Finance

Transaction anomaly narrative

Summarize anomalies into hypotheses, evidence, and follow-up actions.

task.multi_doc_synthesistask.risk_assessment

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

43.3%

Best benchmark score

49.7%

Confidence

All ranked models — top 3

🥇

gemini-3.1-pro-preview

43.3%

🥈

Grok-4-0709

36.7%

🥉

gemini-2.5-pro

36.4%

Ranked Models

Evidence Quality

89%

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	43.3%	50%	$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	36.7%	52%	—	Vals CorpFin v2Vals Finance Agent
🥉	gemini-2.5-pro Strong on FACTS Benchmark Suite facts_grounding_score_pct and Vals CorpFin v2 overall_accuracy_pct	36.4%	54%	$3.44	FACTS Benchmark SuiteVals CorpFin v2
#4	gpt-5-mini-2025-08-07 Strong on Vals Finance Agent overall_accuracy_pct and Vals CorpFin v2 overall_accuracy_pct	35.9%	52%	—	Vals Finance AgentVals CorpFin v2
#5	gpt-5-2025-08-07 Strong on Vals Finance Agent overall_accuracy_pct and Vals CorpFin v2 overall_accuracy_pct	35.7%	46%	—	Vals Finance AgentVals CorpFin v2
#6	gpt-5.2-2025-12-11 Strong on Vals Finance Agent overall_accuracy_pct and Vals CorpFin v2 overall_accuracy_pct	35.1%	41%	—	Vals Finance AgentVals CorpFin v2
#7	gemini-3-pro-preview Strong on Vals Finance Agent overall_accuracy_pct and Vals CorpFin v2 overall_accuracy_pct	35.0%	47%	$4.50	Vals Finance AgentVals CorpFin v2
#8	claude-sonnet-4.6 Strong on Vals Finance Agent overall_accuracy_pct and Vals CorpFin v2 overall_accuracy_pct	34.3%	41%	$6.00	Vals Finance AgentVals CorpFin v2
#9	gemini-3-flash-preview Strong on Vals CorpFin v2 overall_accuracy_pct and Vals Finance Agent overall_accuracy_pct	33.2%	45%	$1.13	Vals CorpFin v2Vals Finance Agent
#10	gpt-5.4-2026-03-05 Strong on Vals Finance Agent overall_accuracy_pct and Vals CorpFin v2 overall_accuracy_pct	32.6%	40%	—	Vals Finance AgentVals CorpFin v2
#11	gemini-3.1-flash-lite-preview Strong on Vals Finance Agent overall_accuracy_pct and Vals CorpFin v2 overall_accuracy_pct	31.9%	46%	$0.56	Vals Finance AgentVals CorpFin v2
#12	gpt-4.1-20250414 Strong on Vals CorpFin v2 overall_accuracy_pct and Vals Tax Eval v2 overall_accuracy_pct	30.4%	43%	—	Vals CorpFin v2Vals Tax Eval v2
#13	grok-4-fast-reasoning Strong on Vals CorpFin v2 overall_accuracy_pct and Vals Finance Agent overall_accuracy_pct	29.4%	49%	$0.28	Vals CorpFin v2Vals Finance Agent
#14	gpt-5.1-2025-11-13 Strong on Vals Finance Agent overall_accuracy_pct and Vals CorpFin v2 overall_accuracy_pct	29.3%	43%	—	Vals Finance AgentVals CorpFin v2
#15	grok-4-1-fast-reasoning Strong on Vals CorpFin v2 overall_accuracy_pct and Vals Finance Agent overall_accuracy_pct	27.2%	38%	$0.28	Vals CorpFin v2Vals Finance Agent
#16	claude-sonnet-4 Strong on Vals CorpFin v2 overall_accuracy_pct and FACTS Benchmark Suite facts_grounding_score_pct	27.1%	42%	$6.00	Vals CorpFin v2FACTS Benchmark Suite
#17	claude-opus-4-6-thinking Strong on Vals Finance Agent overall_accuracy_pct and Vals CorpFin v2 overall_accuracy_pct	27.0%	30%	—	Vals Finance AgentVals CorpFin v2
#18	claude-opus-4-5-20251101-thinking Strong on Vals Finance Agent overall_accuracy_pct and Vals CorpFin v2 overall_accuracy_pct	25.7%	30%	—	Vals Finance AgentVals CorpFin v2
#19	claude-opus-4-5-20251101 Strong on Vals CorpFin v2 overall_accuracy_pct and FACTS Benchmark Suite facts_grounding_score_pct	25.7%	37%	—	Vals CorpFin v2FACTS Benchmark Suite
#20	kimi-k2.5-thinking Strong on Vals CorpFin v2 overall_accuracy_pct and Vals Finance Agent overall_accuracy_pct	25.3%	32%	—	Vals CorpFin v2Vals Finance Agent
#21	claude-sonnet-4-5-20250929-thinking Strong on Vals Finance Agent overall_accuracy_pct and Vals CorpFin v2 overall_accuracy_pct	23.9%	30%	—	Vals Finance AgentVals CorpFin v2
#22	grok-4.20-0309-reasoning Strong on Vals Finance Agent overall_accuracy_pct and Vals CorpFin v2 overall_accuracy_pct	23.6%	30%	—	Vals Finance AgentVals CorpFin v2
#23	o3-20250416 Strong on Vals CorpFin v2 overall_accuracy_pct and SciArena Leaderboard rating_elo	23.3%	35%	$3.50	Vals CorpFin v2SciArena Leaderboard
#25	glm-5-thinking Strong on Vals Finance Agent overall_accuracy_pct and Vals CorpFin v2 overall_accuracy_pct	22.0%	29%	—	Vals Finance AgentVals CorpFin v2
#26	qwen3.5-flash Strong on Vals CorpFin v2 overall_accuracy_pct and Vals Finance Agent overall_accuracy_pct	22.0%	29%	—	Vals CorpFin v2Vals Finance Agent
#28	claude-haiku-4-5-20251001-thinking Strong on Vals Finance Agent overall_accuracy_pct and Vals CorpFin v2 overall_accuracy_pct	21.2%	30%	—	Vals Finance AgentVals CorpFin v2
#29	gpt-5.4-nano-2026-03-17 Strong on Vals CorpFin v2 overall_accuracy_pct and Vals Finance Agent overall_accuracy_pct	21.2%	29%	—	Vals CorpFin v2Vals Finance Agent
#30	MiniMax-M2.7 Strong on Vals Finance Agent overall_accuracy_pct and Vals CorpFin v2 overall_accuracy_pct	20.5%	28%	$0.53	Vals Finance AgentVals CorpFin v2
#31	grok-4-1-fast-non-reasoning Strong on Vals Finance Agent overall_accuracy_pct and Vals CorpFin v2 overall_accuracy_pct	19.4%	37%	$0.28	Vals Finance AgentVals CorpFin v2
#32	grok-3 Strong on Vals CorpFin v2 overall_accuracy_pct and Vals Tax Eval v2 overall_accuracy_pct	19.0%	27%	$6.00	Vals CorpFin v2Vals Tax Eval v2