Skip to content

Leaderboard

Data source: AIHOT

Model data is shown as published (Chinese).

事实准确、长文理解、语言与按要求作答、识破错误前提,看模型知道多少、答得多稳。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。

8 benchmarks · 6 organizations · Updated 2026-11-18 14:08 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
1gpt-6.2-astraOpenAI2026-11-174 benchmarks¥2.67¥53.33¥266.6482.3
2Claude Fable 5.2Anthropic2026-11-096 benchmarks¥1.33¥53.33¥266.6482.1
3Gemini 4 CarbonGoogle2026-10-286 benchmarks¥1.33¥26.66¥133.3279.3
4gpt-6.2-solOpenAI2026-11-173 benchmarks¥0.67¥13.33¥66.6676.9
5GPT-6 AstraOpenAI2026-09-038 benchmarks¥6.67¥66.66¥333.3174.4
6Gemini 4 ArgonGoogle2026-09-307 benchmarks¥1.33¥26.66¥133.3273.1
7Gemini 4 HydrogenGoogle2026-11-122 benchmarks¥0.5¥10¥5072.9
8GPT-6.1 SolOpenAI2026-09-298 benchmarks¥0.67¥13.33¥66.6672.2
9Claude Fable 5.1Anthropic2026-09-017 benchmarks¥1.67¥66.66¥333.3170.8
10Claude Opus 5.5Anthropic2026-09-228 benchmarks¥1.33¥26.66¥133.3270.4
11Kimi K3.1 ProMoonshot AI2026-10-236 benchmarks¥1.3¥13¥6870.2
12Claude Fable 5Anthropic2026-06-096 benchmarks¥6.67¥66.66¥333.3169.7
13Claude Opus 5Anthropic2026-07-247 benchmarks¥3.33¥33.33¥166.6568.9
14Gemini 3.8 FlashGoogle2026-09-027 benchmarks¥1¥10¥5068.6
15GPT-5.6 SolOpenAI2026-07-096 benchmarks¥3.33¥33.33¥199.9867.7
16Qwen4 MaxAlibaba2026-11-164 benchmarks¥0.5¥10¥3067.0
17Kimi K3Moonshot AI2026-07-168 benchmarks¥2¥20¥10066.8
18GPT-6.1 TerraOpenAI2026-10-266 benchmarks¥0.33¥6.67¥33.3366.5
19Hy4Tencent2026-11-045 benchmarks¥0.3¥6¥1866.3
20Gemini 3.7 FlashGoogle2026-08-136 benchmarks¥1¥10¥5066.1
21DeepSeek V4.1 Flash 1017DeepSeek2026-10-176 benchmarks¥0.02¥1¥465.9
22Muse WonderMeta2026-10-126 benchmarks¥1.33¥26.66¥133.3265.4
23GPT-5.5OpenAI2026-04-236 benchmarks¥3.33¥33.33¥199.9865.2
24GPT-6 SolOpenAI2026-09-227 benchmarks¥1.33¥13.33¥66.6665.0
25Grok 4.7xAI2026-09-218 benchmarks¥3.33¥13.33¥4065.0
26Claude Sonnet 5.5Anthropic2026-09-288 benchmarks¥0.67¥13.33¥66.6664.6
27Muse Spark 1.3Meta2026-09-025 benchmarks¥1¥8.33¥28.3364.5
28Claude Opus 4.8Anthropic2026-05-286 benchmarks¥3.33¥33.33¥166.6564.1
29Muse EmberMeta2026-11-093 benchmarks¥0.0267¥0.67¥3.3362.6
30Gemini 3.1 Pro PreviewGoogle2026-02-196 benchmarks¥1.33¥13.33¥79.9962.4
31Grok 4.6xAI2026-08-127 benchmarks¥3.33¥13.33¥4062.2
32DeepSeek V4.1 FlashDeepSeek2026-09-106 benchmarks¥0.02¥1¥461.9
33Qwen3.8 MaxAlibaba2026-07-197 benchmarks¥1.5¥12¥3661.8
34Inkling 2 SmallThinking Machines Lab2026-11-053 benchmarks¥0.2¥2¥6.6761.8
35GLM-5.3Z.ai2026-08-188 benchmarks¥2¥8¥2861.5
36Gemini 3.6 FlashGoogle2026-07-216 benchmarks¥1¥10¥5060.8
37Gemini 3.5 FlashGoogle2026-05-196 benchmarks¥1¥10¥59.9960.7
38Muse Spark 1.2Meta2026-08-056 benchmarks¥1¥8.33¥28.3360.5
39Step 5 PreviewStepFun2026-09-185 benchmarks¥0.7¥7¥2060.5
40Qwen3.7 MaxAlibaba2026-05-196 benchmarks¥2.4¥12¥3660.5
41Qwen3.8 Max 0902Alibaba2026-09-014 benchmarks¥1.5¥12¥3660.5
42MiMo-V2.6-ProXiaomi2026-09-214 benchmarks¥0.025¥3¥660.1
43Grok 4.5xAI2026-07-086 benchmarks¥2¥13.33¥4060.0
44GPT-5.6 TerraOpenAI2026-07-097 benchmarks¥1.33¥13.33¥79.9959.7
45Hy 4 PreviewTencent2026-08-282 benchmarks¥0.3¥6¥1859.5
46Claude Opus 4.6Anthropic2026-02-055 benchmarks¥3.33¥33.33¥166.6559.4
47Claude Opus 4.7Anthropic2026-04-165 benchmarks¥3.33¥33.33¥166.6559.0
48GPT-5.4OpenAI2026-03-054 benchmarks¥1.67¥16.67¥99.9958.8
49Muse Spark 1.1Meta2026-07-095 benchmarks¥1¥8.33¥28.3358.6
50Muse Spark OpenMeta2026-10-154 benchmarks———58.2

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

Unranked · 2

Muse Wonder FullMeta

本轮未收录官方 API 价格或公开权重

68.3
Qwen3.8 2.4 T A 95 BAlibaba

评测数量还不够

59.7
All models · 45
RankModelReleasedBenchmarksCacheInputOutputScore
51Qwen3.8 Flash NextAlibaba2026-08-264 benchmarks¥0.1¥0.8¥2.758.0
52Claude Haiku 5.5Anthropic2026-10-077 benchmarks¥0.0667¥0.67¥3.3356.7
53DeepSeek V4 Pro 0813DeepSeek2026-08-136 benchmarks¥0.15¥4.5¥13.556.7
54GPT-6 LunaOpenAI2026-09-227 benchmarks¥0.0667¥0.67¥3.3355.9
55Claude Sonnet 5Anthropic2026-06-306 benchmarks¥1.33¥13.33¥66.6655.3
56GLM-5.3 FlashZ.ai2026-08-265 benchmarks¥0.23¥0.8¥2.854.1
57DeepSeek V4 Flash 0731DeepSeek2026-07-315 benchmarks¥0.05¥1.5¥4.554.0
58Beam 1.0Reflection2026-10-163 benchmarks———53.8
59Claude Sonnet 4.6Anthropic2026-02-176 benchmarks¥2¥20¥99.9953.5
60Qwen3.8-27BAlibaba2026-08-146 benchmarks¥0.6¥3¥1253.5
61GPT-5.6 LunaOpenAI2026-07-097 benchmarks¥0.13¥1.33¥853.3
62Kimi K2.6Moonshot AI2026-04-206 benchmarks¥1.1¥6.5¥2753.2
63MiniMax-M3.1-FlashMiniMax2026-10-195 benchmarks¥0.1¥1¥453.0
64MiniMax-M3MiniMax2026-06-017 benchmarks¥0.42¥2.1¥8.452.7
65Gemini 3.5 Flash LiteGoogle2026-07-216 benchmarks¥0.2¥2¥16.6752.6
66MiMo V 2.6 FlashXiaomi2026-09-213 benchmarks¥0.02¥1¥252.1
67Qwen3.6 PlusAlibaba2026-04-015 benchmarks¥0.2¥2¥1252.1
68GLM-5.2Z.ai2026-06-167 benchmarks¥2¥8¥2851.1
69InklingThinking Machines Lab2026-07-155 benchmarks¥1.13¥6.67¥2750.9
70Mistral Large 4Mistral AI2026-10-062 benchmarks¥0.47¥4.67¥1450.7
71Kimi K2.7 CodeMoonshot AI2026-06-124 benchmarks¥1.3¥6.5¥2750.5
72DeepSeek V4 Pro PreviewDeepSeek2026-04-247 benchmarks¥0.025¥3¥649.8
73Nemotron 3 UltraNVIDIA2026-06-045 benchmarks———49.6
74Qwen3.7 PlusAlibaba2026-06-013 benchmarks¥0.4¥2¥849.6
75Grok 4.3xAI2026-04-176 benchmarks¥1.33¥8.33¥16.6747.6
76Nemotron 3.5 Super VLNVIDIA2026-10-153 benchmarks———47.4
77GLM-5.1Z.ai2026-04-074 benchmarks¥1.3¥6¥2447.1
78MiMo-V2.5-ProXiaomi2026-04-224 benchmarks¥0.025¥3¥646.8
79DeepSeek V4 Flash PreviewDeepSeek2026-04-243 benchmarks¥0.02¥1¥246.7
80GPT-5.4 Mini 2026-03-17OpenAI2026-03-176 benchmarks¥0.5¥5¥3046.5
81MiMo-V2.5Xiaomi2026-04-222 benchmarks¥0.02¥1¥244.3
82Qwen3.6-27BAlibaba2026-04-223 benchmarks—¥3¥1844.2
83Inkling-SmallThinking Machines Lab2026-07-304 benchmarks¥0.4¥2¥842.4
84GPT-5.4 Nano 2026-03-17OpenAI2026-03-175 benchmarks¥0.13¥1.33¥8.3341.3
85Muse GlimmerMeta2026-08-102 benchmarks———40.2
86GPT-5 MiniOpenAI2025-08-073 benchmarks¥0.17¥1.67¥13.3336.8
87Gemma 4 31 BGoogle2026-04-022 benchmarksFreeFreeFree35.4
88Gemini 2.5 ProGoogle2025-06-173 benchmarks¥0.83¥8.33¥66.6633.6
89MiniMax M 2.7MiniMax2026-03-184 benchmarks¥0.42¥2.1¥8.433.4
90Claude Haiku 4.5 20251001Anthropic2025-10-152 benchmarks¥0.67¥6.67¥33.3333.4
91Mistral Medium 3.5Mistral AI2026-04-294 benchmarks¥1¥10¥5030.4
92Gemini 3.1 Flash Lite PreviewGoogle2026-03-035 benchmarks¥0.17¥1.67¥1027.3
93Granite 4.2 8 BIBM2026-08-252 benchmarks———25.4
94gpt-oss-120bOpenAI2025-08-054 benchmarks———18.5
95Granite 4.2 3 BIBM2026-08-252 benchmarks———11.4