1
A
claude-opus-4-7
claude-opus-4-7Anthropic
100.0
1.1K
1M
¥36 / ¥180Input/Output
Chat · Vision · Homework Leaderboard
Ranking for Vision / Homework, based on public preference data.
Homework model ranking guide
Ranking for Vision / Homework, based on public preference data.
claude-opus-4-7claude-opus-4-7-thinkinggpt-5.5-highgpt-5.5claude-opus-4-6-thinking
2
Aclaude-opus-4-7-thinking
claude-opus-4-7-thinkingAnthropic
98.7
1.1K
1M
¥36 / ¥180Input/Output
3
O
gpt-5.5-high
gpt-5.5-highOpenai
97.4
743
1.05M
¥36 / ¥216Input/Output
4
Ogpt-5.5
gpt-5.5Openai
96.1
788
1.05M
¥36 / ¥216Input/Output
5
Aclaude-opus-4-6-thinking
claude-opus-4-6-thinkingAnthropic
94.8
1.2K
1M
¥36 / ¥180Input/Output
6
Ogpt-5.4
gpt-5.4Openai
93.5
1K
1.05M
¥18 / ¥108Input/Output
7
Aclaude-opus-4-6
claude-opus-4-6Anthropic
92.2
1.4K
1M
¥36 / ¥180Input/Output
8
G
gemini-3.1-pro-preview
gemini-3.1-pro-previewGoogle
90.9
2.6K
1.05M
¥14.4 / ¥86.4Input/Output
9
M
kimi-k2.6
kimi-k2.6Moonshot
89.6
937
262K
¥6.84 / ¥28.8Input/Output
10
Ggemini-3-flash
gemini-3-flashGoogle
88.3
3.2K
1.05M
¥3.6 / ¥21.6Input/Output
11
Ggemini-3-pro
gemini-3-proGoogle
87.0
1.8K
1.05M
¥14.4 / ¥86.4Input/Output
12
Ogpt-5.4-high
gpt-5.4-highOpenai
85.7
951
1.05M
¥18 / ¥108Input/Output
13
Aclaude-sonnet-4-6
claude-sonnet-4-6Anthropic
84.4
1.5K
1M
¥21.6 / ¥108Input/Output
14
Ggemma-4-26b-a4b
gemma-4-26b-a4bGoogle
83.1
1.9K
262K
¥0.94 / ¥2.88Input/Output
15
Ggemma-4-31b
gemma-4-31bGoogle
81.8
3.1K
262K
¥3.24 / ¥7.2Input/Output
16
Ggemini-3-flash (thinking-minimal)
gemini-3-flash (thinking-minimal)Google
80.5
2.9K
1.05M
¥3.6 / ¥21.6Input/Output
17
M
muse-spark
muse-sparkMeta
79.2
782
-
-
18
Mkimi-k2.5-thinking
kimi-k2.5-thinkingMoonshot
77.9
2.1K
262K
¥4.32 / ¥21.6Input/Output
19
B
dola-seed-2.0-pro
dola-seed-2.0-proBytedance
76.6
1.6K
-
-
20
A
qwen3.7-plus-preview
qwen3.7-plus-previewAlibaba
75.3
587
131K
¥3.6 / ¥21.6Input/Output
21
Z
glm-5v-turbo
glm-5v-turboZai
74.0
1.2K
200K
¥0 / ¥0Input/Output
22
Ogpt-5.2-chat-latest-20260210
gpt-5.2-chat-latest-20260210Openai
72.7
2K
400K
¥12.6 / ¥101Input/Output
23
Aqwen3.5-397b-a17b
qwen3.5-397b-a17bAlibaba
71.4
1.7K
262K
¥3.1 / ¥18.6Input/Output
24
Ogpt-5.4-mini-high
gpt-5.4-mini-highOpenai
70.1
1.4K
400K
¥5.4 / ¥32.4Input/Output
25
Ogpt-5-chat
gpt-5-chatOpenai
68.8
1.4K
400K
¥9 / ¥72Input/Output
26
Aqwen3-vl-235b-a22b-instruct
qwen3-vl-235b-a22b-instructAlibaba
67.5
1.6K
128K
¥2.16 / ¥8.64Input/Output
27
Ggemini-2.5-pro
gemini-2.5-proGoogle
66.2
5.1K
1.05M
¥9 / ¥72Input/Output
28
Ggemini-2.5-flash-preview-09-2025
gemini-2.5-flash-preview-09-2025Google
64.9
625
1M
¥2.16 / ¥18Input/Output
29
Ogpt-5.2-high
gpt-5.2-highOpenai
63.6
2.4K
400K
¥12.6 / ¥101Input/Output
30
Ggemini-3.1-flash-lite-preview
gemini-3.1-flash-lite-previewGoogle
62.3
2.2K
1.05M
¥1.8 / ¥10.8Input/Output
31
Ogpt-5.1-high
gpt-5.1-highOpenai
61.0
1.2K
400K
¥9 / ¥72Input/Output
32
X
grok-4.20-multi-agent-beta-0309
grok-4.20-multi-agent-beta-0309Xai
59.7
1.4K
2M
¥14.4 / ¥43.2Input/Output
33
Ogpt-5.5-instant
gpt-5.5-instantOpenai
58.4
609
400K
¥9 / ¥72Input/Output
34
Aqwen3.5-122b-a10b
qwen3.5-122b-a10bAlibaba
57.1
1.5K
262K
¥2.88 / ¥23Input/Output
35
Ogpt-5.2
gpt-5.2Openai
55.8
2.5K
400K
¥12.6 / ¥101Input/Output
36
Mkimi-k2.5-instant
kimi-k2.5-instantMoonshot
54.5
564
262K
¥4.32 / ¥21.6Input/Output
37
Aqwen3.5-27b
qwen3.5-27bAlibaba
53.2
1.4K
262K
¥2.16 / ¥17.3Input/Output
38
Xgrok-4.3
grok-4.3Xai
51.9
633
1M
¥9 / ¥18Input/Output
39
Xgrok-4.20-beta-0309-reasoning
grok-4.20-beta-0309-reasoningXai
50.6
1.5K
2M
¥14.4 / ¥43.2Input/Output
40
MI
mimo-v2.5
mimo-v2.5Xiaomi
49.4
1.3K
1.05M
¥2.88 / ¥14.4Input/Output
41
B
ernie-5.0-preview-1220
ernie-5.0-preview-1220Baidu
48.1
360
128K
¥7.92 / ¥14.4Input/Output
42
Ochatgpt-4o-latest-20250326
chatgpt-4o-latest-20250326Openai
46.8
2.2K
128K
¥18 / ¥72Input/Output
43
MImimo-v2-omni
mimo-v2-omniXiaomi
45.5
1.2K
262K
¥2.88 / ¥14.4Input/Output
44
TE
hunyuan-vision-1.5-thinking
hunyuan-vision-1.5-thinkingTencent
44.2
313
-
-
45
Ogpt-4.1-2025-04-14
gpt-4.1-2025-04-14Openai
42.9
1.5K
1.05M
¥14.4 / ¥57.6Input/Output
46
Ggemini-2.5-flash
gemini-2.5-flashGoogle
41.6
4.6K
1.05M
¥2.16 / ¥18Input/Output
47
Ogpt-5.1
gpt-5.1Openai
40.3
1.4K
400K
¥9 / ¥72Input/Output
48
Aqwen3-vl-235b-a22b-thinking
qwen3-vl-235b-a22b-thinkingAlibaba
39.0
314
131K
¥2.06 / ¥8.26Input/Output
49
Oo3-2025-04-16
o3-2025-04-16Openai
37.7
2K
200K
¥14.4 / ¥57.6Input/Output
50
Oo4-mini-2025-04-16
o4-mini-2025-04-16Openai
36.4
1.7K
200K
¥7.92 / ¥31.7Input/Output
51
Ogpt-5-high
gpt-5-highOpenai
35.1
1.5K
400K
¥9 / ¥72Input/Output
52
Aclaude-opus-4-20250514
claude-opus-4-20250514Anthropic
33.8
336
200K
¥108 / ¥540Input/Output
53
Ogpt-5.4-nano-high
gpt-5.4-nano-highOpenai
32.5
1.4K
400K
¥1.44 / ¥9Input/Output
54
Ogpt-4.1-mini-2025-04-14
gpt-4.1-mini-2025-04-14Openai
31.2
1.4K
1.05M
¥2.88 / ¥11.5Input/Output
55
Ggemini-2.5-flash-lite-preview-09-2025-no-thinking
gemini-2.5-flash-lite-preview-09-2025-no-thinkingGoogle
29.9
625
1.05M
¥0.72 / ¥2.88Input/Output
56
Aclaude-sonnet-4-20250514
claude-sonnet-4-20250514Anthropic
28.6
245
200K
¥21.6 / ¥108Input/Output
57
Ogpt-5-mini-high
gpt-5-mini-highOpenai
27.3
1K
400K
¥1.8 / ¥14.4Input/Output
58
Aclaude-opus-4-20250514-thinking-16k
claude-opus-4-20250514-thinking-16kAnthropic
26.0
170
200K
¥108 / ¥540Input/Output
59
Aclaude-3-7-sonnet-20250219
claude-3-7-sonnet-20250219Anthropic
24.7
241
200K
¥21.6 / ¥108Input/Output
60
Ggemini-2.5-flash-lite-preview-06-17-thinking
gemini-2.5-flash-lite-preview-06-17-thinkingGoogle
23.4
1.4K
65.5K
¥0.72 / ¥2.88Input/Output
61
ST
step-3
step-3Stepfun
22.1
228
65.5K
¥1.8 / ¥4.68Input/Output
62
Aclaude-3-7-sonnet-20250219-thinking-32k
claude-3-7-sonnet-20250219-thinking-32kAnthropic
20.8
184
-
-
63
Ggemini-2.0-flash-001
gemini-2.0-flash-001Google
19.5
792
1.05M
¥1.08 / ¥4.32Input/Output
64
MA
mistral-small-2506
mistral-small-2506Mistral
18.2
632
262K
¥2.88 / ¥14.4Input/Output
65
Xgrok-4-0709
grok-4-0709Xai
16.9
1.1K
256K
¥21.6 / ¥108Input/Output
66
Xgrok-4-1-fast-reasoning
grok-4-1-fast-reasoningXai
15.6
1.7K
2M
¥1.44 / ¥3.6Input/Output
67
Zglm-4.5v
glm-4.5vZai
14.3
223
64K
¥4.32 / ¥13Input/Output
68
Ggemma-3-27b-it
gemma-3-27b-itGoogle
13.0
1.1K
128K
¥2.15 / ¥2.15Input/Output
69
MAmistral-medium-2508
mistral-medium-2508Mistral
11.7
2.2K
262K
¥2.88 / ¥14.4Input/Output
70
MAmistral-medium-2505
mistral-medium-2505Mistral
10.4
846
262K
¥2.88 / ¥14.4Input/Output
71
Mllama-4-maverick-17b-128e-instruct
llama-4-maverick-17b-128e-instructMeta
9.1
549
1M
¥1.8 / ¥6.26Input/Output
72
Ogpt-5-nano-high
gpt-5-nano-highOpenai
7.8
272
400K
¥0.36 / ¥2.88Input/Output
73
Zglm-4.6v
glm-4.6vZai
6.5
282
128K
¥2.16 / ¥6.48Input/Output
74
STstep-1o-turbo-202506
step-1o-turbo-202506Stepfun
5.2
251
-
-
75
MAmistral-small-3.1-24b-instruct-2503
mistral-small-3.1-24b-instruct-2503Mistral
3.9
843
262K
¥2.88 / ¥14.4Input/Output
76
Mllama-4-scout-17b-16e-instruct
llama-4-scout-17b-16e-instructMeta
2.6
500
128K
¥1.44 / ¥5.62Input/Output
77
Aclaude-3-5-sonnet-20241022
claude-3-5-sonnet-20241022Anthropic
1.3
226
200K
¥21.6 / ¥108Input/Output
78
Aclaude-3-5-haiku-20241022
claude-3-5-haiku-20241022Anthropic
0.0
232
200K
¥5.76 / ¥28.8Input/Output
claude-opus-4-7 why it ranks first
claude-opus-4-7 ranks first with a percent score of 100.0 and 1.1K 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
作业辅导排行榜看什么指标？
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。
作业辅导模型应该怎么选？
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。