FinanceBenchmark: Financial AI Leaderboard 2026

FinanceBenchmark provides independent rankings and a composite score for leading Artificial Intelligence models, including Anthropic Claude, OpenAI GPT, and Google Gemini, on complex financial reasoning and forensic accounting tasks. Enable JavaScript to view the interactive, continuously updated leaderboard.

2026-10-20UPDATEPlatform updated: 52 models tracked across 42 independent benchmarks including CorpFin • 2026-10-20BENCHCorpFin added to benchmark suite — long credit agreement comprehension evaluations live • 2026-10-19MODELClaude Sonnet 5.5 and Opus 5.5 achieve 75.9% and 75.8% on Excel Modeling Benchmark v1.1 • 2026-10-19MODELTax Agent Bench updated: Claude Fable 5.1 (49.2%) and Gemini 4 Argon (44.6%) lead corporate tax research • 2026-10-18MODELGemini 4 Argon claims #1 rank on Finance Agent (v2) with 65.4% • 2026-10-13MODELGoogle launches Gemini 4 Argon with 1M-token output limit and native multimodal reasoning • 2026-10-06MODELAnthropic completes Claude 5.5 generation with Claude Haiku 5.5, Opus 5.5, and Sonnet 5.5 • 2026-10-20UPDATEPlatform updated: 52 models tracked across 42 independent benchmarks including CorpFin • 2026-10-20BENCHCorpFin added to benchmark suite — long credit agreement comprehension evaluations live • 2026-10-19MODELClaude Sonnet 5.5 and Opus 5.5 achieve 75.9% and 75.8% on Excel Modeling Benchmark v1.1 • 2026-10-19MODELTax Agent Bench updated: Claude Fable 5.1 (49.2%) and Gemini 4 Argon (44.6%) lead corporate tax research • 2026-10-18MODELGemini 4 Argon claims #1 rank on Finance Agent (v2) with 65.4% • 2026-10-13MODELGoogle launches Gemini 4 Argon with 1M-token output limit and native multimodal reasoning • 2026-10-06MODELAnthropic completes Claude 5.5 generation with Claude Haiku 5.5, Opus 5.5, and Sonnet 5.5 •

Tier 3documentQAnumerical

MMMU

Massive Multi-discipline Multimodal Understanding and Reasoning benchmark for expert AGI.

11,500 tasks

14 models evaluated

Updated 2026

arXiv:2311.16502

View Source →Submit your score Methodology

89.9%

Top Score

Top model

Claude Opus 5

Model Rankings

financebenchmark.ai · MMMU

83.6%

🥇

AnthropicClaude Opus 589.9%

🥈

AnthropicClaude Sonnet 583.0%

🥉

OpenAIGPT-5.6 Sol88.8%

4

Moonshot AIKimi K3OPEN88.2%

5

AnthropicClaude Fable 589.3%

6

GoogleGemini 3.5 Flash Lite83.6%

7

GoogleGemini 3.6 Flash86.7%

8

OpenAIGPT-5.6 Luna85.0%

9

OpenAIGPT-5.6 Terra86.5%

10

xAIGrok 4.561.8%

11

Thinking MachinesInklingOPEN78.5%

12

MetaMuse Spark 1.186.6%

13

MetaMuse Spark 1.286.1%

14

AlibabaQwen 3.8 MaxOPEN88.0%

Full Results Table

#	Model	Overall	Source	Date
🥇	Claude Opus 5 Anthropic	89.9	arXiv:2311.16502	2026-07
🥈	Claude Fable 5 Anthropic	89.3	arXiv:2311.16502	2026-06
🥉	GPT-5.6 Sol OpenAI	88.8	arXiv:2311.16502	2026-07
4	Kimi K3OPEN Moonshot AI	88.2	arXiv:2311.16502	2026-07
5	Qwen 3.8 MaxOPEN Alibaba	88.0	arXiv:2311.16502	2026-08
6	Gemini 3.6 Flash Google	86.7	arXiv:2311.16502	2026-07
7	Muse Spark 1.1 Meta	86.6	arXiv:2311.16502	2026-07
8	GPT-5.6 Terra OpenAI	86.5	arXiv:2311.16502	2026-07
9	Muse Spark 1.2 Meta	86.1	arXiv:2311.16502	2026-08
10	GPT-5.6 Luna OpenAI	85.0	arXiv:2311.16502	2026-07
11	Gemini 3.5 Flash Lite Google	83.6	arXiv:2311.16502	2026-07
12	Claude Sonnet 5 Anthropic	83.0	arXiv:2311.16502	2026-06
13	InklingOPEN Thinking Machines	78.5	arXiv:2311.16502	2026-07
14	Grok 4.5 xAI	61.8	arXiv:2311.16502	2026-07