Skip to content

AI model leaderboard

Financial analysis, legal advice and banking, to see whether professional tasks can be completed.

2 evaluations · 2 organisations · updated 11/13 14:05

Professional worktop 30

Ranked on the evidence several public evaluations share
The top 30 models, sortable by column
Model
01gemini-4-argonGoogleReleased 2026-09-30 · Evidence-sensitiveCached input —Input — · Output —99.9
02claude-sonnet-5.5anthropicReleased — · Evidence-sensitiveCached input —Input — · Output —99.7
03Claude Opus 5.5AnthropicReleased 2026-09-17 · Evidence-sensitiveCached input ¥1.33Input ¥26.67 · Output ¥133.3799.6
04Claude Fable 5.1AnthropicReleased 2026-09-01 · Evidence-sensitiveCached input ¥1.67Input ¥66.68 · Output ¥333.4299.5
05Gemini 3.7 FlashGoogleReleased 2026-08-13 · Evidence-sensitiveCached input ¥0.5Input ¥5 · Output ¥25.0199.2
06Claude Opus 5AnthropicReleased 2026-07-24 · Evidence-sensitiveCached input ¥3.33Input ¥33.34 · Output ¥166.7198.4
07Grok 4.6xAIReleased 2026-08-12 · Evidence-sensitiveCached input ¥3.33Input ¥13.34 · Output ¥40.0196.7
08GPT-6 AstraOpenAIReleased 2026-09-03 · Evidence-sensitiveCached input ¥6.67Input ¥66.68 · Output ¥333.4295.2
09Gemini 3.8 FlashGoogleReleased 2026-09-02 · Evidence-sensitiveCached input ¥0.5Input ¥5 · Output ¥25.0194.8
10Claude Fable 5AnthropicReleased 2026-06-09 · Evidence-sensitiveCached input ¥6.67Input ¥66.68 · Output ¥333.4291.0
11Qwen3.8 MaxAlibabaReleased 2026-07-19 · Evidence-sensitiveCached input —Input ¥12 · Output ¥3686.1
12gpt-6.1-sol—Released — · Evidence-sensitiveCached input —Input — · Output —85.2
13GPT-5.6 TerraOpenAIReleased 2026-07-09 · Evidence-sensitiveCached input ¥1.33Input ¥13.34 · Output ¥80.0283.8
14GLM-5.3Z.aiReleased 2026-08-18 · Evidence-sensitiveCached input ¥1.73Input ¥9.34 · Output ¥29.3481.5
15Grok 4.5xAIReleased 2026-07-08 · Evidence-sensitiveCached input ¥2Input ¥13.34 · Output ¥40.0175.5
16DeepSeek V4 Flash 0731DeepSeekReleased 2026-07-31 · Evidence-sensitiveCached input ¥0.1Input ¥3 · Output ¥974.4
17GPT-5.5OpenAIReleased 2026-04-23 · Evidence-sensitiveCached input ¥3.33Input ¥33.34 · Output ¥200.0573.6
18Grok 4.7xAIReleased 2026-09-21 · Evidence-sensitiveCached input ¥3.33Input ¥13.34 · Output ¥40.0171.5
19Claude Sonnet 5AnthropicReleased 2026-06-30 · Evidence-sensitiveCached input ¥1.33Input ¥13.34 · Output ¥66.6870.6
20MiMo V 2.6 ProXiaomiReleased 2026-09-21 · Evidence-sensitiveCached input —Input — · Output —69.8
21GPT-6 SolOpenAIReleased 2026-09-22 · Evidence-sensitiveCached input ¥1.33Input ¥13.34 · Output ¥66.6863.8
22GLM-5.3 FlashZ.aiReleased 2026-08-26 · Evidence-sensitiveCached input ¥0.23Input ¥0.8 · Output ¥2.862.9
23GPT-5.6 SolOpenAIReleased 2026-07-09 · Evidence-sensitiveCached input ¥2.67Input ¥26.67 · Output ¥133.3757.0
24Claude Opus 4.7AnthropicReleased 2026-04-16 · Evidence-sensitiveCached input ¥3.33Input ¥33.34 · Output ¥166.7151.0
25Claude Opus 4.8AnthropicReleased 2026-05-28 · Evidence-sensitiveCached input ¥3.33Input ¥33.34 · Output ¥166.7150.1
26Kimi K3Moonshot AIReleased 2026-07-16 · Evidence-sensitiveCached input ¥2Input ¥20 · Output ¥10044.3
27Muse Spark 1.3MetaReleased 2026-09-02 · Evidence-sensitiveCached input —Input ¥8.34 · Output ¥28.3443.5
28Qwen3.8 27 BAlibabaReleased 2026-08-14 · Evidence-sensitiveCached input ¥0.6Input ¥3 · Output ¥1238.1
29DeepSeek V4 Pro 0813DeepSeekReleased 2026-08-13 · Evidence-sensitiveCached input ¥0.3Input ¥9 · Output ¥2736.5
30Gemini 3.6 FlashGoogleReleased 2026-07-21 · Evidence-sensitiveCached input ¥0.5Input ¥5 · Output ¥25.0135.8

Each board shows at most 30 models

The consensus index is not an accuracy rate; tied scores keep the order the shared evidence decides.

How to read this board

It currently covers financial analysis, professional consulting and banking, and cannot yet represent all document, spreadsheet and presentation tasks. Prices play no part in the ranking, a missing evaluation does not count as zero, and the index is not an accuracy rate.

How it is calculated

About prices

API prices come from the providers' own sites, per million tokens. Dollar prices are converted to CNY at the rate of 2026-11-12. The cached price is the input price on a cache hit; cache writes, storage and subscriptions are extra.