HR policy Q&A

Answer HR policy questions grounded in authoritative text.

task.policy_qatask.rag_answer_with_citations

Evidence quality is currently limited for this use case. Rankings below are useful for exploration, not a strong winner claim.

Provisional leader

gemini-3.1-pro-preview

Current leader based on limited benchmark evidence. Treat this ranking as directional until coverage improves.

32.3%

Best benchmark score

36.7%

Confidence

All ranked models — top 3

🥇

gemini-3.1-pro-preview

32.3%

🥈

gemini-2.5-pro

29.2%

🥉

gpt-5-2025-08-07

26.7%

Ranked Models

Evidence Quality

84%

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 FACTS Benchmark Suite facts_search_score_pct	32.3%	37%	$4.50	Vals Finance AgentFACTS Benchmark Suite
🥈	gemini-2.5-pro Strong on FACTS Benchmark Suite facts_grounding_score_pct and Vectara HHEM Leaderboard overall_hallucination_error_pct	29.2%	44%	$3.44	FACTS Benchmark SuiteVectara HHEM Leaderboard
🥉	gpt-5-2025-08-07 Strong on FACTS Benchmark Suite facts_grounding_score_pct and Vals Finance Agent overall_accuracy_pct	26.7%	37%	—	FACTS Benchmark SuiteVals Finance Agent
#4	Grok-4-0709 Strong on Galileo Agent Leaderboard v2 Avg TSQ and Vals CorpFin v2 overall_accuracy_pct	25.6%	36%	—	Galileo Agent Leaderboard v2Vals CorpFin v2
#5	gpt-5-mini-2025-08-07 Strong on Vals Finance Agent overall_accuracy_pct and Vals CorpFin v2 overall_accuracy_pct	25.5%	41%	—	Vals Finance AgentVals CorpFin v2
#6	gemini-3-flash-preview Strong on Vals CorpFin v2 overall_accuracy_pct and FACTS Benchmark Suite facts_grounding_score_pct	24.6%	33%	$1.13	Vals CorpFin v2FACTS Benchmark Suite
#7	gpt-4.1-20250414 Strong on Vectara HHEM Leaderboard overall_hallucination_error_pct and Vals CorpFin v2 overall_accuracy_pct	23.8%	36%	—	Vectara HHEM LeaderboardVals CorpFin v2
#8	claude-sonnet-4 Strong on Galileo Agent Leaderboard v2 Avg TSQ and Vectara HHEM Leaderboard overall_hallucination_error_pct	23.8%	37%	$6.00	Galileo Agent Leaderboard v2Vectara HHEM Leaderboard
#9	gemini-3-pro-preview Strong on Vals Finance Agent overall_accuracy_pct and Vals CorpFin v2 overall_accuracy_pct	23.0%	32%	$4.50	Vals Finance AgentVals CorpFin v2
#10	gpt-5.2-2025-12-11 Strong on FACTS Benchmark Suite facts_grounding_score_pct and Vals CorpFin v2 overall_accuracy_pct	22.7%	27%	—	FACTS Benchmark SuiteVals CorpFin v2
#11	gemini-3.1-flash-lite-preview Strong on FACTS Benchmark Suite facts_grounding_score_pct and Vectara HHEM Leaderboard overall_hallucination_error_pct	22.7%	33%	$0.56	FACTS Benchmark SuiteVectara HHEM Leaderboard
#12	claude-sonnet-4.6 Strong on Vals Finance Agent overall_accuracy_pct and Vals CorpFin v2 overall_accuracy_pct	22.4%	29%	$6.00	Vals Finance AgentVals CorpFin v2
#13	gpt-5.4-2026-03-05 Strong on Vectara HHEM Leaderboard overall_hallucination_error_pct and Vals CorpFin v2 overall_accuracy_pct	21.1%	26%	—	Vectara HHEM LeaderboardVals CorpFin v2
#14	gemini-2.5-flash Strong on Galileo Agent Leaderboard v2 Avg TSQ and FACTS Benchmark Suite facts_grounding_score_pct	20.6%	32%	$0.17	Galileo Agent Leaderboard v2FACTS Benchmark Suite
#15	claude-opus-4-5-20251101 Strong on FACTS Benchmark Suite facts_grounding_score_pct and Vals CorpFin v2 overall_accuracy_pct	20.2%	29%	—	FACTS Benchmark SuiteVals CorpFin v2
#16	gpt-5.1-2025-11-13 Strong on Vals Finance Agent overall_accuracy_pct and Vals CorpFin v2 overall_accuracy_pct	19.1%	30%	—	Vals Finance AgentVals CorpFin v2
#17	grok-4-fast-reasoning Strong on Vals CorpFin v2 overall_accuracy_pct and Vals Finance Agent overall_accuracy_pct	18.9%	36%	$0.28	Vals CorpFin v2Vals Finance Agent
#18	o3-20250416 Strong on Vals CorpFin v2 overall_accuracy_pct and SciArena Leaderboard rating_elo	18.3%	28%	$3.50	Vals CorpFin v2SciArena Leaderboard
#19	claude-opus-4-6-thinking Strong on Vals CorpFin v2 overall_accuracy_pct and Vals Finance Agent overall_accuracy_pct	15.7%	17%	—	Vals CorpFin v2Vals Finance Agent
#20	grok-4-1-fast-reasoning Strong on Vals CorpFin v2 overall_accuracy_pct and Vals Finance Agent overall_accuracy_pct	15.6%	24%	$0.28	Vals CorpFin v2Vals Finance Agent
#21	kimi-k2.5-thinking Strong on Vals CorpFin v2 overall_accuracy_pct and Vals Finance Agent overall_accuracy_pct	14.9%	21%	—	Vals CorpFin v2Vals Finance Agent
#22	grok-3 Strong on Vectara HHEM Leaderboard overall_hallucination_error_pct and Vals CorpFin v2 overall_accuracy_pct	14.6%	21%	$6.00	Vectara HHEM LeaderboardVals CorpFin v2
#23	claude-opus-4-5-20251101-thinking Strong on Vals Finance Agent overall_accuracy_pct and Vals CorpFin v2 overall_accuracy_pct	14.5%	17%	—	Vals Finance AgentVals CorpFin v2
#24	claude-sonnet-4-5-20250929-thinking Strong on Vals Finance Agent overall_accuracy_pct and Vals CorpFin v2 overall_accuracy_pct	13.6%	17%	—	Vals Finance AgentVals CorpFin v2
#26	grok-4.20-0309-reasoning Strong on Vals CorpFin v2 overall_accuracy_pct and Vals Finance Agent overall_accuracy_pct	13.3%	17%	—	Vals CorpFin v2Vals Finance Agent
#27	glm-5-thinking Strong on Vals CorpFin v2 overall_accuracy_pct and Vals Finance Agent overall_accuracy_pct	13.3%	19%	—	Vals CorpFin v2Vals Finance Agent
#28	mistral-large-2512 Strong on Vals CorpFin v2 overall_accuracy_pct and Vectara HHEM Leaderboard overall_answer_rate_pct	12.2%	22%	—	Vals CorpFin v2Vectara HHEM Leaderboard
#29	MiniMax-M2.7 Strong on Vals CorpFin v2 overall_accuracy_pct and Vals Finance Agent overall_accuracy_pct	12.2%	16%	$0.53	Vals CorpFin v2Vals Finance Agent
#30	claude-haiku-4-5-20251001-thinking Strong on Vals CorpFin v2 overall_accuracy_pct and Vals Finance Agent overall_accuracy_pct	12.0%	17%	—	Vals CorpFin v2Vals Finance Agent
#31	claude-opus-4-1-20250805 Strong on Vectara HHEM Leaderboard overall_hallucination_error_pct and FACTS Benchmark Suite facts_grounding_score_pct	11.9%	23%	—	Vectara HHEM LeaderboardFACTS Benchmark Suite

Compare Models

Select two different models above to compare their evidence side by side.

▶Ranking diagnostics & missing models

Source lift

Ranked

Sources

Quality

Low

Vals CorpFin v2

44 rows · 1.6% avg lift

Vals Legal Bench

36 rows · 0.4% avg lift

Vals MedQA

36 rows · 0.4% avg lift

Vals Tax Eval v2

35 rows · 0.4% avg lift

Missing frontier models

No obvious gaps right now.

▶Taxonomy & task details

Core tasks

task.policy_qatask.rag_answer_with_citations

Required modes

mode.citations

Domains

domain.hr_recruiting

Related in HR

Job description drafting

Draft job descriptions that match role requirements and tone.

Candidate summary memo

Summarize a candidate profile into strengths, gaps, and questions.

Interview question bank

Generate structured interview questions and rubrics for a role.

Resume structuring

Extract structured candidate profiles from resumes.