1
A
claude-opus-4-7-thinking
claude-opus-4-7-thinkingAnthropic
100.0
4.6K
1M
¥36 / ¥180Input/Output
Code · Web Development · React Leaderboard
Ranking for Web Development / React, based on public preference data.
React model ranking guide
Ranking for Web Development / React, based on public preference data.
claude-opus-4-7-thinkingclaude-opus-4-7qwen3.7-max-20260517claude-opus-4-6-thinkingclaude-opus-4-6
2
Aclaude-opus-4-7
claude-opus-4-7Anthropic
98.4
4.3K
1M
¥36 / ¥180Input/Output
3
A
qwen3.7-max-20260517
qwen3.7-max-20260517Alibaba
96.9
1.3K
1M
¥18 / ¥54Input/Output
4
Aclaude-opus-4-6-thinking
claude-opus-4-6-thinkingAnthropic
95.3
6.7K
1M
¥36 / ¥180Input/Output
5
Aclaude-opus-4-6
claude-opus-4-6Anthropic
93.8
7.6K
1M
¥36 / ¥180Input/Output
6
Z
glm-5.1
glm-5.1Zai
92.2
3.1K
200K
¥0 / ¥0Input/Output
7
Aclaude-sonnet-4-6
claude-sonnet-4-6Anthropic
90.6
9.5K
1M
¥21.6 / ¥108Input/Output
8
M
kimi-k2.6
kimi-k2.6Moonshot
89.1
3.5K
262K
¥6.84 / ¥28.8Input/Output
9
G
gemini-3.5-flash
gemini-3.5-flashGoogle
87.5
1.9K
1.05M
¥10.8 / ¥64.8Input/Output
10
M
muse-spark
muse-sparkMeta
85.9
1.4K
-
-
11
O
gpt-5.5-xhigh (codex-harness)
gpt-5.5-xhigh (codex-harness)Openai
84.4
3.6K
400K
¥9 / ¥72Input/Output
12
Aqwen3.6-max-preview
qwen3.6-max-previewAlibaba
82.8
2.2K
246K
¥9.5 / ¥56.9Input/Output
13
Aclaude-opus-4-5-20251101-thinking-32k
claude-opus-4-5-20251101-thinking-32kAnthropic
81.3
5.1K
200K
¥108 / ¥540Input/Output
14
Ogpt-5.5-high (codex-harness)
gpt-5.5-high (codex-harness)Openai
79.7
3.8K
400K
¥9 / ¥72Input/Output
15
MI
mimo-v2.5-pro
mimo-v2.5-proXiaomi
78.1
4.1K
1.05M
¥7.2 / ¥21.6Input/Output
16
Aclaude-opus-4-5-20251101
claude-opus-4-5-20251101Anthropic
76.6
6.9K
200K
¥36 / ¥180Input/Output
17
D
deepseek-v4-pro-thinking
deepseek-v4-pro-thinkingDeepseek
75.0
3.4K
1M
¥3.13 / ¥6.26Input/Output
18
Aqwen3.6-plus
qwen3.6-plusAlibaba
73.4
5.3K
1M
¥3.6 / ¥21.6Input/Output
19
Ogpt-5.4-high (codex-harness)
gpt-5.4-high (codex-harness)Openai
71.9
1.3K
400K
¥9 / ¥72Input/Output
20
Zglm-4.7
glm-4.7Zai
70.3
119
205K
¥0 / ¥0Input/Output
21
MImimo-v2.5
mimo-v2.5Xiaomi
68.8
3.3K
1.05M
¥2.88 / ¥14.4Input/Output
22
Ggemini-3.1-pro-preview
gemini-3.1-pro-previewGoogle
67.2
9K
1.05M
¥14.4 / ¥86.4Input/Output
23
Ogpt-5.5 (codex-harness)
gpt-5.5 (codex-harness)Openai
65.6
3.6K
400K
¥9 / ¥72Input/Output
24
Ggemini-3-flash
gemini-3-flashGoogle
64.1
4K
1.05M
¥3.6 / ¥21.6Input/Output
25
Ogpt-5.4-medium (codex-harness)
gpt-5.4-medium (codex-harness)Openai
62.5
1.3K
400K
¥9 / ¥72Input/Output
26
MImimo-v2-pro
mimo-v2-proXiaomi
60.9
6K
1.05M
¥7.2 / ¥21.6Input/Output
27
Zglm-5
glm-5Zai
59.4
5.8K
205K
¥7.2 / ¥23Input/Output
28
Mkimi-k2.5-thinking
kimi-k2.5-thinkingMoonshot
57.8
9.1K
262K
¥4.32 / ¥21.6Input/Output
29
Ggemini-3-pro
gemini-3-proGoogle
56.3
3.4K
1.05M
¥14.4 / ¥86.4Input/Output
30
Ogpt-5.3-codex (codex-harness)
gpt-5.3-codex (codex-harness)Openai
54.7
2.6K
400K
¥9 / ¥72Input/Output
31
Mkimi-k2.5-instant
kimi-k2.5-instantMoonshot
53.1
3K
262K
¥4.32 / ¥21.6Input/Output
32
M
minimax-m2.7
minimax-m2.7Minimax
51.6
5.5K
205K
¥0 / ¥0Input/Output
33
Ogpt-5.4-mini-high
gpt-5.4-mini-highOpenai
50.0
4.8K
400K
¥5.4 / ¥32.4Input/Output
34
X
grok-4.20-beta-0309-reasoning
grok-4.20-beta-0309-reasoningXai
48.4
6.3K
2M
¥14.4 / ¥43.2Input/Output
35
Aclaude-sonnet-4-5-20250929
claude-sonnet-4-5-20250929Anthropic
46.9
5.4K
200K
¥21.6 / ¥108Input/Output
36
Aqwen3.5-397b-a17b
qwen3.5-397b-a17bAlibaba
45.3
8.4K
262K
¥3.1 / ¥18.6Input/Output
37
Aclaude-sonnet-4-5-20250929-thinking-32k
claude-sonnet-4-5-20250929-thinking-32kAnthropic
43.8
4.4K
200K
¥21.6 / ¥108Input/Output
38
Ggemma-4-31b
gemma-4-31bGoogle
42.2
3K
262K
¥3.24 / ¥7.2Input/Output
39
Ggemini-3-flash (thinking-minimal)
gemini-3-flash (thinking-minimal)Google
40.6
9.8K
1.05M
¥3.6 / ¥21.6Input/Output
40
Xgrok-4.3
grok-4.3Xai
39.1
3K
1M
¥9 / ¥18Input/Output
41
Mminimax-m2.1-preview
minimax-m2.1-previewMinimax
37.5
2.5K
205K
¥0 / ¥0Input/Output
42
Mminimax-m2.5
minimax-m2.5Minimax
35.9
6.8K
205K
¥0 / ¥0Input/Output
43
Ogpt-5.4
gpt-5.4Openai
34.4
216
1.05M
¥18 / ¥108Input/Output
44
Ddeepseek-v3.2-thinking
deepseek-v3.2-thinkingDeepseek
32.8
3.9K
128K
¥2.09 / ¥3.1Input/Output
45
TE
hunyuan-hy3-preview
hunyuan-hy3-previewTencent
31.3
1.2K
256K
¥0 / ¥0Input/Output
46
Ogpt-5.3-codex (codex-harness)
gpt-5.3-codex (codex-harness)Openai
29.7
3.1K
400K
¥9 / ¥72Input/Output
47
Aqwen3.5-122b-a10b
qwen3.5-122b-a10bAlibaba
28.1
7.1K
262K
¥2.88 / ¥23Input/Output
48
Ggemma-4-26b-a4b
gemma-4-26b-a4bGoogle
26.6
1.3K
262K
¥0.94 / ¥2.88Input/Output
49
Aqwen3.5-27b
qwen3.5-27bAlibaba
25.0
6.7K
262K
¥2.16 / ¥17.3Input/Output
50
Ddeepseek-v3.2
deepseek-v3.2Deepseek
23.4
5.2K
128K
¥2.09 / ¥3.1Input/Output
51
Ogpt-5.2-codex
gpt-5.2-codexOpenai
21.9
4.6K
400K
¥12.6 / ¥101Input/Output
52
Aclaude-haiku-4-5-20251001
claude-haiku-4-5-20251001Anthropic
20.3
8.9K
200K
¥7.2 / ¥36Input/Output
53
Mkimi-k2-thinking-turbo
kimi-k2-thinking-turboMoonshot
18.8
5.4K
262K
¥17.3 / ¥72Input/Output
54
MImimo-v2-flash (non-thinking)
mimo-v2-flash (non-thinking)Xiaomi
17.2
2.6K
262K
¥0.72 / ¥2.16Input/Output
55
Ogpt-5.1
gpt-5.1Openai
15.6
2.9K
400K
¥9 / ¥72Input/Output
56
Aqwen3-coder-480b-a35b-instruct
qwen3-coder-480b-a35b-instructAlibaba
14.1
4.4K
262K
¥6.2 / ¥24.8Input/Output
57
Ggemini-3.1-flash-lite-preview
gemini-3.1-flash-lite-previewGoogle
12.5
8.2K
1.05M
¥1.8 / ¥10.8Input/Output
58
MImimo-v2-flash (thinking)
mimo-v2-flash (thinking)Xiaomi
10.9
913
262K
¥0.72 / ¥2.16Input/Output
59
UNtrinity-large-thinking
-
9.4
1.1K
262K
¥1.8 / ¥6.48Input/Output
60
Aqwen3.5-35b-a3b
qwen3.5-35b-a3bAlibaba
7.8
1.6K
262K
¥1.8 / ¥14.4Input/Output
61
Xgrok-4-1-fast-reasoning
grok-4-1-fast-reasoningXai
6.3
1.5K
2M
¥1.44 / ¥3.6Input/Output
62
Aqwen3.5-flash
qwen3.5-flashAlibaba
4.7
1.4K
1M
¥1.24 / ¥12.4Input/Output
63
IB
granite-4.1-8b
granite-4.1-8bIbm
3.1
1.5K
131K
¥0.36 / ¥0.72Input/Output
64
MA
devstral-2
devstral-2Mistral
1.6
225
262K
¥2.88 / ¥14.4Input/Output
65
IA
mercury-2
mercury-2Inception Ai
0.0
845
128K
¥1.8 / ¥5.4Input/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 4.6K 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
React 网页排行榜看什么指标？
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。
React 网页模型应该怎么选？
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。