Skip to content
PAY.NEWS LEADERBOARD

AI model leaderboard

Evaluation sources How ranks are computed

Financial analysis, legal advice and banking tasks — can the model finish professional work?

2 evaluations·2 operators·10/17 20:05 updated

Professional boardTOP 30

Ranked by the shared evidence of multiple public evaluations

Benchmark aggregation, not a payment-provider rating. Sponsorship, payment and affiliations must not affect results. Editorial standards

The top 30 models, sortable by column
Model
01gemini-4-argonGoogleEvidence-sensitive · 2 evaluationsOfficial —99.9
02claude-sonnet-5.5anthropicEvidence-sensitive · 2 evaluationsOfficial —99.7
03Claude Opus 5.5AnthropicEvidence-sensitive · 2 evaluationsOfficial $4 / $2099.6
04Claude Fable 5.1AnthropicEvidence-sensitive · 2 evaluationsOfficial $10 / $5099.5
05Gemini 3.7 FlashGoogleEvidence-sensitive · 2 evaluationsOfficial $0.75 / $3.7599.2
06Claude Opus 5AnthropicEvidence-sensitive · 2 evaluationsOfficial $5 / $2598.4
07Grok 4.6xAIEvidence-sensitive · 2 evaluationsOfficial $2 / $696.7
08GPT-6 AstraOpenAIEvidence-sensitive · 2 evaluationsOfficial $10 / $5095.2
09Gemini 3.8 FlashGoogleEvidence-sensitive · 2 evaluationsOfficial $0.75 / $3.7594.8
10Claude Fable 5AnthropicEvidence-sensitive · 2 evaluationsOfficial $10 / $5091.0
11Qwen3.8 MaxAlibabaEvidence-sensitive · 2 evaluationsOfficial $1.79 / $5.3886.1
12gpt-6.1-sol—Evidence-sensitive · 2 evaluationsOfficial —85.2
13GPT-5.6 TerraOpenAIEvidence-sensitive · 2 evaluationsOfficial $2 / $1283.8
14GLM-5.3Z.aiEvidence-sensitive · 2 evaluationsOfficial $1.4 / $4.481.5
15Grok 4.5xAIEvidence-sensitive · 2 evaluationsOfficial $2 / $675.5
16DeepSeek V4 Flash 0731DeepSeekEvidence-sensitive · 2 evaluationsOfficial $0.449 / $1.3574.4
17GPT-5.5OpenAIEvidence-sensitive · 2 evaluationsOfficial $5 / $3073.6
18Grok 4.7xAIEvidence-sensitive · 2 evaluationsOfficial $2 / $671.5
19Claude Sonnet 5AnthropicEvidence-sensitive · 2 evaluationsOfficial $2 / $1070.6
20MiMo V 2.6 ProXiaomiEvidence-sensitive · 2 evaluationsOfficial —69.8
21GPT-6 SolOpenAIEvidence-sensitive · 2 evaluationsOfficial $2 / $1063.8
22GLM-5.3 FlashZ.aiEvidence-sensitive · 2 evaluationsOfficial $0.12 / $0.41962.9
23GPT-5.6 SolOpenAIEvidence-sensitive · 2 evaluationsOfficial $4 / $2057.0
24Claude Opus 4.7AnthropicEvidence-sensitive · 2 evaluationsOfficial $5 / $2551.0
25Claude Opus 4.8AnthropicEvidence-sensitive · 2 evaluationsOfficial $5 / $2550.1
26Kimi K3Moonshot AIEvidence-sensitive · 2 evaluationsOfficial $2.99 / $14.9644.3
27Muse Spark 1.3MetaEvidence-sensitive · 2 evaluationsOfficial $1.25 / $4.2543.5
28Qwen3.8 27 BAlibabaEvidence-sensitive · 2 evaluationsOfficial $0.449 / $1.7938.1
29DeepSeek V4 Pro 0813DeepSeekEvidence-sensitive · 2 evaluationsOfficial $1.35 / $4.0436.5
30Gemini 3.6 FlashGoogleEvidence-sensitive · 2 evaluationsOfficial $0.75 / $3.7535.8

Each board shows at most 30 models

The consensus index is not an accuracy rate; ties keep the order the shared evidence establishes.

How to read this board

Coverage is currently financial analysis, professional advice and banking; it does not yet represent every document, spreadsheet and slide task.

See how it is computed →

About prices

API prices are shown in USD per million tokens by default. Vendor list prices and the DogRouter reference sit in separate columns; the latter is the relay price of a Dogpay sister service, carries a verification date and a link to its price page, is never shown as a discount, and does not affect the ranking. Cached price is the input rate on a cache hit; cache writes, storage and subscriptions are billed separately. CNY list prices are converted at the 2026-10-16 rate (欧洲央行).