1
A
claude-opus-4-7
claude-opus-4-7Anthropic
100.0
1.8K
1M
¥36 / ¥180Input/Output
Chat · Vision · Diagram Leaderboard
Ranking for Vision / Diagram, based on public preference data.
Diagram model ranking guide
Ranking for Vision / Diagram, based on public preference data.
claude-opus-4-7claude-opus-4-7-thinkingclaude-opus-4-6-thinkinggpt-5.5claude-opus-4-6
2
Aclaude-opus-4-7-thinking
claude-opus-4-7-thinkingAnthropic
98.8
1.8K
1M
¥36 / ¥180Input/Output
3
Aclaude-opus-4-6-thinking
claude-opus-4-6-thinkingAnthropic
97.5
1.8K
1M
¥36 / ¥180Input/Output
4
O
gpt-5.5
gpt-5.5Openai
96.3
1.2K
1.05M
¥36 / ¥216Input/Output
5
Aclaude-opus-4-6
claude-opus-4-6Anthropic
95.1
2.2K
1M
¥36 / ¥180Input/Output
6
Ogpt-5.4-high
gpt-5.4-highOpenai
93.8
1.6K
1.05M
¥18 / ¥108Input/Output
7
M
muse-spark
muse-sparkMeta
92.6
1.2K
-
-
8
G
gemini-3.1-pro-preview
gemini-3.1-pro-previewGoogle
91.4
4.2K
1.05M
¥14.4 / ¥86.4Input/Output
9
Aclaude-sonnet-4-6
claude-sonnet-4-6Anthropic
90.1
2.4K
1M
¥21.6 / ¥108Input/Output
10
Ogpt-5.4
gpt-5.4Openai
88.9
1.5K
1.05M
¥18 / ¥108Input/Output
11
Ogpt-5.5-high
gpt-5.5-highOpenai
87.7
1.2K
1.05M
¥36 / ¥216Input/Output
12
Ggemini-3-pro
gemini-3-proGoogle
86.4
2.9K
1.05M
¥14.4 / ¥86.4Input/Output
13
M
kimi-k2.6
kimi-k2.6Moonshot
85.2
1.5K
262K
¥6.84 / ¥28.8Input/Output
14
A
qwen3.7-plus-preview
qwen3.7-plus-previewAlibaba
84.0
977
131K
¥3.6 / ¥21.6Input/Output
15
Ggemini-3-flash
gemini-3-flashGoogle
82.7
5.1K
1.05M
¥3.6 / ¥21.6Input/Output
16
B
dola-seed-2.0-pro
dola-seed-2.0-proBytedance
81.5
2.3K
-
-
17
Ogpt-5.2-chat-latest-20260210
gpt-5.2-chat-latest-20260210Openai
80.2
3.1K
400K
¥12.6 / ¥101Input/Output
18
Mkimi-k2.5-thinking
kimi-k2.5-thinkingMoonshot
79.0
3.6K
262K
¥4.32 / ¥21.6Input/Output
19
Aqwen3.5-397b-a17b
qwen3.5-397b-a17bAlibaba
77.8
3K
262K
¥3.1 / ¥18.6Input/Output
20
Ggemma-4-31b
gemma-4-31bGoogle
76.5
4.4K
262K
¥3.24 / ¥7.2Input/Output
21
Z
glm-5v-turbo
glm-5v-turboZai
75.3
1.9K
200K
¥0 / ¥0Input/Output
22
Ggemini-3-flash (thinking-minimal)
gemini-3-flash (thinking-minimal)Google
74.1
4.9K
1.05M
¥3.6 / ¥21.6Input/Output
23
Ggemini-2.5-pro
gemini-2.5-proGoogle
72.8
8.9K
1.05M
¥9 / ¥72Input/Output
24
Ogpt-5.5-instant
gpt-5.5-instantOpenai
71.6
1.1K
400K
¥9 / ¥72Input/Output
25
Aqwen-vl-max-2025-08-13
qwen-vl-max-2025-08-13Alibaba
70.4
356
131K
¥1.66 / ¥4.13Input/Output
26
Ogpt-5.2-high
gpt-5.2-highOpenai
69.1
3.8K
400K
¥12.6 / ¥101Input/Output
27
Ogpt-5.1-high
gpt-5.1-highOpenai
67.9
2.2K
400K
¥9 / ¥72Input/Output
28
Ggemma-4-26b-a4b
gemma-4-26b-a4bGoogle
66.7
2.7K
262K
¥0.94 / ¥2.88Input/Output
29
MI
mimo-v2.5
mimo-v2.5Xiaomi
65.4
1.9K
1.05M
¥2.88 / ¥14.4Input/Output
30
Mkimi-k2.5-instant
kimi-k2.5-instantMoonshot
64.2
911
262K
¥4.32 / ¥21.6Input/Output
31
Ochatgpt-4o-latest-20250326
chatgpt-4o-latest-20250326Openai
63.0
3.7K
128K
¥18 / ¥72Input/Output
32
Aqwen3-vl-235b-a22b-instruct
qwen3-vl-235b-a22b-instructAlibaba
61.7
2.7K
128K
¥2.16 / ¥8.64Input/Output
33
X
grok-4.20-multi-agent-beta-0309
grok-4.20-multi-agent-beta-0309Xai
60.5
2.2K
2M
¥14.4 / ¥43.2Input/Output
34
Ogpt-5.4-mini-high
gpt-5.4-mini-highOpenai
59.3
2.2K
400K
¥5.4 / ¥32.4Input/Output
35
Ogpt-5-chat
gpt-5-chatOpenai
58.0
2.6K
400K
¥9 / ¥72Input/Output
36
Xgrok-4.20-beta-0309-reasoning
grok-4.20-beta-0309-reasoningXai
56.8
2.5K
2M
¥14.4 / ¥43.2Input/Output
37
Ogpt-5.2
gpt-5.2Openai
55.6
4K
400K
¥12.6 / ¥101Input/Output
38
Ggemini-2.5-flash-preview-09-2025
gemini-2.5-flash-preview-09-2025Google
54.3
973
1M
¥2.16 / ¥18Input/Output
39
MImimo-v2-omni
mimo-v2-omniXiaomi
53.1
2K
262K
¥2.88 / ¥14.4Input/Output
40
Xgrok-4.3
grok-4.3Xai
51.9
1.1K
1M
¥9 / ¥18Input/Output
41
Ggemini-2.5-flash
gemini-2.5-flashGoogle
50.6
7.7K
1.05M
¥2.16 / ¥18Input/Output
42
Ogpt-5.1
gpt-5.1Openai
49.4
2.4K
400K
¥9 / ¥72Input/Output
43
Ggemini-3.1-flash-lite-preview
gemini-3.1-flash-lite-previewGoogle
48.1
3.5K
1.05M
¥1.8 / ¥10.8Input/Output
44
Aqwen3.5-122b-a10b
qwen3.5-122b-a10bAlibaba
46.9
2.6K
262K
¥2.88 / ¥23Input/Output
45
Aqwen3.5-27b
qwen3.5-27bAlibaba
45.7
2.4K
262K
¥2.16 / ¥17.3Input/Output
46
B
ernie-5.0-preview-1220
ernie-5.0-preview-1220Baidu
44.4
704
128K
¥7.92 / ¥14.4Input/Output
47
Ogpt-5-high
gpt-5-highOpenai
43.2
3K
400K
¥9 / ¥72Input/Output
48
Oo3-2025-04-16
o3-2025-04-16Openai
42.0
3.6K
200K
¥14.4 / ¥57.6Input/Output
49
Ogpt-4.1-2025-04-14
gpt-4.1-2025-04-14Openai
40.7
2.8K
1.05M
¥14.4 / ¥57.6Input/Output
50
Aqwen3-vl-235b-a22b-thinking
qwen3-vl-235b-a22b-thinkingAlibaba
39.5
479
131K
¥2.06 / ¥8.26Input/Output
51
Ogpt-5-mini-high
gpt-5-mini-highOpenai
38.3
2K
400K
¥1.8 / ¥14.4Input/Output
52
Xgrok-4-0709
grok-4-0709Xai
37.0
2.5K
256K
¥21.6 / ¥108Input/Output
53
Xgrok-4-1-fast-reasoning
grok-4-1-fast-reasoningXai
35.8
2.7K
2M
¥1.44 / ¥3.6Input/Output
54
Ogpt-5.4-nano-high
gpt-5.4-nano-highOpenai
34.6
2.2K
400K
¥1.44 / ¥9Input/Output
55
Ggemini-2.5-flash-lite-preview-09-2025-no-thinking
gemini-2.5-flash-lite-preview-09-2025-no-thinkingGoogle
33.3
986
1.05M
¥0.72 / ¥2.88Input/Output
56
Oo4-mini-2025-04-16
o4-mini-2025-04-16Openai
32.1
2.9K
200K
¥7.92 / ¥31.7Input/Output
57
Aclaude-sonnet-4-20250514-thinking-32k
claude-sonnet-4-20250514-thinking-32kAnthropic
30.9
230
200K
¥21.6 / ¥108Input/Output
58
TE
hunyuan-vision-1.5-thinking
hunyuan-vision-1.5-thinkingTencent
29.6
497
-
-
59
Ggemini-2.5-flash-lite-preview-06-17-thinking
gemini-2.5-flash-lite-preview-06-17-thinkingGoogle
28.4
2.5K
65.5K
¥0.72 / ¥2.88Input/Output
60
ST
step-1o-turbo-202506
step-1o-turbo-202506Stepfun
27.2
394
-
-
61
Ogpt-4.1-mini-2025-04-14
gpt-4.1-mini-2025-04-14Openai
25.9
2.4K
1.05M
¥2.88 / ¥11.5Input/Output
62
Aclaude-sonnet-4-20250514
claude-sonnet-4-20250514Anthropic
24.7
397
200K
¥21.6 / ¥108Input/Output
63
Zglm-4.6v
glm-4.6vZai
23.5
551
128K
¥2.16 / ¥6.48Input/Output
64
Aclaude-3-7-sonnet-20250219-thinking-32k
claude-3-7-sonnet-20250219-thinking-32kAnthropic
22.2
304
-
-
65
Aclaude-opus-4-20250514
claude-opus-4-20250514Anthropic
21.0
471
200K
¥108 / ¥540Input/Output
66
MA
mistral-medium-2508
mistral-medium-2508Mistral
19.8
3.7K
262K
¥2.88 / ¥14.4Input/Output
67
Aclaude-opus-4-20250514-thinking-16k
claude-opus-4-20250514-thinking-16kAnthropic
18.5
285
200K
¥108 / ¥540Input/Output
68
Ggemma-3-27b-it
gemma-3-27b-itGoogle
17.3
1.8K
128K
¥2.15 / ¥2.15Input/Output
69
MAmistral-medium-2505
mistral-medium-2505Mistral
16.0
1.4K
262K
¥2.88 / ¥14.4Input/Output
70
Zglm-4.5v
glm-4.5vZai
14.8
376
64K
¥4.32 / ¥13Input/Output
71
STstep-3
step-3Stepfun
13.6
364
65.5K
¥1.8 / ¥4.68Input/Output
72
Aclaude-3-7-sonnet-20250219
claude-3-7-sonnet-20250219Anthropic
12.3
306
200K
¥21.6 / ¥108Input/Output
73
Ggemini-2.0-flash-001
gemini-2.0-flash-001Google
11.1
1.1K
1.05M
¥1.08 / ¥4.32Input/Output
74
Ogpt-5-nano-high
gpt-5-nano-highOpenai
9.9
527
400K
¥0.36 / ¥2.88Input/Output
75
TEhunyuan-large-vision
hunyuan-large-visionTencent
8.6
263
-
-
76
Mllama-4-maverick-17b-128e-instruct
llama-4-maverick-17b-128e-instructMeta
7.4
970
1M
¥1.8 / ¥6.26Input/Output
77
Aclaude-3-5-sonnet-20241022
claude-3-5-sonnet-20241022Anthropic
6.2
318
200K
¥21.6 / ¥108Input/Output
78
MAmistral-small-2506
mistral-small-2506Mistral
4.9
1.2K
262K
¥2.88 / ¥14.4Input/Output
79
Mllama-4-scout-17b-16e-instruct
llama-4-scout-17b-16e-instructMeta
3.7
867
128K
¥1.44 / ¥5.62Input/Output
80
MAmistral-small-3.1-24b-instruct-2503
mistral-small-3.1-24b-instruct-2503Mistral
2.5
1.7K
262K
¥2.88 / ¥14.4Input/Output
81
Aclaude-3-5-haiku-20241022
claude-3-5-haiku-20241022Anthropic
1.2
325
200K
¥5.76 / ¥28.8Input/Output
82
AI
molmo-2-8b
molmo-2-8bAllenai
0.0
281
-
-
claude-opus-4-7 why it ranks first
claude-opus-4-7 ranks first with a percent score of 100.0 and 1.8K 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
图表理解排行榜看什么指标？
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。
图表理解模型应该怎么选？
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。