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

Code Migration

Assesses code refactoring, legacy framework migration, and syntax translation accuracy.

Variable tasks

23 models evaluated

Updated 2026

View Source →Submit your score Methodology

57.5%

Top Score

Top model

Claude Opus 5

Model Rankings

financebenchmark.ai · Code Migration

16.1%

🥇

AnthropicClaude Opus 557.5%

🥈

AnthropicClaude Sonnet 544.4%

🥉

OpenAIGPT-5.6 Sol52.9%

4

DeepSeekDeepSeek V4 FlashOPEN38.6%

5

xAIGrok 4.644.6%

6

Moonshot AIKimi K3OPEN16.1%

7

AnthropicClaude Fable 555.1%

8

DeepSeekDeepSeek V4 Pro (0813)OPEN41.5%

9

GoogleGemini 3.5 Flash Lite6.2%

10

GoogleGemini 3.6 Flash30.9%

11

Zhipu AIGLM 5.2OPEN37.9%

12

OpenAIGPT-5.6 Luna44.5%

13

OpenAIGPT-5.6 Terra36.5%

14

xAIGrok 4.536.6%

15

Thinking MachinesInklingOPEN11.8%

16

Thinking MachinesInkling SmallOPEN13.7%

17

Moonshot AIKimi K2.7 CodeOPEN25.4%

18

Ant GroupLing 3.0 FlashOPEN0.0%

19

MetaMuse Spark 1.131.1%

20

MetaMuse Spark 1.229.9%

21

NVIDIANemotron 3 UltraOPEN4.9%

22

AlibabaQwen 3.7 Plus12.9%

23

AlibabaQwen 3.8 MaxOPEN24.0%

Full Results Table

#	Model	Overall	Source	Date
🥇	Claude Opus 5 Anthropic	57.5	VALS (2026)	2026-07
🥈	Claude Fable 5 Anthropic	55.1	VALS (2026)	2026-06
🥉	GPT-5.6 Sol OpenAI	52.9	VALS (2026)	2026-07
4	Grok 4.6 xAI	44.6	VALS (2026)	2026-08
5	GPT-5.6 Luna OpenAI	44.5	VALS (2026)	2026-07
6	Claude Sonnet 5 Anthropic	44.4	VALS (2026)	2026-06
7	DeepSeek V4 Pro (0813)OPEN DeepSeek	41.5	VALS (2026)	2026-08
8	DeepSeek V4 FlashOPEN DeepSeek	38.6	VALS (2026)	2026-07
9	GLM 5.2OPEN Zhipu AI	37.9	VALS (2026)	2026-06
10	Grok 4.5 xAI	36.6	VALS (2026)	2026-07
11	GPT-5.6 Terra OpenAI	36.5	VALS (2026)	2026-07
12	Muse Spark 1.1 Meta	31.1	VALS (2026)	2026-07
13	Gemini 3.6 Flash Google	30.9	VALS (2026)	2026-07
14	Muse Spark 1.2 Meta	29.9	VALS (2026)	2026-08
15	Kimi K2.7 CodeOPEN Moonshot AI	25.4	VALS (2026)	2026-06
16	Qwen 3.8 MaxOPEN Alibaba	24.0	VALS (2026)	2026-08
17	Kimi K3OPEN Moonshot AI	16.1	VALS (2026)	2026-07
18	Inkling SmallOPEN Thinking Machines	13.7	VALS (2026)	2026-07
19	Qwen 3.7 Plus Alibaba	12.9	VALS (2026)	2026-06
20	InklingOPEN Thinking Machines	11.8	VALS (2026)	2026-07
21	Gemini 3.5 Flash Lite Google	6.2	VALS (2026)	2026-07
22	Nemotron 3 UltraOPEN NVIDIA	4.9	VALS (2026)	2026-06
23	Ling 3.0 FlashOPEN Ant Group	0.0	VALS (2026)	2026-07