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 2verificationforensic

TaxEval v2

Comprehensive benchmark for corporate and individual tax code interpretation and compliance reasoning.

Variable tasks

23 models evaluated

Updated 2026

View Source →Submit your score Methodology

80.4%

Top Score

Top model

Muse Spark 1.2

Model Rankings

financebenchmark.ai · TaxEval v2

75.7%

🥇

AnthropicClaude Opus 575.1%

🥈

AnthropicClaude Sonnet 575.6%

🥉

OpenAIGPT-5.6 Sol74.8%

4

DeepSeekDeepSeek V4 FlashOPEN70.7%

5

xAIGrok 4.671.1%

6

Moonshot AIKimi K3OPEN75.7%

7

AnthropicClaude Fable 576.9%

8

DeepSeekDeepSeek V4 Pro (0813)OPEN73.1%

9

GoogleGemini 3.5 Flash Lite72.6%

10

GoogleGemini 3.6 Flash74.9%

11

Zhipu AIGLM 5.2OPEN73.3%

12

OpenAIGPT-5.6 Luna76.2%

13

OpenAIGPT-5.6 Terra76.2%

14

xAIGrok 4.571.7%

15

Thinking MachinesInklingOPEN75.3%

16

Thinking MachinesInkling SmallOPEN75.5%

17

Ant GroupLing 3.0 FlashOPEN70.7%

18

MetaMuse Spark 1.179.7%

19

MetaMuse Spark 1.280.4%

20

NVIDIANemotron 3 UltraOPEN73.1%

21

AlibabaQwen 3.8 MaxOPEN75.5%

22

AnthropicClaude Fable 5.176.0%

23

Zhipu AIGLM 5.3 FlashOPEN75.6%

Full Results Table

#	Model	Overall	Source	Date
🥇	Muse Spark 1.2 Meta	80.4	VALS (2026)	2026-09
🥈	Muse Spark 1.1 Meta	79.7	VALS (2026)	2026-09
🥉	Claude Fable 5 Anthropic	76.9	VALS (2026)	2026-09
4	GPT-5.6 Luna OpenAI	76.2	VALS (2026)	2026-09
5	GPT-5.6 Terra OpenAI	76.2	VALS (2026)	2026-09
6	Claude Fable 5.1 Anthropic	76.0	VALS (2026)	2026-09
7	Kimi K3OPEN Moonshot AI	75.7	VALS (2026)	2026-09
8	Claude Sonnet 5 Anthropic	75.6	VALS (2026)	2026-09
9	GLM 5.3 FlashOPEN Zhipu AI	75.6	VALS (2026)	2026-09
10	Qwen 3.8 MaxOPEN Alibaba	75.5	VALS (2026)	2026-08
11	Inkling SmallOPEN Thinking Machines	75.5	VALS (2026)	2026-07
12	InklingOPEN Thinking Machines	75.3	VALS (2026)	2026-07
13	Claude Opus 5 Anthropic	75.1	VALS (2026)	2026-07
14	Gemini 3.6 Flash Google	74.9	VALS (2026)	2026-07
15	GPT-5.6 Sol OpenAI	74.8	VALS (2026)	2026-07
16	GLM 5.2OPEN Zhipu AI	73.3	VALS (2026)	2026-06
17	Nemotron 3 UltraOPEN NVIDIA	73.1	VALS (2026)	2026-06
18	DeepSeek V4 Pro (0813)OPEN DeepSeek	73.1	VALS (2026)	2026-08
19	Gemini 3.5 Flash Lite Google	72.6	VALS (2026)	2026-07
20	Grok 4.5 xAI	71.7	VALS (2026)	2026-07
21	Grok 4.6 xAI	71.1	VALS (2026)	2026-08
22	DeepSeek V4 FlashOPEN DeepSeek	70.7	VALS (2026)	2026-07
23	Ling 3.0 FlashOPEN Ant Group	70.7	VALS (2026)	2026-07

Contents.md

All evaluated models

Claude Opus 5

75.1%

Claude Sonnet 5

75.6%

GPT-5.6 Sol

74.8%

DeepSeek V4 Flash

70.7%

Grok 4.6

71.1%

Kimi K3

75.7%

Claude Fable 5

76.9%

DeepSeek V4 Pro (0813)

73.1%

Gemini 3.5 Flash Lite

72.6%

Gemini 3.6 Flash

74.9%

GLM 5.2

73.3%

GPT-5.6 Luna

76.2%

GPT-5.6 Terra

76.2%

Grok 4.5

71.7%

Inkling

75.3%

Inkling Small

75.5%

Ling 3.0 Flash

70.7%

Muse Spark 1.1

79.7%

Muse Spark 1.2

80.4%

Nemotron 3 Ultra

73.1%

Qwen 3.8 Max

75.5%

Claude Fable 5.1

76.0%

GLM 5.3 Flash

75.6%