anthropic
46.3
8.6K
200K
¥108 / ¥540Input/Output
45
Mminimax-m2.5
minimax-m2.5Minimax
45.0
7.8K
205K
¥0 / ¥0Input/Output
46
Ggemma-4-31b
gemma-4-31bGoogle
43.8
3.4K
262K
¥3.24 / ¥7.2Input/Output
47
Xgrok-4.3
grok-4.3Xai
42.5
3.5K
1M
¥9 / ¥18Input/Output
48
Ogpt-5.3-codex (codex-harness)
gpt-5.3-codex (codex-harness)Openai
41.3
3.5K
400K
¥9 / ¥72Input/Output
49
Ddeepseek-v3.2-thinking
deepseek-v3.2-thinkingDeepseek
40.0
7.9K
128K
¥2.09 / ¥3.1Input/Output
50
TE
hunyuan-hy3-preview
hunyuan-hy3-previewTencent
38.7
1.3K
256K
¥0 / ¥0Input/Output
51
Aqwen3.5-122b-a10b
qwen3.5-122b-a10bAlibaba
37.5
8.1K
262K
¥2.88 / ¥23Input/Output
52
Ggemma-4-26b-a4b
gemma-4-26b-a4bGoogle
36.3
1.5K
262K
¥0.94 / ¥2.88Input/Output
53
Aqwen3.5-27b
qwen3.5-27bAlibaba
35.0
7.7K
262K
¥2.16 / ¥17.3Input/Output
54
Zglm-4.6
glm-4.6Zai
33.8
8.3K
205K
¥4.32 / ¥15.8Input/Output
55
Ogpt-5.1
gpt-5.1Openai
32.5
12.9K
400K
¥9 / ¥72Input/Output
56
MImimo-v2-flash (non-thinking)
mimo-v2-flash (non-thinking)Xiaomi
31.3
6.7K
262K
¥0.72 / ¥2.16Input/Output
57
Ogpt-5.2-codex
gpt-5.2-codexOpenai
30.0
7.8K
400K
¥12.6 / ¥101Input/Output
58
Ddeepseek-v3.2
deepseek-v3.2Deepseek
28.8
10.5K
128K
¥2.09 / ¥3.1Input/Output
59
Mkimi-k2-thinking-turbo
kimi-k2-thinking-turboMoonshot
27.5
15.3K
262K
¥17.3 / ¥72Input/Output
60
Ogpt-5.1-codex
gpt-5.1-codexOpenai
26.3
6.2K
400K
¥9 / ¥72Input/Output
61
Aclaude-haiku-4-5-20251001
claude-haiku-4-5-20251001Anthropic
25.0
20.6K
200K
¥7.2 / ¥36Input/Output
62
Mminimax-m2
minimax-m2Minimax
23.8
8.4K
197K
¥0 / ¥0Input/Output
63
MImimo-v2-flash (thinking)
mimo-v2-flash (thinking)Xiaomi
22.5
2.1K
262K
¥0.72 / ¥2.16Input/Output
64
Ddeepseek-v3.2-exp
deepseek-v3.2-expDeepseek
21.3
4.9K
128K
¥0 / ¥0Input/Output
65
Aqwen3-coder-480b-a35b-instruct
qwen3-coder-480b-a35b-instructAlibaba
20.0
15.2K
262K
¥6.2 / ¥24.8Input/Output
66
UNKAT-Coder-Pro-V1
-
18.8
1.9K
256K
¥0.22 / ¥8.64Input/Output
67
Aqwen3.5-35b-a3b
qwen3.5-35b-a3bAlibaba
17.5
1.8K
262K
¥1.8 / ¥14.4Input/Output
68
Ggemini-3.1-flash-lite-preview
gemini-3.1-flash-lite-previewGoogle
16.3
9.3K
1.05M
¥1.8 / ¥10.8Input/Output
69
UNtrinity-large-thinking
-
15.0
1.3K
262K
¥1.8 / ¥6.48Input/Output
70
Ogpt-5.1-codex-mini
gpt-5.1-codex-miniOpenai
13.8
1.4K
400K
¥1.8 / ¥14.4Input/Output
71
Aqwen3.5-flash
qwen3.5-flashAlibaba
12.5
1.6K
1M
¥1.24 / ¥12.4Input/Output
72
Xgrok-4-1-fast-reasoning
grok-4-1-fast-reasoningXai
11.3
6.9K
2M
¥1.44 / ¥3.6Input/Output
73
MA
mistral-large-3
mistral-large-3Mistral
10.0
1K
262K
¥3.6 / ¥10.8Input/Output
74
Xgrok-4.1-thinking
grok-4.1-thinkingXai
8.8
1.2K
200K
¥14.4 / ¥72Input/Output
75
Ggemini-2.5-pro
gemini-2.5-proGoogle
7.5
3.3K
1.05M
¥9 / ¥72Input/Output
76
IB
granite-4.1-8b
granite-4.1-8bIbm
6.3
1.7K
131K
¥0.36 / ¥0.72Input/Output
77
MAdevstral-2
devstral-2Mistral
5.0
1.6K
262K
¥2.88 / ¥14.4Input/Output
78
IA
mercury-2
mercury-2Inception Ai
3.8
946
128K
¥1.8 / ¥5.4Input/Output
79
Xgrok-4-fast-reasoning
grok-4-fast-reasoningXai
2.5
933
2M
¥1.44 / ¥3.6Input/Output
80
Xgrok-code-fast-1
grok-code-fast-1Xai
1.3
982
256K
¥1.44 / ¥10.8Input/Output
81
MAdevstral-medium-2507
devstral-medium-2507Mistral
0.0
992
262K
¥2.88 / ¥14.4Input/Output
claude-opus-4-7-thinking why it ranks first
claude-opus-4-7-thinking ranks first with a percent score of 100.0 and 5.3K samples. Use it as the first option for this leaderboard, then compare price, context and availability.
Do 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.
Compare adjacent capabilities
FAQ
总榜排行榜看什么指标？
主要看排名、百分制分数、样本量和来源。分数用于快速比较同一榜单内模型表现，样本量用于判断结果稳定性。
为什么不同榜单不能直接混合成总分？
不同榜单的任务、样本和评测口径不同，模力榜默认只在同一榜单内排序，避免把写作、代码、图像等能力强行合并。
总榜模型应该怎么选？
优先看与你任务最接近的榜单，再结合价格、上下文长度、开源闭源和厂商可用性。排名靠前不代表适合所有预算和部署方式。
榜单多久更新？
页面展示的是最新成功采集的公开榜单数据。当前优先使用 LMArena leaderboard dataset，并在页面来源中保留原始链接。