BasedAGIBasedAGI
Finance

KYC profile synthesis

Turn identity docs and notes into a structured KYC profile.

task.entity_extractiontask.json_schema_filling

Best for this use case

gemini-3.1-pro-preview

Strong on Vals Finance Agent overall_accuracy_pct and Vals CorpFin v2 overall_accuracy_pct

41.5%

Best benchmark score

47.7%

Confidence

Ranked Models

30

Evidence Quality

88%

Evidence Points

28

Top Signal

Vals Finance Agent: overall_accuracy_pct

All Ranked Models

30 of 30 models
RankModelScore
๐Ÿฅ‡gemini-3.1-pro-preview

Strong on Vals Finance Agent overall_accuracy_pct and Vals CorpFin v2 overall_accuracy_pct

41.5%
๐Ÿฅˆgpt-5-2025-08-07

Strong on Vals Finance Agent overall_accuracy_pct and Vals CorpFin v2 overall_accuracy_pct

35.0%
๐Ÿฅ‰Grok-4-0709

Strong on Vals CorpFin v2 overall_accuracy_pct and Vals Finance Agent overall_accuracy_pct

34.7%
#4gemini-2.5-pro

Strong on FACTS Benchmark Suite facts_grounding_score_pct and Vals CorpFin v2 overall_accuracy_pct

34.5%
#5gpt-5-mini-2025-08-07

Strong on Vals Finance Agent overall_accuracy_pct and Vals CorpFin v2 overall_accuracy_pct

33.8%
#6gpt-5.2-2025-12-11

Strong on Vals Finance Agent overall_accuracy_pct and Vals CorpFin v2 overall_accuracy_pct

33.0%
#7claude-sonnet-4.6

Strong on Vals Finance Agent overall_accuracy_pct and Vals CorpFin v2 overall_accuracy_pct

32.9%
#8gemini-3-pro-preview

Strong on Vals Finance Agent overall_accuracy_pct and Vals CorpFin v2 overall_accuracy_pct

32.0%
#9gemini-3-flash-preview

Strong on Vals CorpFin v2 overall_accuracy_pct and Vals Finance Agent overall_accuracy_pct

31.9%
#10gpt-5.4-2026-03-05

Strong on Vals Finance Agent overall_accuracy_pct and Vals CorpFin v2 overall_accuracy_pct

31.3%
#11gemini-3.1-flash-lite-preview

Strong on Vals Finance Agent overall_accuracy_pct and Vals CorpFin v2 overall_accuracy_pct

30.6%
#12gpt-4.1-20250414

Strong on Vals CorpFin v2 overall_accuracy_pct and Vals Tax Eval v2 overall_accuracy_pct

29.1%
#13grok-4-fast-reasoning

Strong on Vals CorpFin v2 overall_accuracy_pct and Vals Finance Agent overall_accuracy_pct

28.3%
#14gpt-5.1-2025-11-13

Strong on Vals Finance Agent overall_accuracy_pct and Vals CorpFin v2 overall_accuracy_pct

28.2%
#15claude-sonnet-4

Strong on Vals CorpFin v2 overall_accuracy_pct and FACTS Benchmark Suite facts_grounding_score_pct

26.0%
#16claude-opus-4-6-thinking

Strong on Vals Finance Agent overall_accuracy_pct and Vals CorpFin v2 overall_accuracy_pct

25.9%
#17grok-4-1-fast-reasoning

Strong on Vals CorpFin v2 overall_accuracy_pct and Vals Finance Agent overall_accuracy_pct

25.3%
#18claude-opus-4-5-20251101-thinking

Strong on Vals Finance Agent overall_accuracy_pct and Vals CorpFin v2 overall_accuracy_pct

24.7%
#19claude-opus-4-5-20251101

Strong on Vals CorpFin v2 overall_accuracy_pct and FACTS Benchmark Suite facts_grounding_score_pct

24.4%
#20kimi-k2.5-thinking

Strong on Vals CorpFin v2 overall_accuracy_pct and Vals Finance Agent overall_accuracy_pct

24.3%
#21claude-sonnet-4-5-20250929-thinking

Strong on Vals Finance Agent overall_accuracy_pct and Vals CorpFin v2 overall_accuracy_pct

23.0%
#22grok-4.20-0309-reasoning

Strong on Vals Finance Agent overall_accuracy_pct and Vals CorpFin v2 overall_accuracy_pct

22.6%
#24o3-20250416

Strong on Vals CorpFin v2 overall_accuracy_pct and Vals Tax Eval v2 overall_accuracy_pct

21.2%
#25glm-5-thinking

Strong on Vals Finance Agent overall_accuracy_pct and Vals CorpFin v2 overall_accuracy_pct

21.1%
#26qwen3.5-flash

Strong on Vals CorpFin v2 overall_accuracy_pct and Vals Finance Agent overall_accuracy_pct

21.1%
#28claude-haiku-4-5-20251001-thinking

Strong on Vals Finance Agent overall_accuracy_pct and Vals CorpFin v2 overall_accuracy_pct

20.4%
#29gpt-5.4-nano-2026-03-17

Strong on Vals CorpFin v2 overall_accuracy_pct and Vals Finance Agent overall_accuracy_pct

20.3%
#30MiniMax-M2.7

Strong on Vals Finance Agent overall_accuracy_pct and Vals CorpFin v2 overall_accuracy_pct

19.7%
#31mistral-large-2512

Strong on Vals CorpFin v2 overall_accuracy_pct and Vals Tax Eval v2 overall_accuracy_pct

18.0%
#32grok-4-1-fast-non-reasoning

Strong on Vals Finance Agent overall_accuracy_pct and Vals CorpFin v2 overall_accuracy_pct

17.9%

Compare Models

Select two different models above to compare their evidence side by side.
โ–ถRanking diagnostics & missing models

Source lift

Ranked

54

Sources

8

Quality

Good

Vals Tax Eval v2

45 rows ยท 1.6% avg lift

Vals CorpFin v2

44 rows ยท 1.6% avg lift

Vals GPQA

36 rows ยท 0.7% avg lift

Vals Mortgage Tax

33 rows ยท 1.2% avg lift

Missing frontier models

No obvious gaps right now.

โ–ถTaxonomy & task details

Core tasks

task.entity_extractiontask.json_schema_filling

Required modes

mode.json_schema

Domains

domain.finance_compliance_aml

Related in Finance