Skip to content
HOTAI LEADERBOARD

AI model leaderboard

金融分析、法律咨询与银行业务,看专业任务能否完成。

2 evaluations·2 organizations·10/01 14:05 updated

专业办公TOP 30

Ranked by shared evidence across public evaluations
Top 30 models, sortable by column
Model
01Gemini 4 ArgonGoogleReleased 2026-09-30 · LowCached input —Input — · Output —99.9
02claude-sonnet-5-5—Released — · LowCached input —Input — · Output —99.7
03Claude Opus 5.5AnthropicReleased 2026-09-17 · LowCached input ¥1.34Input ¥26.82 · Output ¥134.0999.7
04Claude Fable 5.1AnthropicReleased 2026-09-01 · LowCached input ¥1.68Input ¥67.05 · Output ¥335.2399.5
05Gemini 3.7 FlashGoogleReleased 2026-08-13 · LowCached input ¥0.5Input ¥5.03 · Output ¥25.1499.2
06Claude Opus 5AnthropicReleased 2026-07-24 · LowCached input ¥3.35Input ¥33.52 · Output ¥167.6198.5
07Grok 4.6xAIReleased 2026-08-12 · LowCached input ¥3.35Input ¥13.41 · Output ¥40.2396.9
08GPT-6 AstraOpenAIReleased 2026-09-03 · LowCached input ¥6.7Input ¥67.05 · Output ¥335.2395.5
09Gemini 3.8 FlashGoogleReleased 2026-09-02 · LowCached input ¥0.5Input ¥5.03 · Output ¥25.1495.1
10Claude Fable 5AnthropicReleased 2026-06-09 · LowCached input ¥6.7Input ¥67.05 · Output ¥335.2391.7
11Qwen3.8 MaxAlibabaReleased 2026-07-19 · LowCached input —Input ¥12 · Output ¥3687.4
12GPT-6.1 SolOpenAIReleased 2026-09-29 · LowCached input —Input — · Output —86.7
13Muse Spark 1.3MetaReleased 2026-09-02 · LowCached input —Input ¥8.38 · Output ¥28.4986.0
14GPT-5.6 TerraOpenAIReleased 2026-07-09 · LowCached input ¥1.34Input ¥13.41 · Output ¥80.4581.3
15GLM-5.3Z.aiReleased 2026-08-18 · LowCached input ¥1.74Input ¥9.39 · Output ¥29.579.2
16Grok 4.5xAIReleased 2026-07-08 · LowCached input ¥2.01Input ¥13.41 · Output ¥40.2373.7
17DeepSeek V4 Flash 0731DeepSeekReleased 2026-07-31 · LowCached input ¥0.1Input ¥3 · Output ¥972.7
18GPT-5.5OpenAIReleased 2026-04-23 · LowCached input ¥3.35Input ¥33.52 · Output ¥201.1471.9
19Grok 4.7xAIReleased 2026-09-21 · LowCached input ¥3.35Input ¥13.41 · Output ¥40.2369.8
20Claude Sonnet 5AnthropicReleased 2026-06-30 · LowCached input ¥1.34Input ¥13.41 · Output ¥67.0568.9
21GPT-6 SolOpenAIReleased 2026-09-22 · LowCached input ¥1.34Input ¥13.41 · Output ¥67.0562.5
22GLM-5.3 FlashZ.aiReleased 2026-08-26 · LowCached input ¥0.23Input ¥0.8 · Output ¥2.861.6
23GPT-5.6 SolOpenAIReleased 2026-07-09 · LowCached input ¥2.68Input ¥26.82 · Output ¥134.0955.0
24Kimi K3Moonshot AIReleased 2026-07-16 · LowCached input ¥2Input ¥20 · Output ¥10052.3
25Claude Opus 4.7AnthropicReleased 2026-04-16 · LowCached input ¥3.35Input ¥33.52 · Output ¥167.6145.6
26Claude Opus 4.8AnthropicReleased 2026-05-28 · LowCached input ¥3.35Input ¥33.52 · Output ¥167.6144.7
27Qwen3.8 27 BAlibabaReleased 2026-08-14 · LowCached input ¥0.6Input ¥3 · Output ¥1238.6
28DeepSeek V4 Pro 0813DeepSeekReleased 2026-08-13 · LowCached input ¥0.3Input ¥9 · Output ¥2736.8
29Gemini 3.6 FlashGoogleReleased 2026-07-21 · LowCached input ¥0.5Input ¥5.03 · Output ¥25.1436.0
30GLM-5.2Z.aiReleased 2026-06-16 · LowCached input ¥2Input ¥8 · Output ¥2830.5

Up to 30 models are shown per board

The consensus index is not accuracy; ties follow the ranking supported by shared evidence.

How to read this board

当前覆盖金融分析、专业咨询与银行业务,尚不能代表所有文档、表格和演示文稿任务。 Prices do not affect ranking; missing scores are not treated as zero, and the index is not accuracy.

See the methodology →

About pricing

API prices come from vendor websites and are shown per million tokens. USD quotes are converted using the 2026-09-30 exchange rate. Cached price is the input price after a cache hit; cache writes, storage and subscription fees are separate.