Resume structuring

Extract structured candidate profiles from resumes.

task.resume_profile_extractiontask.json_schema_filling

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

Provisional leader

gpt-4.1-20250414

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

20.0%

Best benchmark score

28.5%

Confidence

All ranked models — top 3

🥇

gpt-4.1-20250414

20.0%

🥈

claude-sonnet-4

17.6%

🥉

gpt-5-2025-08-07

16.0%

Ranked Models

Evidence Quality

79%

Evidence Points

Top Signal

MMLongBench-Doc Leaderboard: acc_score_pct

All Ranked Models

30 of 30 models

Rank	Model	Score	Confidence	Price / 1M	Evidence sources
🥇	gpt-4.1-20250414 Strong on MMLongBench-Doc Leaderboard acc_score_pct and Galileo Agent Leaderboard v2 Avg TSQ	20.0%	29%	—	MMLongBench-Doc LeaderboardGalileo Agent Leaderboard v2
🥈	claude-sonnet-4 Strong on Galileo Agent Leaderboard v2 Avg TSQ and LanguageBench overall:mean	17.6%	23%	$6.00	Galileo Agent Leaderboard v2LanguageBench
🥉	gpt-5-2025-08-07 Strong on ExtractBench Paper Baselines credit_pass_rate_pct and Aider Polyglot Leaderboard percent_correct_pct	16.0%	27%	—	ExtractBench Paper BaselinesAider Polyglot Leaderboard
#4	gemini-2.5-pro Strong on Galileo Agent Leaderboard v2 Avg TSQ and Galileo Agent Leaderboard v2 Avg AC	14.8%	24%	$3.44	Galileo Agent Leaderboard v2Galileo Agent Leaderboard v2
#5	Grok-4-0709 Strong on Galileo Agent Leaderboard v2 Avg TSQ and Galileo Agent Leaderboard v2 Avg AC	13.9%	19%	—	Galileo Agent Leaderboard v2Galileo Agent Leaderboard v2
#6	gemini-2.5-flash Strong on Galileo Agent Leaderboard v2 Avg TSQ and LanguageBench overall:mean	13.5%	17%	$0.17	Galileo Agent Leaderboard v2LanguageBench
#9	gpt-4o-20241120 Strong on MMLongBench-Doc Leaderboard acc_score_pct and DuckDB NSQL Leaderboard all_execution_accuracy	13.0%	21%	—	MMLongBench-Doc LeaderboardDuckDB NSQL Leaderboard
#10	qwen-2.5-72b-instruct Strong on Galileo Agent Leaderboard v2 Avg TSQ and DuckDB NSQL Leaderboard all_execution_accuracy	12.5%	18%	—	Galileo Agent Leaderboard v2DuckDB NSQL Leaderboard
#15	gemini-3.1-pro-preview Strong on FACTS Benchmark Suite average_score_pct and Vals Mortgage Tax overall_accuracy_pct	12.0%	13%	$4.50	FACTS Benchmark SuiteVals Mortgage Tax
#22	gpt-5-mini-2025-08-07 Strong on Vals MedQA overall_accuracy_pct and Vals LiveCodeBench overall_accuracy_pct	10.7%	16%	—	Vals MedQAVals LiveCodeBench
#27	o3-20250416 Strong on Aider Polyglot Leaderboard percent_correct_pct and Vals MedQA overall_accuracy_pct	10.0%	13%	$3.50	Aider Polyglot LeaderboardVals MedQA
#28	gpt-4o Strong on JSONSchemaBench Leaderboard medium_schema_compliance_pct and DuckDB NSQL Leaderboard all_execution_accuracy	9.8%	13%	$0.26	JSONSchemaBench LeaderboardDuckDB NSQL Leaderboard
#29	gemini-3-flash-preview Strong on Vals Legal Bench overall_accuracy_pct and Vals MedQA overall_accuracy_pct	9.7%	12%	$1.13	Vals Legal BenchVals MedQA
#30	gpt-5.2-2025-12-11 Strong on FACTS Benchmark Suite facts_grounding_score_pct and Vals Tax Eval v2 overall_accuracy_pct	9.6%	11%	—	FACTS Benchmark SuiteVals Tax Eval v2
#31	gemini-3-pro-preview Strong on Vals Mortgage Tax overall_accuracy_pct and Vals Legal Bench overall_accuracy_pct	9.3%	12%	$4.50	Vals Mortgage TaxVals Legal Bench
#34	gpt-5.4-2026-03-05 Strong on Vectara HHEM Leaderboard overall_hallucination_error_pct and Vals MedQA overall_accuracy_pct	9.1%	11%	—	Vectara HHEM LeaderboardVals MedQA
#35	gpt-5.1-2025-11-13 Strong on Vals Case Law v2 overall_accuracy_pct and Vals MedScribe overall_accuracy_pct	8.9%	11%	—	Vals Case Law v2Vals MedScribe
#36	gpt-4.1-mini-20250414 Strong on Galileo Agent Leaderboard v2 Avg TSQ and Galileo Agent Leaderboard v2 Avg AC	8.8%	12%	—	Galileo Agent Leaderboard v2Galileo Agent Leaderboard v2
#37	claude-sonnet-4.6 Strong on Vals Tax Eval v2 overall_accuracy_pct and Vals Finance Agent overall_accuracy_pct	8.8%	11%	$6.00	Vals Tax Eval v2Vals Finance Agent
#40	gpt-4.1 Strong on DuckDB NSQL Leaderboard all_execution_accuracy and LanguageBench overall:mean	8.4%	10%	$3.50	DuckDB NSQL LeaderboardLanguageBench
#43	claude-opus-4-5-20251101 Strong on Vals Mortgage Tax overall_accuracy_pct and Vals MedQA overall_accuracy_pct	8.1%	10%	—	Vals Mortgage TaxVals MedQA
#44	gemini-3.1-flash-lite-preview Strong on Vals Mortgage Tax overall_accuracy_pct and Vectara HHEM Leaderboard overall_hallucination_error_pct	8.1%	12%	$0.56	Vals Mortgage TaxVectara HHEM Leaderboard
#45	deepseek-r1 Strong on DuckDB NSQL Leaderboard all_execution_accuracy and Aider Polyglot Leaderboard percent_correct_pct	8.0%	13%	$0.27	DuckDB NSQL LeaderboardAider Polyglot Leaderboard
#47	gpt-4o-mini-2024-07-18 Strong on DuckDB NSQL Leaderboard all_execution_accuracy and LLM Trustworthy Leaderboard privacy	7.7%	16%	—	DuckDB NSQL LeaderboardLLM Trustworthy Leaderboard
#48	kimi-k2.5-thinking Strong on Vals CorpFin v2 overall_accuracy_pct and Vals MedQA overall_accuracy_pct	7.6%	10%	—	Vals CorpFin v2Vals MedQA
#49	grok-4-fast-reasoning Strong on Vals CorpFin v2 overall_accuracy_pct and Vals Tax Eval v2 overall_accuracy_pct	7.4%	13%	$0.28	Vals CorpFin v2Vals Tax Eval v2
#50	o4-mini Strong on Aider Polyglot Leaderboard percent_correct_pct and Vals MedQA overall_accuracy_pct	7.4%	12%	$1.93	Aider Polyglot LeaderboardVals MedQA
#51	gemini-2.0-flash-001 Strong on LanguageBench overall:mean and DuckDB NSQL Leaderboard all_execution_accuracy	7.2%	11%	—	LanguageBenchDuckDB NSQL Leaderboard
#53	gemini-2.5-flash-lite Strong on Galileo Agent Leaderboard v2 Avg TSQ and Galileo Agent Leaderboard v2 Avg AC	7.1%	10%	$0.17	Galileo Agent Leaderboard v2Galileo Agent Leaderboard v2
#54	gpt-4o-2024-08-06 Strong on DuckDB NSQL Leaderboard all_execution_accuracy and Vectara HHEM Leaderboard overall_hallucination_error_pct	6.9%	11%	—	DuckDB NSQL LeaderboardVectara HHEM Leaderboard

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 Legal Bench

24 rows · 0.5% avg lift

Vals Tax Eval v2

24 rows · 0.5% avg lift

Vals Mortgage Tax

24 rows · 0.5% avg lift

Vals CorpFin v2

24 rows · 0.4% avg lift

Missing frontier models

grok-4-1-fast-non-reasoning

Thin evidence after weighting

Rank #15

14.9%

▶Taxonomy & task details

Core tasks

task.resume_profile_extractiontask.json_schema_filling

Required modes

mode.json_schema

Domains

domain.hr_recruiting

Related in HR

HR policy Q&A

Answer HR policy questions grounded in authoritative text.

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.