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 3verification

MedCode

Evaluates medical ontology mapping, ICD billing codes, and clinical software tasks.

Variable tasks

20 models evaluated

Updated 2026

View Source →Submit your score Methodology

63.6%

Top Score

Top model

Claude Opus 5

Model Rankings

financebenchmark.ai · MedCode

48.9%

🥇

AnthropicClaude Opus 563.6%

🥈

AnthropicClaude Sonnet 547.5%

🥉

OpenAIGPT-5.6 Sol44.0%

4

DeepSeekDeepSeek V4 FlashOPEN41.4%

5

xAIGrok 4.644.7%

6

Moonshot AIKimi K3OPEN48.9%

7

AnthropicClaude Fable 556.1%

8

DeepSeekDeepSeek V4 Pro (0813)OPEN42.5%

9

GoogleGemini 3.5 Flash Lite43.5%

10

GoogleGemini 3.6 Flash53.1%

11

Zhipu AIGLM 5.2OPEN40.8%

12

OpenAIGPT-5.6 Luna42.4%

13

OpenAIGPT-5.6 Terra43.4%

14

xAIGrok 4.543.3%

15

Thinking MachinesInklingOPEN41.2%

16

Thinking MachinesInkling SmallOPEN37.9%

17

Ant GroupLing 3.0 FlashOPEN32.3%

18

MetaMuse Spark 1.249.4%

19

NVIDIANemotron 3 UltraOPEN38.6%

20

AlibabaQwen 3.8 MaxOPEN40.7%

Full Results Table

#	Model	Overall	Source	Date
🥇	Claude Opus 5 Anthropic	63.6	VALS (2026)	2026-07
🥈	Claude Fable 5 Anthropic	56.1	VALS (2026)	2026-06
🥉	Gemini 3.6 Flash Google	53.1	VALS (2026)	2026-07
4	Muse Spark 1.2 Meta	49.4	VALS (2026)	2026-08
5	Kimi K3OPEN Moonshot AI	48.9	VALS (2026)	2026-07
6	Claude Sonnet 5 Anthropic	47.5	VALS (2026)	2026-06
7	Grok 4.6 xAI	44.7	VALS (2026)	2026-08
8	GPT-5.6 Sol OpenAI	44.0	VALS (2026)	2026-07
9	Gemini 3.5 Flash Lite Google	43.5	VALS (2026)	2026-07
10	GPT-5.6 Terra OpenAI	43.4	VALS (2026)	2026-07
11	Grok 4.5 xAI	43.3	VALS (2026)	2026-07
12	DeepSeek V4 Pro (0813)OPEN DeepSeek	42.5	VALS (2026)	2026-08
13	GPT-5.6 Luna OpenAI	42.4	VALS (2026)	2026-07
14	DeepSeek V4 FlashOPEN DeepSeek	41.4	VALS (2026)	2026-07
15	InklingOPEN Thinking Machines	41.2	VALS (2026)	2026-07
16	GLM 5.2OPEN Zhipu AI	40.8	VALS (2026)	2026-06
17	Qwen 3.8 MaxOPEN Alibaba	40.7	VALS (2026)	2026-08
18	Nemotron 3 UltraOPEN NVIDIA	38.6	VALS (2026)	2026-06
19	Inkling SmallOPEN Thinking Machines	37.9	VALS (2026)	2026-07
20	Ling 3.0 FlashOPEN Ant Group	32.3	VALS (2026)	2026-07