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 3agentTasks

SAGE

Structured Agent Goal Execution across multi-modal tools and interactive environments.

Variable tasks

17 models evaluated

Updated 2026

View Source →Submit your score Methodology

54.3%

Top Score

Top model

Kimi K3

Model Rankings

financebenchmark.ai · SAGE

51.9%

🥇

AnthropicClaude Opus 549.4%

🥈

AnthropicClaude Sonnet 548.9%

🥉

OpenAIGPT-5.6 Sol52.6%

4

xAIGrok 4.628.9%

5

Moonshot AIKimi K3OPEN54.3%

6

AnthropicClaude Fable 551.9%

7

GoogleGemini 3.5 Flash Lite47.3%

8

GoogleGemini 3.6 Flash48.7%

9

OpenAIGPT-5.6 Luna44.2%

10

OpenAIGPT-5.6 Terra47.0%

11

xAIGrok 4.535.0%

12

Thinking MachinesInklingOPEN36.5%

13

Thinking MachinesInkling SmallOPEN32.7%

14

MetaMuse Spark 1.145.6%

15

MetaMuse Spark 1.247.7%

16

AlibabaQwen 3.7 Plus39.3%

17

AlibabaQwen 3.8 MaxOPEN51.3%

Full Results Table

#	Model	Overall	Source	Date
🥇	Kimi K3OPEN Moonshot AI	54.3	VALS (2026)	2026-07
🥈	GPT-5.6 Sol OpenAI	52.6	VALS (2026)	2026-07
🥉	Claude Fable 5 Anthropic	51.9	VALS (2026)	2026-06
4	Qwen 3.8 MaxOPEN Alibaba	51.3	VALS (2026)	2026-08
5	Claude Opus 5 Anthropic	49.4	VALS (2026)	2026-07
6	Claude Sonnet 5 Anthropic	48.9	VALS (2026)	2026-06
7	Gemini 3.6 Flash Google	48.7	VALS (2026)	2026-07
8	Muse Spark 1.2 Meta	47.7	VALS (2026)	2026-08
9	Gemini 3.5 Flash Lite Google	47.3	VALS (2026)	2026-07
10	GPT-5.6 Terra OpenAI	47.0	VALS (2026)	2026-07
11	Muse Spark 1.1 Meta	45.6	VALS (2026)	2026-07
12	GPT-5.6 Luna OpenAI	44.2	VALS (2026)	2026-07
13	Qwen 3.7 Plus Alibaba	39.3	VALS (2026)	2026-06
14	InklingOPEN Thinking Machines	36.5	VALS (2026)	2026-07
15	Grok 4.5 xAI	35.0	VALS (2026)	2026-07
16	Inkling SmallOPEN Thinking Machines	32.7	VALS (2026)	2026-07
17	Grok 4.6 xAI	28.9	VALS (2026)	2026-08