Finance

Accounts payable invoice extraction (text)

Extract structured fields from invoices/receipts for AP workflows.

task.invoice_receipt_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

38.8%

Best benchmark score

44.6%

Confidence

All ranked models — top 3

🥇

gemini-3.1-pro-preview

38.8%

🥈

Grok-4-0709

36.4%

🥉

gpt-5-2025-08-07

35.1%

Ranked Models

Evidence Quality

88%

Evidence Points

Top Signal

Vals Finance Agent: overall_accuracy_pct

All Ranked Models

30 of 30 models

Rank	Model	Score	Confidence	Price / 1M	Evidence sources
🥇	gemini-3.1-pro-preview Strong on Vals Finance Agent overall_accuracy_pct and Vals CorpFin v2 overall_accuracy_pct	38.8%	45%	$4.50	Vals Finance AgentVals CorpFin v2
🥈	Grok-4-0709 Strong on Vals CorpFin v2 overall_accuracy_pct and Vals Finance Agent overall_accuracy_pct	36.4%	50%	—	Vals CorpFin v2Vals Finance Agent
🥉	gpt-5-2025-08-07 Strong on Vals Finance Agent overall_accuracy_pct and Vals Tax Eval v2 overall_accuracy_pct	35.1%	47%	—	Vals Finance AgentVals Tax Eval v2
#4	gemini-2.5-pro Strong on Vals CorpFin v2 overall_accuracy_pct and Vals Finance Agent overall_accuracy_pct	33.5%	50%	$3.44	Vals CorpFin v2Vals Finance Agent
#5	gpt-5.2-2025-12-11 Strong on Vals Finance Agent overall_accuracy_pct and Vals CorpFin v2 overall_accuracy_pct	33.5%	38%	—	Vals Finance AgentVals CorpFin v2
#6	claude-sonnet-4.6 Strong on Vals Finance Agent overall_accuracy_pct and Vals CorpFin v2 overall_accuracy_pct	33.0%	38%	$6.00	Vals Finance AgentVals CorpFin v2
#7	gpt-5-mini-2025-08-07 Strong on Vals Finance Agent overall_accuracy_pct and Vals Tax Eval v2 overall_accuracy_pct	32.9%	44%	—	Vals Finance AgentVals Tax Eval v2
#8	gpt-5.4-2026-03-05 Strong on Vals Finance Agent overall_accuracy_pct and Vals CorpFin v2 overall_accuracy_pct	32.2%	39%	—	Vals Finance AgentVals CorpFin v2
#9	gemini-3-pro-preview Strong on Vals Finance Agent overall_accuracy_pct and Vals CorpFin v2 overall_accuracy_pct	31.5%	41%	$4.50	Vals Finance AgentVals CorpFin v2
#10	gpt-4.1-20250414 Strong on Vals Tax Eval v2 overall_accuracy_pct and Vals CorpFin v2 overall_accuracy_pct	30.9%	41%	—	Vals Tax Eval v2Vals CorpFin v2
#11	gemini-3-flash-preview Strong on Vals CorpFin v2 overall_accuracy_pct and Vals Tax Eval v2 overall_accuracy_pct	30.2%	40%	$1.13	Vals CorpFin v2Vals Tax Eval v2
#12	gpt-5.1-2025-11-13 Strong on Vals Finance Agent overall_accuracy_pct and Vals CorpFin v2 overall_accuracy_pct	29.3%	40%	—	Vals Finance AgentVals CorpFin v2
#13	gemini-3.1-flash-lite-preview Strong on Vals Finance Agent overall_accuracy_pct and Vals Tax Eval v2 overall_accuracy_pct	29.1%	42%	$0.56	Vals Finance AgentVals Tax Eval v2
#14	claude-opus-4-6-thinking Strong on Vals Finance Agent overall_accuracy_pct and Vals CorpFin v2 overall_accuracy_pct	28.7%	32%	—	Vals Finance AgentVals CorpFin v2
#15	grok-4-fast-reasoning Strong on Vals CorpFin v2 overall_accuracy_pct and Vals Tax Eval v2 overall_accuracy_pct	28.5%	44%	$0.28	Vals CorpFin v2Vals Tax Eval v2
#16	claude-sonnet-4 Strong on Galileo Agent Leaderboard v2 Banking AC and Vals Tax Eval v2 overall_accuracy_pct	28.2%	41%	$6.00	Galileo Agent Leaderboard v2Vals Tax Eval v2
#17	claude-opus-4-5-20251101-thinking Strong on Vals Finance Agent overall_accuracy_pct and Vals CorpFin v2 overall_accuracy_pct	27.8%	32%	—	Vals Finance AgentVals CorpFin v2
#18	grok-4-1-fast-reasoning Strong on Vals CorpFin v2 overall_accuracy_pct and Vals Finance Agent overall_accuracy_pct	26.7%	37%	$0.28	Vals CorpFin v2Vals Finance Agent
#19	kimi-k2.5-thinking Strong on Vals CorpFin v2 overall_accuracy_pct and Vals Finance Agent overall_accuracy_pct	26.6%	33%	—	Vals CorpFin v2Vals Finance Agent
#20	claude-sonnet-4-5-20250929-thinking Strong on Vals Finance Agent overall_accuracy_pct and Vals CorpFin v2 overall_accuracy_pct	25.7%	32%	—	Vals Finance AgentVals CorpFin v2
#21	grok-4.20-0309-reasoning Strong on Vals Finance Agent overall_accuracy_pct and Vals CorpFin v2 overall_accuracy_pct	24.7%	32%	—	Vals Finance AgentVals CorpFin v2
#22	qwen3.5-flash Strong on Vals CorpFin v2 overall_accuracy_pct and Vals Tax Eval v2 overall_accuracy_pct	23.4%	31%	—	Vals CorpFin v2Vals Tax Eval v2
#25	claude-opus-4-5-20251101 Strong on Vals Tax Eval v2 overall_accuracy_pct and Vals CorpFin v2 overall_accuracy_pct	22.5%	30%	—	Vals Tax Eval v2Vals CorpFin v2
#26	claude-haiku-4-5-20251001-thinking Strong on Vals Finance Agent overall_accuracy_pct and Vals CorpFin v2 overall_accuracy_pct	22.4%	32%	—	Vals Finance AgentVals CorpFin v2
#27	gpt-5.4-nano-2026-03-17 Strong on Vals Finance Agent overall_accuracy_pct and Vals CorpFin v2 overall_accuracy_pct	22.4%	31%	—	Vals Finance AgentVals CorpFin v2
#28	glm-5-thinking Strong on Vals Finance Agent overall_accuracy_pct and Vals CorpFin v2 overall_accuracy_pct	22.3%	29%	—	Vals Finance AgentVals CorpFin v2
#29	MiniMax-M2.7 Strong on Vals Finance Agent overall_accuracy_pct and Vals CorpFin v2 overall_accuracy_pct	21.1%	29%	$0.53	Vals Finance AgentVals CorpFin v2
#30	o3-20250416 Strong on Vals Tax Eval v2 overall_accuracy_pct and Vals CorpFin v2 overall_accuracy_pct	20.9%	29%	$3.50	Vals Tax Eval v2Vals CorpFin v2
#31	gpt-4.1-mini-20250414 Strong on Vals Tax Eval v2 overall_accuracy_pct and Galileo Agent Leaderboard v2 Banking AC	20.8%	27%	—	Vals Tax Eval v2Galileo Agent Leaderboard v2
#32	glm-4.7 Strong on Vals Finance Agent overall_accuracy_pct and Vals Tax Eval v2 overall_accuracy_pct	19.6%	30%	—	Vals Finance AgentVals Tax Eval v2