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 3verificationforensic

Public Benefits Bench

Evaluates civic policy compliance, public benefits eligibility, and regulatory adjudication.

Variable tasks

16 models evaluated

Updated 2026

View Source →Submit your score Methodology

76.9%

Top Score

Top model

Claude Opus 5

Model Rankings

financebenchmark.ai · Public Benefits

70.4%

🥇

AnthropicClaude Opus 576.9%

🥈

AnthropicClaude Sonnet 566.0%

🥉

OpenAIGPT-5.6 Sol66.5%

4

xAIGrok 4.666.8%

5

Moonshot AIKimi K3OPEN68.3%

6

AnthropicClaude Fable 570.4%

7

GoogleGemini 3.5 Flash Lite51.8%

8

GoogleGemini 3.6 Flash56.6%

9

OpenAIGPT-5.6 Luna61.2%

10

OpenAIGPT-5.6 Terra62.4%

11

Thinking MachinesInklingOPEN58.5%

12

Thinking MachinesInkling SmallOPEN59.4%

13

Ant GroupLing 3.0 FlashOPEN50.7%

14

MetaMuse Spark 1.161.3%

15

MetaMuse Spark 1.268.5%

16

AlibabaQwen 3.8 MaxOPEN67.1%

Full Results Table

#	Model	Overall	Source	Date
🥇	Claude Opus 5 Anthropic	76.9	VALS (2026)	2026-07
🥈	Claude Fable 5 Anthropic	70.4	VALS (2026)	2026-06
🥉	Muse Spark 1.2 Meta	68.5	VALS (2026)	2026-08
4	Kimi K3OPEN Moonshot AI	68.3	VALS (2026)	2026-07
5	Qwen 3.8 MaxOPEN Alibaba	67.1	VALS (2026)	2026-08
6	Grok 4.6 xAI	66.8	VALS (2026)	2026-08
7	GPT-5.6 Sol OpenAI	66.5	VALS (2026)	2026-07
8	Claude Sonnet 5 Anthropic	66.0	VALS (2026)	2026-06
9	GPT-5.6 Terra OpenAI	62.4	VALS (2026)	2026-07
10	Muse Spark 1.1 Meta	61.3	VALS (2026)	2026-07
11	GPT-5.6 Luna OpenAI	61.2	VALS (2026)	2026-07
12	Inkling SmallOPEN Thinking Machines	59.4	VALS (2026)	2026-07
13	InklingOPEN Thinking Machines	58.5	VALS (2026)	2026-07
14	Gemini 3.6 Flash Google	56.6	VALS (2026)	2026-07
15	Gemini 3.5 Flash Lite Google	51.8	VALS (2026)	2026-07
16	Ling 3.0 FlashOPEN Ant Group	50.7	VALS (2026)	2026-07