1
G
gemini-3-pro
gemini-3-proGoogle
100.0
243
1.05M
¥14.4 / ¥86.4Input/Output
Chat · Vision · Entity Recognition Leaderboard
Ranking for Vision / Entity Recognition, based on public preference data.
Entity Recognition model ranking guide
Ranking for Vision / Entity Recognition, based on public preference data.
gemini-3-progemini-3-flashgemini-3.1-pro-previewgemini-3-flash (thinking-minimal)qwen3.5-397b-a17b
2
Ggemini-3-flash
gemini-3-flashGoogle
96.8
206
1.05M
¥3.6 / ¥21.6Input/Output
3
Ggemini-3.1-pro-preview
gemini-3.1-pro-previewGoogle
93.5
171
1.05M
¥14.4 / ¥86.4Input/Output
4
Ggemini-3-flash (thinking-minimal)
gemini-3-flash (thinking-minimal)Google
90.3
182
1.05M
¥3.6 / ¥21.6Input/Output
5
A
qwen3.5-397b-a17b
qwen3.5-397b-a17bAlibaba
87.1
95
262K
¥3.1 / ¥18.6Input/Output
6
X
grok-4-0709
grok-4-0709Xai
83.9
341
256K
¥21.6 / ¥108Input/Output
7
Ggemini-2.5-pro
gemini-2.5-proGoogle
80.6
865
1.05M
¥9 / ¥72Input/Output
8
Ggemini-3.1-flash-lite-preview
gemini-3.1-flash-lite-previewGoogle
77.4
105
1.05M
¥1.8 / ¥10.8Input/Output
9
M
kimi-k2.5-thinking
kimi-k2.5-thinkingMoonshot
74.2
136
262K
¥4.32 / ¥21.6Input/Output
10
O
gpt-5-high
gpt-5-highOpenai
71.0
434
400K
¥9 / ¥72Input/Output
11
Aqwen3-vl-235b-a22b-instruct
qwen3-vl-235b-a22b-instructAlibaba
67.7
148
128K
¥2.16 / ¥8.64Input/Output
12
Ochatgpt-4o-latest-20250326
chatgpt-4o-latest-20250326Openai
64.5
295
128K
¥18 / ¥72Input/Output
13
Ggemini-2.5-flash
gemini-2.5-flashGoogle
61.3
579
1.05M
¥2.16 / ¥18Input/Output
14
Ogpt-5.1-high
gpt-5.1-highOpenai
58.1
106
400K
¥9 / ¥72Input/Output
15
Oo3-2025-04-16
o3-2025-04-16Openai
54.8
506
200K
¥14.4 / ¥57.6Input/Output
16
Ogpt-5-mini-high
gpt-5-mini-highOpenai
51.6
283
400K
¥1.8 / ¥14.4Input/Output
17
Ogpt-5-chat
gpt-5-chatOpenai
48.4
383
400K
¥9 / ¥72Input/Output
18
Oo4-mini-2025-04-16
o4-mini-2025-04-16Openai
45.2
398
200K
¥7.92 / ¥31.7Input/Output
19
Ogpt-5.2-high
gpt-5.2-highOpenai
41.9
119
400K
¥12.6 / ¥101Input/Output
20
Xgrok-4-1-fast-reasoning
grok-4-1-fast-reasoningXai
38.7
63
2M
¥1.44 / ¥3.6Input/Output
21
Ogpt-5.2-chat-latest-20260210
gpt-5.2-chat-latest-20260210Openai
35.5
84
400K
¥12.6 / ¥101Input/Output
22
Ogpt-4.1-2025-04-14
gpt-4.1-2025-04-14Openai
32.3
404
1.05M
¥14.4 / ¥57.6Input/Output
23
Ggemma-3-27b-it
gemma-3-27b-itGoogle
29.0
326
128K
¥2.15 / ¥2.15Input/Output
24
Ogpt-5.2
gpt-5.2Openai
25.8
129
400K
¥12.6 / ¥101Input/Output
25
Ogpt-4.1-mini-2025-04-14
gpt-4.1-mini-2025-04-14Openai
22.6
363
1.05M
¥2.88 / ¥11.5Input/Output
26
Ggemini-2.5-flash-lite-preview-06-17-thinking
gemini-2.5-flash-lite-preview-06-17-thinkingGoogle
19.4
422
65.5K
¥0.72 / ¥2.88Input/Output
27
Ogpt-5.1
gpt-5.1Openai
16.1
141
400K
¥9 / ¥72Input/Output
28
Ggemma-4-31b
gemma-4-31bGoogle
12.9
93
262K
¥3.24 / ¥7.2Input/Output
29
MA
mistral-small-3.1-24b-instruct-2503
mistral-small-3.1-24b-instruct-2503Mistral
9.7
249
262K
¥2.88 / ¥14.4Input/Output
30
MAmistral-small-2506
mistral-small-2506Mistral
6.5
212
262K
¥2.88 / ¥14.4Input/Output
31
MAmistral-medium-2508
mistral-medium-2508Mistral
3.2
444
262K
¥2.88 / ¥14.4Input/Output
32
MAmistral-medium-2505
mistral-medium-2505Mistral
0.0
201
262K
¥2.88 / ¥14.4Input/Output
gemini-3-pro why it ranks first
gemini-3-pro ranks first with a percent score of 100.0 and 243 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
实体识别排行榜看什么指标？
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。
实体识别模型应该怎么选？
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。