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.

2026-09-10MODELDeepSeek-V4.1-Flash released with extreme agent memory efficiency and evaluated across VALS • 2026-09-03MODELGPT-6 Astra released by OpenAI - 71.7% on EMB, 63.3% on Tax Agent Bench • 2026-09-02MODELGoogle Gemini 3.8 Flash takes #1 rank on Finance Agent (v2) with 61.4% and 72.2% on EMB • 2026-09-02MODELMeta releases Muse Spark 1.3 & 1.3 Max - 59.0%-60.0% on Finance Agent (v2) • 2026-09-01MODELClaude Fable 5.1 leads Tax Agent Bench (77.6%) and EMB (76.7%) with 75% cheaper cache reads • 2026-09-11BENCHTax Agent Bench and FAB v2 benchmarks updated with latest frontier model rankings • 2026-09-15UPDATEPlatform updated: 43 models tracked across 41 independent benchmarks • 2026-09-10MODELDeepSeek-V4.1-Flash released with extreme agent memory efficiency and evaluated across VALS • 2026-09-03MODELGPT-6 Astra released by OpenAI - 71.7% on EMB, 63.3% on Tax Agent Bench • 2026-09-02MODELGoogle Gemini 3.8 Flash takes #1 rank on Finance Agent (v2) with 61.4% and 72.2% on EMB • 2026-09-02MODELMeta releases Muse Spark 1.3 & 1.3 Max - 59.0%-60.0% on Finance Agent (v2) • 2026-09-01MODELClaude Fable 5.1 leads Tax Agent Bench (77.6%) and EMB (76.7%) with 75% cheaper cache reads • 2026-09-11BENCHTax Agent Bench and FAB v2 benchmarks updated with latest frontier model rankings • 2026-09-15UPDATEPlatform updated: 43 models tracked across 41 independent benchmarks •

Tier 1verificationnumericalagentTasks

VALS Index

Holistic evaluation index measuring agent accuracy, reasoning, coding, and specialized domain proficiency.

Variable tasks

22 models evaluated

Updated 2026

View Source →Submit your score Methodology

67.2%

Top Score

Top model

Claude Opus 5

Model Rankings

financebenchmark.ai · VALS Index

57.8%

🥇

AnthropicClaude Opus 567.2%

🥈

AnthropicClaude Sonnet 559.6%

🥉

OpenAIGPT-5.6 Sol63.7%

4

DeepSeekDeepSeek V4 FlashOPEN53.6%

5

xAIGrok 4.659.2%

6

Moonshot AIKimi K3OPEN57.8%

7

AnthropicClaude Fable 566.0%

8

DeepSeekDeepSeek V4 Pro (0813)OPEN52.4%

9

GoogleGemini 3.5 Flash Lite36.7%

10

GoogleGemini 3.6 Flash55.4%

11

Zhipu AIGLM 5.2OPEN53.1%

12

OpenAIGPT-5.6 Luna59.9%

13

OpenAIGPT-5.6 Terra56.5%

14

xAIGrok 4.551.5%

15

Thinking MachinesInklingOPEN34.1%

16

Thinking MachinesInkling SmallOPEN31.9%

17

Ant GroupLing 3.0 FlashOPEN21.7%

18

MetaMuse Spark 1.154.8%

19

MetaMuse Spark 1.257.0%

20

NVIDIANemotron 3 UltraOPEN27.4%

21

AlibabaQwen 3.7 Plus38.6%

22

AlibabaQwen 3.8 MaxOPEN51.8%

Full Results Table

#	Model	Overall	Source	Date
🥇	Claude Opus 5 Anthropic	67.2	VALS (2026)	2026-07
🥈	Claude Fable 5 Anthropic	66.0	VALS (2026)	2026-06
🥉	GPT-5.6 Sol OpenAI	63.7	VALS (2026)	2026-07
4	GPT-5.6 Luna OpenAI	59.9	VALS (2026)	2026-07
5	Claude Sonnet 5 Anthropic	59.6	VALS (2026)	2026-06
6	Grok 4.6 xAI	59.2	VALS (2026)	2026-08
7	Kimi K3OPEN Moonshot AI	57.8	VALS (2026)	2026-07
8	Muse Spark 1.2 Meta	57.0	VALS (2026)	2026-08
9	GPT-5.6 Terra OpenAI	56.5	VALS (2026)	2026-07
10	Gemini 3.6 Flash Google	55.4	VALS (2026)	2026-07
11	Muse Spark 1.1 Meta	54.8	VALS (2026)	2026-07
12	DeepSeek V4 FlashOPEN DeepSeek	53.6	VALS (2026)	2026-07
13	GLM 5.2OPEN Zhipu AI	53.1	VALS (2026)	2026-06
14	DeepSeek V4 Pro (0813)OPEN DeepSeek	52.4	VALS (2026)	2026-08
15	Qwen 3.8 MaxOPEN Alibaba	51.8	VALS (2026)	2026-08
16	Grok 4.5 xAI	51.5	VALS (2026)	2026-07
17	Qwen 3.7 Plus Alibaba	38.6	VALS (2026)	2026-06
18	Gemini 3.5 Flash Lite Google	36.7	VALS (2026)	2026-07
19	InklingOPEN Thinking Machines	34.1	VALS (2026)	2026-07
20	Inkling SmallOPEN Thinking Machines	31.9	VALS (2026)	2026-07
21	Nemotron 3 UltraOPEN NVIDIA	27.4	VALS (2026)	2026-06
22	Ling 3.0 FlashOPEN Ant Group	21.7	VALS (2026)	2026-07