Skip to content

Leaderboard

Data source: AIHOT

Model data is shown as published (Chinese).

职业交付件、业务流程、金融、法律、投行咨询长任务、客服、数据分析与医疗编码,看专业工作能不能交付。AIHOT 评分把各家难度不同的评测折算成同一种分数:50 分是参照模型的平均水平,每 15 分约是一个标准差;两个模型相差 3 分以上,先后基本不会变。评分不是正确率。分类评分只看这个领域,只列在这个领域测得够多的模型。

13 benchmarks · 4 organizations · Updated 2026-11-18 20:05 Beijing time

Domestic is inferred from vendor; open weights uses the model page’s weights link. Unranked models have no weights flag and are hidden by that filter. Prices: ¥ / million tokens.

RankModelReleasedBenchmarksCacheInputOutputScore
1Gemini 4 CarbonGoogle2026-10-2810 benchmarks¥1.33¥26.66¥133.3276.5
2Claude Fable 5.2Anthropic2026-11-0911 benchmarks¥1.33¥53.33¥266.6475.3
3Gemini 4 ArgonGoogle2026-09-3012 benchmarks¥1.33¥26.66¥133.3274.3
4Claude Opus 5.5Anthropic2026-09-2213 benchmarks¥1.33¥26.66¥133.3273.4
5Gemini 4 HydrogenGoogle2026-11-127 benchmarks¥0.5¥10¥5073.2
6Claude Fable 5.1Anthropic2026-09-0111 benchmarks¥1.67¥66.66¥333.3173.1
7gpt-6.2-astraOpenAI2026-11-179 benchmarks¥2.67¥53.33¥266.6472.9
8Claude Sonnet 5.5Anthropic2026-09-2813 benchmarks¥0.67¥13.33¥66.6672.5
9Qwen4 MaxAlibaba2026-11-1610 benchmarks¥0.5¥10¥3071.2
10Muse WonderMeta2026-10-1210 benchmarks¥1.33¥26.66¥133.3270.8
11Claude Opus 5Anthropic2026-07-249 benchmarks¥3.33¥33.33¥166.6570.6
12Muse EmberMeta2026-11-099 benchmarks¥0.0267¥0.67¥3.3370.0
13gpt-6.2-solOpenAI2026-11-179 benchmarks¥0.67¥13.33¥66.6669.9
14DeepSeek V4.1 Flash 1017DeepSeek2026-10-1710 benchmarks¥0.02¥1¥469.3
15Claude Fable 5Anthropic2026-06-098 benchmarks¥6.67¥66.66¥333.3169.0
16Kimi K3.1 ProMoonshot AI2026-10-2311 benchmarks¥1.3¥13¥6868.7
17Hy4Tencent2026-11-049 benchmarks¥0.3¥6¥1868.6
18GPT-6 AstraOpenAI2026-09-0313 benchmarks¥6.67¥66.66¥333.3168.5
19Muse Spark 1.3Meta2026-09-0210 benchmarks¥1¥8.33¥28.3368.3
20Grok 4.7xAI2026-09-2113 benchmarks¥3.33¥13.33¥4068.0
21Qwen3.8 Max 0902Alibaba2026-09-019 benchmarks¥1.5¥12¥3667.9
22Inkling 2 SmallThinking Machines Lab2026-11-059 benchmarks¥0.2¥2¥6.6767.8
23GPT-5.6 SolOpenAI2026-07-097 benchmarks¥3.33¥33.33¥199.9867.6
24Grok 4.6xAI2026-08-129 benchmarks¥3.33¥13.33¥4067.3
25GPT-6.1 SolOpenAI2026-09-2913 benchmarks¥0.67¥13.33¥66.6667.3
26GLM-5.3Z.ai2026-08-1813 benchmarks¥2¥8¥2866.4
27Gemini 3.8 FlashGoogle2026-09-0213 benchmarks¥1¥10¥5066.3
28Qwen3.8 MaxAlibaba2026-07-199 benchmarks¥1.5¥12¥3665.9
29MiMo-V2.6-ProXiaomi2026-09-2110 benchmarks¥0.025¥3¥665.6
30Hy 4 PreviewTencent2026-08-285 benchmarks¥0.3¥6¥1865.1
31Kimi K3Moonshot AI2026-07-1613 benchmarks¥2¥20¥10064.9
32MiMo V 2.6 FlashXiaomi2026-09-218 benchmarks¥0.02¥1¥264.8
33GPT-5.6 TerraOpenAI2026-07-098 benchmarks¥1.33¥13.33¥79.9964.5
34MiniMax-M3.1-FlashMiniMax2026-10-198 benchmarks¥0.1¥1¥464.1
35GPT-6.1 TerraOpenAI2026-10-2610 benchmarks¥0.33¥6.67¥33.3364.0
36Claude Haiku 5.5Anthropic2026-10-0713 benchmarks¥0.0667¥0.67¥3.3363.9
37GPT-6 SolOpenAI2026-09-229 benchmarks¥1.33¥13.33¥66.6663.9
38DeepSeek V4.1 FlashDeepSeek2026-09-1012 benchmarks¥0.02¥1¥463.9
39Gemini 3.7 FlashGoogle2026-08-138 benchmarks¥1¥10¥5063.4
40Step 5 PreviewStepFun2026-09-189 benchmarks¥0.7¥7¥2063.3
41GLM-5.3 FlashZ.ai2026-08-2613 benchmarks¥0.23¥0.8¥2.863.3
42Qwen3.8 Flash NextAlibaba2026-08-264 benchmarks¥0.1¥0.8¥2.762.9
43GPT-5.5OpenAI2026-04-238 benchmarks¥3.33¥33.33¥199.9862.7
44DeepSeek V4 Pro 0813DeepSeek2026-08-1311 benchmarks¥0.15¥4.5¥13.562.6
45Claude Opus 4.8Anthropic2026-05-288 benchmarks¥3.33¥33.33¥166.6562.4
46Muse Spark 1.2Meta2026-08-057 benchmarks¥1¥8.33¥28.3362.1
47Mistral Large 4Mistral AI2026-10-068 benchmarks¥0.47¥4.67¥1461.8
48Claude Sonnet 5Anthropic2026-06-308 benchmarks¥1.33¥13.33¥66.6661.8
49Grok 4.5xAI2026-07-088 benchmarks¥2¥13.33¥4061.5
50Claude Opus 4.7Anthropic2026-04-167 benchmarks¥3.33¥33.33¥166.6561.4

Blended usage: cache hits:input:output = 7:2:1. 2026-11-17 · $1 = ¥6.6661

Unranked · 6

Muse Wonder FullMeta

本轮未收录官方 API 价格或公开权重

73.5
ember-1Fireworks AI

评测数量还不够

65.6
Ling 3.1 Flash 1019InclusionAI

评测数量还不够

65.4
Ling 3.1 FlashInclusionAI

评测数量还不够

63.4
Qwen3.8 2.4 T A 95 BAlibaba

评测数量还不够

63.3
hy4-flashTencent

评测数量还不够

62.4
All models · 45
RankModelReleasedBenchmarksCacheInputOutputScore
51DeepSeek V4 Flash 0731DeepSeek2026-07-316 benchmarks¥0.05¥1.5¥4.561.2
52Qwen3.8-27BAlibaba2026-08-147 benchmarks¥0.6¥3¥1260.7
53GPT-6 LunaOpenAI2026-09-2213 benchmarks¥0.0667¥0.67¥3.3360.7
54GPT-5.6 LunaOpenAI2026-07-098 benchmarks¥0.13¥1.33¥860.5
55GPT-5.4OpenAI2026-03-053 benchmarks¥1.67¥16.67¥99.9960.0
56Muse Spark OpenMeta2026-10-1510 benchmarks———59.9
57Claude Opus 4.6Anthropic2026-02-052 benchmarks¥3.33¥33.33¥166.6557.8
58GLM-5.2Z.ai2026-06-166 benchmarks¥2¥8¥2856.6
59Muse Spark 1.1Meta2026-07-096 benchmarks¥1¥8.33¥28.3356.2
60Claude Sonnet 4.6Anthropic2026-02-178 benchmarks¥2¥20¥99.9955.7
61Gemini 3.6 FlashGoogle2026-07-217 benchmarks¥1¥10¥5055.5
62Beam 1.0Reflection2026-10-1610 benchmarks———55.5
63Gemini 3.5 FlashGoogle2026-05-198 benchmarks¥1¥10¥59.9955.1
64DeepSeek V4 Pro PreviewDeepSeek2026-04-247 benchmarks¥0.025¥3¥654.9
65MiniMax-M3MiniMax2026-06-0112 benchmarks¥0.42¥2.1¥8.453.6
66Qwen3.7 MaxAlibaba2026-05-197 benchmarks¥2.4¥12¥3651.8
67Gemini 3.1 Pro PreviewGoogle2026-02-199 benchmarks¥1.33¥13.33¥79.9951.8
68GLM-5.1Z.ai2026-04-075 benchmarks¥1.3¥6¥2450.7
69Kimi K2.7 CodeMoonshot AI2026-06-125 benchmarks¥1.3¥6.5¥2749.3
70DeepSeek V4 Flash PreviewDeepSeek2026-04-245 benchmarks¥0.02¥1¥248.8
71InklingThinking Machines Lab2026-07-1513 benchmarks¥1.13¥6.67¥2747.8
72Kimi K2.6Moonshot AI2026-04-206 benchmarks¥1.1¥6.5¥2746.9
73Inkling-SmallThinking Machines Lab2026-07-3010 benchmarks¥0.4¥2¥846.6
74Nemotron 3.5 Super VLNVIDIA2026-10-155 benchmarks———46.4
75Qwen3.6 PlusAlibaba2026-04-014 benchmarks¥0.2¥2¥1246.0
76MiMo-V2.5-ProXiaomi2026-04-226 benchmarks¥0.025¥3¥645.7
77Qwen3.6-27BAlibaba2026-04-224 benchmarks—¥3¥1845.3
78Qwen3.7 PlusAlibaba2026-06-015 benchmarks¥0.4¥2¥845.0
79GPT-5.4 Mini 2026-03-17OpenAI2026-03-177 benchmarks¥0.5¥5¥3044.7
80Gemini 3.5 Flash LiteGoogle2026-07-219 benchmarks¥0.2¥2¥16.6743.8
81MiMo-V2.5Xiaomi2026-04-225 benchmarks¥0.02¥1¥241.0
82Nemotron 3 UltraNVIDIA2026-06-046 benchmarks———39.9
83Grok 4.3xAI2026-04-177 benchmarks¥1.33¥8.33¥16.6738.4
84Muse GlimmerMeta2026-08-104 benchmarks———38.3
85GPT-5.4 Nano 2026-03-17OpenAI2026-03-176 benchmarks¥0.13¥1.33¥8.3336.4
86MiniMax M 2.7MiniMax2026-03-186 benchmarks¥0.42¥2.1¥8.435.9
87Claude Haiku 4.5 20251001Anthropic2025-10-152 benchmarks¥0.67¥6.67¥33.3334.0
88GPT-5 MiniOpenAI2025-08-073 benchmarks¥0.17¥1.67¥13.3334.0
89Mistral Medium 3.5Mistral AI2026-04-296 benchmarks¥1¥10¥5032.3
90Gemma 4 31 BGoogle2026-04-023 benchmarksFreeFreeFree31.8
91Gemini 2.5 ProGoogle2025-06-173 benchmarks¥0.83¥8.33¥66.6628.4
92Gemini 3.1 Flash Lite PreviewGoogle2026-03-036 benchmarks¥0.17¥1.67¥1026.9
93Granite 4.2 8 BIBM2026-08-253 benchmarks———22.3
94gpt-oss-120bOpenAI2025-08-054 benchmarks———17.5
95Granite 4.2 3 BIBM2026-08-253 benchmarks———12.0