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 3agentTasks

SkillsBench

Measures procedural tool orchestration and software skill invocation.

Variable tasks

17 models evaluated

Updated 2026

View Source →Submit your score Methodology

66.0%

Top Score

Top model

Grok 4.5

Model Rankings

financebenchmark.ai · SkillsBench

45.1%

🥇

AnthropicClaude Opus 560.4%

🥈

AnthropicClaude Sonnet 546.5%

🥉

OpenAIGPT-5.6 Sol54.1%

4

DeepSeekDeepSeek V4 FlashOPEN50.7%

5

xAIGrok 4.655.8%

6

Zhipu AIGLM 5.2OPEN45.1%

7

OpenAIGPT-5.6 Luna60.5%

8

OpenAIGPT-5.6 Terra60.6%

9

xAIGrok 4.566.0%

10

Thinking MachinesInklingOPEN26.1%

11

Thinking MachinesInkling SmallOPEN33.6%

12

Moonshot AIKimi K2.7 CodeOPEN50.0%

13

Ant GroupLing 3.0 FlashOPEN27.9%

14

MetaMuse Spark 1.159.2%

15

MetaMuse Spark 1.253.0%

16

AlibabaQwen 3.7 Plus54.3%

17

AlibabaQwen 3.8 MaxOPEN42.0%

Full Results Table

#	Model	Overall	Source	Date
🥇	Grok 4.5 xAI	66.0	VALS (2026)	2026-07
🥈	GPT-5.6 Terra OpenAI	60.6	VALS (2026)	2026-07
🥉	GPT-5.6 Luna OpenAI	60.5	VALS (2026)	2026-07
4	Claude Opus 5 Anthropic	60.4	VALS (2026)	2026-07
5	Muse Spark 1.1 Meta	59.2	VALS (2026)	2026-07
6	Grok 4.6 xAI	55.8	VALS (2026)	2026-08
7	Qwen 3.7 Plus Alibaba	54.3	VALS (2026)	2026-06
8	GPT-5.6 Sol OpenAI	54.1	VALS (2026)	2026-07
9	Muse Spark 1.2 Meta	53.0	VALS (2026)	2026-08
10	DeepSeek V4 FlashOPEN DeepSeek	50.7	VALS (2026)	2026-07
11	Kimi K2.7 CodeOPEN Moonshot AI	50.0	VALS (2026)	2026-06
12	Claude Sonnet 5 Anthropic	46.5	VALS (2026)	2026-06
13	GLM 5.2OPEN Zhipu AI	45.1	VALS (2026)	2026-06
14	Qwen 3.8 MaxOPEN Alibaba	42.0	VALS (2026)	2026-08
15	Inkling SmallOPEN Thinking Machines	33.6	VALS (2026)	2026-07
16	Ling 3.0 FlashOPEN Ant Group	27.9	VALS (2026)	2026-07
17	InklingOPEN Thinking Machines	26.1	VALS (2026)	2026-07