1
A
claude-opus-4-6-thinking
claude-opus-4-6-thinkingAnthropic
100.0
435
1M
¥36 / ¥180Input/Output
Chat · Vision · Chinese Leaderboard
Ranking for Vision / Chinese, based on public preference data.
Chinese model ranking guide
Ranking for Vision / Chinese, based on public preference data.
claude-opus-4-6-thinkingclaude-opus-4-6gemini-3.1-pro-previewgemini-3-proclaude-opus-4-7-thinking
2
Aclaude-opus-4-6
claude-opus-4-6Anthropic
98.9
466
1M
¥36 / ¥180Input/Output
3
G
gemini-3.1-pro-preview
gemini-3.1-pro-previewGoogle
97.8
1K
1.05M
¥14.4 / ¥86.4Input/Output
4
Ggemini-3-pro
gemini-3-proGoogle
96.7
1.4K
1.05M
¥14.4 / ¥86.4Input/Output
5
Aclaude-opus-4-7-thinking
claude-opus-4-7-thinkingAnthropic
95.7
386
1M
¥36 / ¥180Input/Output
6
M
muse-spark
muse-sparkMeta
94.6
325
-
-
7
M
kimi-k2.6
kimi-k2.6Moonshot
93.5
368
262K
¥6.84 / ¥28.8Input/Output
8
O
gpt-5.5
gpt-5.5Openai
92.4
315
1.05M
¥36 / ¥216Input/Output
9
Ogpt-5.4-high
gpt-5.4-highOpenai
91.3
357
1.05M
¥18 / ¥108Input/Output
10
Aclaude-opus-4-7
claude-opus-4-7Anthropic
90.2
493
1M
¥36 / ¥180Input/Output
11
Mkimi-k2.5-instant
kimi-k2.5-instantMoonshot
89.1
170
262K
¥4.32 / ¥21.6Input/Output
12
Ogpt-5.5-high
gpt-5.5-highOpenai
88.0
256
1.05M
¥36 / ¥216Input/Output
13
Ggemini-3-flash
gemini-3-flashGoogle
87.0
1.1K
1.05M
¥3.6 / ¥21.6Input/Output
14
Ggemma-4-26b-a4b
gemma-4-26b-a4bGoogle
85.9
668
262K
¥0.94 / ¥2.88Input/Output
15
Z
glm-5v-turbo
glm-5v-turboZai
84.8
488
200K
¥0 / ¥0Input/Output
16
Ogpt-5.4
gpt-5.4Openai
83.7
322
1.05M
¥18 / ¥108Input/Output
17
Ggemma-4-31b
gemma-4-31bGoogle
82.6
1.1K
262K
¥3.24 / ¥7.2Input/Output
18
B
dola-seed-2.0-pro
dola-seed-2.0-proBytedance
81.5
495
-
-
19
A
qwen3.5-397b-a17b
qwen3.5-397b-a17bAlibaba
80.4
570
262K
¥3.1 / ¥18.6Input/Output
20
Aqwen3.5-27b
qwen3.5-27bAlibaba
79.3
530
262K
¥2.16 / ¥17.3Input/Output
21
Ggemini-3-flash (thinking-minimal)
gemini-3-flash (thinking-minimal)Google
78.3
989
1.05M
¥3.6 / ¥21.6Input/Output
22
Mkimi-k2.5-thinking
kimi-k2.5-thinkingMoonshot
77.2
744
262K
¥4.32 / ¥21.6Input/Output
23
X
grok-4.20-multi-agent-beta-0309
grok-4.20-multi-agent-beta-0309Xai
76.1
525
2M
¥14.4 / ¥43.2Input/Output
24
MI
mimo-v2.5
mimo-v2.5Xiaomi
75.0
379
1.05M
¥2.88 / ¥14.4Input/Output
25
Aqwen3.7-plus-preview
qwen3.7-plus-previewAlibaba
73.9
216
131K
¥3.6 / ¥21.6Input/Output
26
Aqwen3.5-122b-a10b
qwen3.5-122b-a10bAlibaba
72.8
562
262K
¥2.88 / ¥23Input/Output
27
Aclaude-sonnet-4-6
claude-sonnet-4-6Anthropic
71.7
524
1M
¥21.6 / ¥108Input/Output
28
Ogpt-5.4-mini-high
gpt-5.4-mini-highOpenai
70.7
517
400K
¥5.4 / ¥32.4Input/Output
29
Ogpt-5.2-high
gpt-5.2-highOpenai
69.6
778
400K
¥12.6 / ¥101Input/Output
30
Xgrok-4.20-beta-0309-reasoning
grok-4.20-beta-0309-reasoningXai
68.5
560
2M
¥14.4 / ¥43.2Input/Output
31
Ggemini-2.5-pro
gemini-2.5-proGoogle
67.4
2.9K
1.05M
¥9 / ¥72Input/Output
32
Ggemini-2.5-flash-preview-09-2025
gemini-2.5-flash-preview-09-2025Google
66.3
391
1M
¥2.16 / ¥18Input/Output
33
Aqwen3-vl-235b-a22b-instruct
qwen3-vl-235b-a22b-instructAlibaba
65.2
719
128K
¥2.16 / ¥8.64Input/Output
34
Ggemini-2.5-flash
gemini-2.5-flashGoogle
64.1
2.4K
1.05M
¥2.16 / ¥18Input/Output
35
Ggemini-3.1-flash-lite-preview
gemini-3.1-flash-lite-previewGoogle
63.0
812
1.05M
¥1.8 / ¥10.8Input/Output
36
MImimo-v2-omni
mimo-v2-omniXiaomi
62.0
397
262K
¥2.88 / ¥14.4Input/Output
37
Ogpt-5.1-high
gpt-5.1-highOpenai
60.9
453
400K
¥9 / ¥72Input/Output
38
Ogpt-5.2
gpt-5.2Openai
59.8
826
400K
¥12.6 / ¥101Input/Output
39
Ogpt-5.2-chat-latest-20260210
gpt-5.2-chat-latest-20260210Openai
58.7
636
400K
¥12.6 / ¥101Input/Output
40
B
ernie-5.0-preview-1220
ernie-5.0-preview-1220Baidu
57.6
173
128K
¥7.92 / ¥14.4Input/Output
41
Ogpt-5.1
gpt-5.1Openai
56.5
558
400K
¥9 / ¥72Input/Output
42
Ogpt-5-chat
gpt-5-chatOpenai
55.4
1.3K
400K
¥9 / ¥72Input/Output
43
Ogpt-5.4-nano-high
gpt-5.4-nano-highOpenai
54.3
537
400K
¥1.44 / ¥9Input/Output
44
Xgrok-4-0709
grok-4-0709Xai
53.3
1.2K
256K
¥21.6 / ¥108Input/Output
45
Ochatgpt-4o-latest-20250326
chatgpt-4o-latest-20250326Openai
52.2
1.1K
128K
¥18 / ¥72Input/Output
46
Ogpt-5-high
gpt-5-highOpenai
51.1
1.4K
400K
¥9 / ¥72Input/Output
47
Ggemini-2.5-flash-lite-preview-09-2025-no-thinking
gemini-2.5-flash-lite-preview-09-2025-no-thinkingGoogle
50.0
405
1.05M
¥0.72 / ¥2.88Input/Output
48
Oo3-2025-04-16
o3-2025-04-16Openai
48.9
1.6K
200K
¥14.4 / ¥57.6Input/Output
49
Oo1-2024-12-17
o1-2024-12-17Openai
47.8
99
128K
¥108 / ¥432Input/Output
50
Ogpt-5.5-instant
gpt-5.5-instantOpenai
46.7
231
400K
¥9 / ¥72Input/Output
51
Ogpt-4.1-2025-04-14
gpt-4.1-2025-04-14Openai
45.7
1.4K
1.05M
¥14.4 / ¥57.6Input/Output
52
Xgrok-4-1-fast-reasoning
grok-4-1-fast-reasoningXai
44.6
632
2M
¥1.44 / ¥3.6Input/Output
53
Ogpt-5-mini-high
gpt-5-mini-highOpenai
43.5
1K
400K
¥1.8 / ¥14.4Input/Output
54
Oo4-mini-2025-04-16
o4-mini-2025-04-16Openai
42.4
1.3K
200K
¥7.92 / ¥31.7Input/Output
55
Ggemini-2.5-flash-lite-preview-06-17-thinking
gemini-2.5-flash-lite-preview-06-17-thinkingGoogle
41.3
1K
65.5K
¥0.72 / ¥2.88Input/Output
56
Ogpt-4.1-mini-2025-04-14
gpt-4.1-mini-2025-04-14Openai
40.2
1.1K
1.05M
¥2.88 / ¥11.5Input/Output
57
Ggemini-1.5-pro-002
gemini-1.5-pro-002Google
39.1
395
-
-
58
MA
mistral-medium-2508
mistral-medium-2508Mistral
38.0
1.4K
262K
¥2.88 / ¥14.4Input/Output
59
Ogpt-4.5-preview-2025-02-27
gpt-4.5-preview-2025-02-27Openai
37.0
77
8.19K
¥216 / ¥432Input/Output
60
Ggemma-3-27b-it
gemma-3-27b-itGoogle
35.9
734
128K
¥2.15 / ¥2.15Input/Output
61
Aclaude-3-7-sonnet-20250219
claude-3-7-sonnet-20250219Anthropic
34.8
153
200K
¥21.6 / ¥108Input/Output
62
MAmistral-medium-2505
mistral-medium-2505Mistral
33.7
477
262K
¥2.88 / ¥14.4Input/Output
63
MAmistral-small-2506
mistral-small-2506Mistral
32.6
481
262K
¥2.88 / ¥14.4Input/Output
64
Ggemini-2.0-flash-001
gemini-2.0-flash-001Google
31.5
339
1.05M
¥1.08 / ¥4.32Input/Output
65
MAmistral-small-3.1-24b-instruct-2503
mistral-small-3.1-24b-instruct-2503Mistral
30.4
718
262K
¥2.88 / ¥14.4Input/Output
66
Ggemini-1.5-flash-002
gemini-1.5-flash-002Google
29.3
370
2M
¥0.54 / ¥2.2Input/Output
67
Ogpt-4o-2024-05-13
gpt-4o-2024-05-13Openai
28.3
1.5K
128K
¥36 / ¥108Input/Output
68
Mllama-4-maverick-17b-128e-instruct
llama-4-maverick-17b-128e-instructMeta
27.2
232
1M
¥1.8 / ¥6.26Input/Output
69
Aclaude-3-5-sonnet-20241022
claude-3-5-sonnet-20241022Anthropic
26.1
513
200K
¥21.6 / ¥108Input/Output
70
Aqwen2.5-vl-72b-instruct
qwen2.5-vl-72b-instructAlibaba
25.0
119
131K
¥16.5 / ¥49.5Input/Output
71
Aclaude-3-5-sonnet-20240620
claude-3-5-sonnet-20240620Anthropic
23.9
1.6K
200K
¥21.6 / ¥108Input/Output
72
MApixtral-large-2411
pixtral-large-2411Mistral
22.8
156
128K
¥14.4 / ¥43.2Input/Output
73
Mllama-4-scout-17b-16e-instruct
llama-4-scout-17b-16e-instructMeta
21.7
237
128K
¥1.44 / ¥5.62Input/Output
74
Aqwen2-vl-72b
qwen2-vl-72bAlibaba
20.7
291
-
-
75
UNinternvl2-26b
-
19.6
287
-
-
76
Ogpt-4-turbo-2024-04-09
gpt-4-turbo-2024-04-09Openai
18.5
937
128K
¥72 / ¥216Input/Output
77
Ogpt-4o-mini-2024-07-18
gpt-4o-mini-2024-07-18Openai
17.4
952
128K
¥1.08 / ¥4.32Input/Output
78
Ggemini-1.5-pro-001
gemini-1.5-pro-001Google
16.3
1.2K
-
-
79
Ggemini-2.0-flash-lite-preview-02-05
gemini-2.0-flash-lite-preview-02-05Google
15.2
98
1.05M
¥0.54 / ¥2.16Input/Output
80
Ogpt-4o-2024-08-06
gpt-4o-2024-08-06Openai
14.1
186
128K
¥18 / ¥72Input/Output
81
Aqwen2-vl-7b-instruct
qwen2-vl-7b-instructAlibaba
13.0
298
131K
¥2.07 / ¥5.16Input/Output
82
Aclaude-3-opus-20240229
claude-3-opus-20240229Anthropic
12.0
1K
200K
¥108 / ¥540Input/Output
83
Ggemini-1.5-flash-8b-001
gemini-1.5-flash-8b-001Google
10.9
332
2M
¥0.54 / ¥2.2Input/Output
84
Ggemini-1.5-flash-001
gemini-1.5-flash-001Google
9.8
950
2M
¥0.54 / ¥2.2Input/Output
85
Mllama-3.2-vision-90b-instruct
llama-3.2-vision-90b-instructMeta
8.7
393
131K
¥2.48 / ¥2.48Input/Output
86
MApixtral-12b-2409
pixtral-12b-2409Mistral
7.6
335
128K
¥1.08 / ¥1.08Input/Output
87
UNinternvl2-4b
-
6.5
177
-
-
88
Aclaude-3-sonnet-20240229
claude-3-sonnet-20240229Anthropic
5.4
915
200K
¥21.6 / ¥108Input/Output
89
AI
molmo-72b-0924
molmo-72b-0924Allenai
4.3
182
-
-
90
Aclaude-3-haiku-20240307
claude-3-haiku-20240307Anthropic
3.3
1K
200K
¥1.8 / ¥9Input/Output
91
Mllama-3.2-vision-11b-instruct
llama-3.2-vision-11b-instructMeta
2.2
266
131K
¥2.48 / ¥2.48Input/Output
92
UNllava-v1.6-34b
-
1.1
415
-
-
93
AImolmo-7b-d-0924
molmo-7b-d-0924Allenai
0.0
171
-
-
claude-opus-4-6-thinking why it ranks first
claude-opus-4-6-thinking ranks first with a percent score of 100.0 and 435 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
中文排行榜看什么指标？
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。
中文模型应该怎么选？
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。