Finance

🏆 Leaderboard

As of August 21, 2026, Muse Spark 1.2 is #1 for finance and data analysis at 60.6%. Ranked by FinanceAgent: financial analysis tasks, not a generic chat vibe. Best AI for finance and data analysis, ranked by FinanceAgent, GDPval, and OfficeQA. Compare investing and spreadsheet scores next to API price.

Updated August 21, 2026282 models33 providers


Muse Spark 1.2 Meta · Proprietary	60.6%	80.4%	70.9%	—	—	—	$5.50
Gemini 3.7 Flash Google · Proprietary	59.0%	74.7%	—	—	34%	—	$4.50
Claude Opus 5 Anthropic · Proprietary	58.6%	75.1%	73.2%	—	24%	—	$30.00
Gemini 3.5 Flash Google · Proprietary	57.9%	74.4%	64.7%	57.9%	14%	—	$10.50
Muse Spark 1.1 Meta · Proprietary	57.2%	79.7%	71.3%	—	15%	—	$5.50
Claude Fable 5 Anthropic · Proprietary	56.3%	76.9%	71.8%	—	29.8%	—	$60.00
Gemini 3.6 Flash Google · Proprietary	56.3%	74.9%	63.3%	—	14%	—	$4.50
GPT-5.6 Luna OpenAI · Proprietary	55.0%	76.2%	64.2%	—	22.7%	—	$1.40
Kimi K3OSS Moonshot AI · Open Source	54.4%	75.7%	71.6%	—	19%	—	$18.00
Claude Opus 4.8 Anthropic · Proprietary	53.9%	75.6%	66.7%	53.9%	23%	—	$30.00
Claude Sonnet 5 Anthropic · Proprietary	53.9%	75.6%	67.0%	—	81.6%	—	$12.00
GPT-5.6 Sol OpenAI · Proprietary	53.8%	74.8%	64.4%	—	30.7%	—	$35.00
Grok 4.6 xAI · Proprietary	53.7%	71.1%	66.2%	—	—	—	$8.00
GPT-5.6 Terra OpenAI · Proprietary	52.4%	76.2%	65.3%	—	24.7%	—	$14.00
GPT-5.5 OpenAI · Proprietary	51.8%	75.0%	68.4%	60%	25%	84.9%	$35.00
Claude Opus 4.7 Anthropic · Proprietary	51.5%	75.3%	66.1%	64.4%	21%	—	$30.00
Claude Sonnet 4.6 Anthropic · Proprietary	51.0%	77.1%	65.3%	63.3%	18%	—	$18.00
Qwen3.8 MaxOSS Qwen · Open Source	50.6%	75.5%	65.8%	—	—	—	$8.00
DeepSeek-V4-Pro-0813OSS DeepSeek · Open Source	50.4%	73.1%	65.4%	60.4%	—	—	$5.28
GLM-5.2OSS Z AI · Open Source	49.7%	73.3%	66.1%	—	—	—	$5.80
DeepSeek-V4-Flash-0731OSS DeepSeek · Open Source	49.5%	70.7%	61.9%	—	—	—	$1.76
Qwen3.7 Max Qwen · Proprietary	48.4%	75.3%	63.7%	—	—	—	$5.00
Grok 4.5 xAI · Proprietary	48.4%	71.7%	67.4%	—	14%	—	$8.00
MiniMax M3OSS MiniMax · Open Source	48.3%	72.7%	68.1%	—	—	—	$1.50
Gemini 3.5 Flash-Lite Google · Proprietary	47.4%	72.6%	60.7%	—	10%	—	$2.80
GPT-5.4 mini OpenAI · Proprietary	45.4%	71.2%	60.9%	53.4%	—	—	$5.25
Kimi K2.6OSS Moonshot AI · Open Source	44.9%	74.7%	66.7%	57.1%	12%	—	$4.93
GLM-5.1OSS Z AI · Open Source	44.8%	71.2%	64.5%	57.7%	—	—	$5.80
Gemini 3.1 Pro Google · Proprietary	43.0%	72.9%	64.5%	59.7%	17%	—	$17.50
Gemini 3 Flash Google · Proprietary	42.5%	73.9%	66.4%	47.6%	10%	—	$3.50
MiMo-V2.5-ProOSS Xiaomi · Open Source	41.5%	73.8%	61.4%	—	—	—	$1.30
Inkling-SmallOSS Thinking Machines · Open Source · via Thinking Machines Lab	41.3%	75.5%	69.6%	—	—	—	$1.50
Qwen3.6 Plus Qwen · Proprietary	40.9%	74.7%	61.9%	54.6%	—	—	$3.50
Qwen3.7-Plus Qwen · Proprietary	38.2%	—	—	—	—	—	$1.60
GPT-5.4 nano OpenAI · Proprietary	38.2%	67.4%	61.2%	47.8%	—	—	$1.45
Grok 4.3 xAI · Proprietary	37.7%	70.8%	68.5%	53.8%	8%	—	$3.75
Nemotron 3 Ultra (550B A55B)OSS NVIDIA · Open Source · via OpenRouter	37.5%	73.1%	65.5%	53.7%	—	46.7%	$2.70
MiMo-V2.5OSS Xiaomi · Open Source	36.7%	71.8%	59.9%	—	—	—	$0.50
Mistral Medium 3.5OSS Mistral · Open Source · via Mistral AI	32.1%	68.0%	58.8%	46.1%	—	—	$9.00
Claude Haiku 4.5 Anthropic · Proprietary	31.0%	—	60.3%	—	—	—	$6.00
Gemini 3.1 Flash-Lite Google · Proprietary	30.0%	71.8%	59.4%	46.1%	—	—	$1.75
MiniMax M2.7OSS MiniMax · Open Source	27.9%	66.6%	61.2%	48.4%	—	—	$1.50
ChatGPT-4o Latest OpenAI · Proprietary	—	—	—	—	—	—	$12.50
Claude 3 Haiku Anthropic · Proprietary	—	—	—	—	—	—	$1.50
Claude 3 Opus Anthropic · Proprietary	—	—	—	—	—	—	$90.00
Claude 3 Sonnet Anthropic · Proprietary	—	—	—	—	—	—	$18.00
Claude 3.5 Haiku Anthropic · Proprietary	—	57.4%	50.8%	—	—	—	$4.80
Claude 3.5 Sonnet Anthropic · Proprietary	—	70.2%	53.6%	—	—	—	$18.00
Claude 3.5 Sonnet Anthropic · Proprietary	—	—	—	—	—	—	$18.00
Claude 3.7 Sonnet Anthropic · Proprietary	—	72.4%	—	—	—	—	$18.00

Showing 1–50 of 282 models

Next step

You found the model. Now ship the product.

Auth, billing, and the API layer are already decided. Fork 8 finished AI apps, or have us build the first version with you.

Build with the APIs Have us build it with you

The index

All Large Language Models

282 models across 33 providers. Search or jump to a lab — every model page stays linked here.

Cursor

2 models

Composer 2 Composer 2 Fast

xAI

15 models

Grok 4.6 Grok 4.5 Grok 4.3 Grok-4.1 Grok-4.1 Fast Non-Reasoning Grok-4.1 Fast Reasoning Grok-4.1 Thinking Grok 4 Fast Grok Code Fast 1 Grok-4 Fast Non-Reasoning Grok-4 Fast Reasoning Grok-4 Grok-3 Grok-3 Mini Grok-2

DeepSeek

16 models

DeepSeek-V4-Pro-0813 DeepSeek-V4-Flash-0731 DeepSeek-V4-Flash-0423 DeepSeek-V4-Flash-Max DeepSeek-V4-Pro-Max DeepSeek-V3.2 DeepSeek-V3.2 (Non-thinking)DeepSeek-V3.2-Exp DeepSeek-R1-0528 DeepSeek-V3 0324 DeepSeek R1 Distill Llama 70B DeepSeek R1 Distill Qwen 32B DeepSeek-R1 DeepSeek-V3.1 DeepSeek-V3 DeepSeek-V2.5

MiniMax

6 models

MiniMax M3 MiniMax M2.7 MiniMax M2.5 MiniMax M2.1 MiniMax M2 MiniMax M1 80K

AI21 Labs

2 models

Jamba 1.5 Large Jamba 1.5 Mini

Amazon

5 models

Nova 2 Lite Nova 2 Sonic Nova Lite Nova Micro Nova Pro

Baidu

1 models

ERNIE 4.5

ByteDance

2 models

Seed 2.1 Turbo Seed 2.0 Pro

Cohere

3 models

North Mini Code 1.0 Command A+Command R+

IBM

1 models

Granite 3.3 8B Instruct

Inception

1 models

Mercury 2

inclusionAI

1 models

Ling-3.0-flash

LG AI Research

1 models

K-EXAONE-236B-A23B

Meituan

4 models

LongCat-Flash-Lite LongCat-Flash-Thinking-2601 LongCat-Flash-Thinking LongCat-Flash-Chat

Microsoft

5 models

MAI-Code-1.1-Flash Phi 4 Mini Phi-4-multimodal-instruct Phi 4 Phi-3.5-mini-instruct

Moonshot AI

9 models

Kimi K3 Kimi K2.7 Code Kimi K2.7 Code HighSpeed Kimi K2.6 Kimi K2.5 Kimi K2 0905 Kimi K2-Instruct-0905 Kimi K2-Thinking-0905 Kimi K2 Instruct

Nous Research

1 models

Hermes 3 70B

NVIDIA

5 models

Nemotron 3.5 Lightning (30B A3B)Nemotron 3 Ultra (550B A55B)Nemotron 3 Super (120B A12B)Nemotron 3 Nano (30B A3B)Nemotron Nano 9B v2

Poolside

2 models

Laguna S 2.1 Laguna XS 2.1

Sakana AI

1 models

Sakana Namazu

StepFun

1 models

Step-3.5-Flash

Tencent

1 models

Hy3

Thinking Machines

1 models

Inkling-Small

Unisound

1 models

Upstage

1 models

Solar Pro 4

Xiaomi

3 models

MiMo-V2.5-Pro MiMo-V2.5 MiMo-V2-Flash

What is the best AI for finance?

As of August 21, 2026, Muse Spark 1.2 by Meta is #1 for finance and data analysis at 60.6%. Ranked by FinanceAgent: financial analysis tasks, not a generic chat vibe. This board also tracks FinanceAgent v2, Tax Eval v2, CorpFin v2, FinanceAgent v1.1. Next on the same board: Gemini 3.7 Flash and Claude Opus 5. Related leaders: Claude Opus 5 on CorpFin v2 at 73.2%; GPT-5.4 on FinanceAgent v1.1 at 79.6%. This finance leaderboard ranks models by FinanceAgent v2. Scores come from public evals. Prices are the live API rates in the table above.

Sources: OpenAI API pricing (https://developers.openai.com/api/docs/pricing); Anthropic Claude API pricing (https://platform.claude.com/docs/en/about-claude/pricing); Gemini API pricing (https://ai.google.dev/gemini-api/docs/pricing)

Top 8 for finance. Ranked by FinanceAgent: financial analysis tasks, not a generic chat vibe. Input and output are dollars per million tokens.
Rank	Model	FinanceAgent v2	Input /M	Output /M
1	Muse Spark 1.2	60.6%	$1.25	$4.25
2	Gemini 3.7 Flash	59.0%	$0.75	$3.75
3	Claude Opus 5	58.6%	$5.00	$25.00
4	Gemini 3.5 Flash	57.9%	$1.50	$9.00
5	Muse Spark 1.1	57.2%	$1.25	$4.25
6	Claude Fable 5	56.3%	$10.00	$50.00
7	Gemini 3.6 Flash	56.3%	$0.75	$3.75
8	GPT-5.6 Luna	55.0%	$0.20	$1.20

What is the best AI for data analysis?

Data analysis searches often mean ChatGPT's file/analysis mode. That is still a model plus tools. This board ranks finance and knowledge-work evals (FinanceAgent, GDPval, OfficeQA) next to API price. For long PDFs, also open the long-context board.

What is GDPval?

GDPval is a knowledge-work eval tied to economic tasks. Use it when you care about office-grade output, not AIME. FinanceAgent is the more finance-specific public number.

Related LLM leaderboards

LLM Leaderboard Coding Math Agentic Reasoning Writing Science Long Context Vision Open Source

Individual benchmark pages

Rank one eval at a time. All LLM benchmarks.

HLE SWE Bench Humanity's Last Exam (No Tools)Humanity's Last Exam (With Tools)Terminal-Bench 2.0 Terminal-Bench Terminal-Bench 2.1 Terminal-Bench 2 Terminal-Bench 3.0 ARC-AGI-1 Verified

Finance FAQ

Who ranks #1 on the Finance leaderboard?

As of August 21, 2026, Muse Spark 1.2 by Meta ranks #1 on FinanceAgent v2 at 60.6%. API pricing is $1.25/M input and $4.25/M output.

What is the best AI for finance?

What are the top models on FinanceAgent v2?

The current FinanceAgent v2 ranking as of August 21, 2026 is 1. Muse Spark 1.2 at 60.6%; 2. Gemini 3.7 Flash at 59.0%; 3. Claude Opus 5 at 58.6%.

Which finance model is the cheapest?

MiMo-V2.5 is the cheapest scored model on this finance leaderboard at $0.17/M input and $0.34/M output ($0.50 blended). Muse Spark 1.2 still leads FinanceAgent v2 at 60.6%.

Should I always pick the #1 FinanceAgent v2 model?

Not automatically. Muse Spark 1.2 leads FinanceAgent v2, but a cheaper scored model can be the better production choice if the quality gap is small. Use the table to weigh FinanceAgent v2 against input/output price, context window, and related evals.

How often is the Finance leaderboard updated?

Scores and API prices on this page are refreshed from published evals and provider rates. The snapshot is labeled August 21, 2026. Treat it as a current index, not a one-off blog post.

What is the best LLM for finance?

GDPval and FinanceAgent score professional knowledge-work and financial analysis. Big Finance Bench is a newer public finance eval.

What is GDPval?

GDPval measures models on tasks tied to real economic work, not trivia. It is closer to knowledge-work quality than to a math contest.

Are finance evals as dense as coding evals?

No. Fewer labs publish finance scores, so this ranking is thinner than SWE-bench. We still show every public score we have.

What is the best AI for data analysis?

Best AI for data analysis is the query next to finance. GDPval, FinanceAgent, and OfficeQA score knowledge-work and spreadsheets more than contest math. ChatGPT data analysis is a product mode. This page ranks the models behind those modes.

What is the best AI for investing?

Public finance evals are thinner than SWE-bench. FinanceAgent and Big Finance Bench are the usual scores. This is not investment advice. A high GDPval score means knowledge-work quality, not alpha.

Claude vs ChatGPT for finance?

Rank FinanceAgent and GDPval, then compare token price. Spreadsheet and PDF workflows often care more about tool use and long context than about a chat vibe.

You found the model. Now ship the product.

All Large Language Models

OpenAI

Anthropic

Google

Cursor

xAI

DeepSeek

MiniMax

Qwen

AI21 Labs

Amazon

Baidu

ByteDance

Cohere

IBM

Inception

inclusionAI

LG AI Research

Meituan

Meta

Microsoft

Mistral

Moonshot AI

Nous Research

NVIDIA

Poolside

Sakana AI

StepFun

Tencent

Thinking Machines

Unisound

Upstage

Xiaomi

Z AI

What is the best AI for finance?

What is the best AI for data analysis?

What is GDPval?

Related LLM leaderboards

Individual benchmark pages

Finance FAQ

Who ranks #1 on the Finance leaderboard?

What is the best AI for finance?

What are the top models on FinanceAgent v2?

Which finance model is the cheapest?

Should I always pick the #1 FinanceAgent v2 model?

How often is the Finance leaderboard updated?

What is the best LLM for finance?

What is GDPval?

Are finance evals as dense as coding evals?

What is the best AI for data analysis?

What is the best AI for investing?

Claude vs ChatGPT for finance?