1
A
claude-opus-4-6-search
claude-opus-4-6-searchAnthropic
100.0
48.7K
200K
¥108 / ¥540Input/Output
Chat · Search · Overall Leaderboard
Ranking for Search / Overall, based on public preference data.
Overall model ranking guide
Ranking for Search / Overall, based on public preference data.
claude-opus-4-6-searchgpt-5.5-searchclaude-opus-4-7ernie-5.1claude-sonnet-4-6-search
2
O
gpt-5.5-search
gpt-5.5-searchOpenai
96.4
9.5K
400K
¥9 / ¥72Input/Output
3
Aclaude-opus-4-7
claude-opus-4-7Anthropic
92.9
9.7K
1M
¥36 / ¥180Input/Output
4
B
ernie-5.1
ernie-5.1Baidu
89.3
2.3K
119K
¥5.4 / ¥21.6Input/Output
5
Aclaude-sonnet-4-6-search
claude-sonnet-4-6-searchAnthropic
85.7
48.1K
200K
¥21.6 / ¥108Input/Output
6
G
gemini-3.1-pro-grounding
gemini-3.1-pro-groundingGoogle
82.1
28K
1.05M
¥14.4 / ¥86.4Input/Output
7
Ogpt-5.2-search
gpt-5.2-searchOpenai
78.6
47.1K
400K
¥12.6 / ¥101Input/Output
8
X
grok-4.20-multi-agent-beta-0309
grok-4.20-multi-agent-beta-0309Xai
75.0
27.5K
2M
¥14.4 / ¥43.2Input/Output
9
Ggemini-3-pro-grounding
gemini-3-pro-groundingGoogle
71.4
37.3K
1.05M
¥14.4 / ¥86.4Input/Output
10
Ggemini-3-flash-grounding
gemini-3-flash-groundingGoogle
67.9
62.9K
1.05M
¥3.6 / ¥21.6Input/Output
11
Ogpt-5.1-search
gpt-5.1-searchOpenai
64.3
53.7K
400K
¥9 / ¥72Input/Output
12
Ogpt-5.4-search
gpt-5.4-searchOpenai
60.7
27.9K
400K
¥9 / ¥72Input/Output
13
Xgrok-4.20-beta1
grok-4.20-beta1Xai
57.1
49K
2M
¥14.4 / ¥43.2Input/Output
14
Xgrok-4.3
grok-4.3Xai
53.6
6.9K
1M
¥9 / ¥18Input/Output
15
Aclaude-opus-4-5-search
claude-opus-4-5-searchAnthropic
50.0
53.4K
200K
¥108 / ¥540Input/Output
16
Ogpt-5.2-search-non-reasoning
gpt-5.2-search-non-reasoningOpenai
46.4
65.5K
400K
¥12.6 / ¥101Input/Output
17
Xgrok-4-1-fast-search
grok-4-1-fast-searchXai
42.9
71.6K
1M
¥9 / ¥18Input/Output
18
Xgrok-4-fast-search
grok-4-fast-searchXai
39.3
43K
1M
¥9 / ¥18Input/Output
19
Aclaude-sonnet-4-5-search
claude-sonnet-4-5-searchAnthropic
35.7
45.7K
200K
¥21.6 / ¥108Input/Output
20
Aclaude-opus-4-1-search
claude-opus-4-1-searchAnthropic
32.1
71.3K
200K
¥108 / ¥540Input/Output
21
Oo3-search
o3-searchOpenai
28.6
20.7K
200K
¥14.4 / ¥57.6Input/Output
22
Ggemini-2.5-pro-grounding
gemini-2.5-pro-groundingGoogle
25.0
76.8K
1.05M
¥9 / ¥72Input/Output
23
Xgrok-4-search
grok-4-searchXai
21.4
19.3K
1M
¥9 / ¥18Input/Output
24
PE
ppl-sonar-reasoning-pro-high
ppl-sonar-reasoning-pro-highPerplexity
17.9
29.1K
128K
¥7.2 / ¥7.2Input/Output
25
Ogpt-5-search
gpt-5-searchOpenai
14.3
20.8K
400K
¥9 / ¥72Input/Output
26
PEppl-sonar-pro-high
ppl-sonar-pro-highPerplexity
10.7
28.6K
128K
¥7.2 / ¥7.2Input/Output
27
Aclaude-opus-4-search
claude-opus-4-searchAnthropic
7.1
31.1K
200K
¥108 / ¥540Input/Output
28
D
diffbot-small-xl
diffbot-small-xlDiffbot
3.6
6.4K
-
-
29
Oapi-gpt-4o-search
api-gpt-4o-searchOpenai
0.0
3.4K
128K
¥18 / ¥72Input/Output
claude-opus-4-6-search why it ranks first
claude-opus-4-6-search ranks first with a percent score of 100.0 and 48.7K 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。