hr_recruiting

Best LLM for Resume Parsing

Compare models for extracting structured candidate profiles from resumes.

#1 Recommendation

gpt-4.1-20250414

Strong on MMLongBench-Doc Leaderboard acc_score_pct (75%) and Galileo Agent Leaderboard v2 Avg TSQ (64%)

external/openai/gpt-4-1-20250414

20.5%

Score

29.5%

Confidence

Evidence

Runners-up:#2 Grok-4-0709 (13.4%)#3 claude-sonnet-4-20250514 (13.4%)#4 gemini-2.5-flash (13.3%)

Ranked Models

Evidence Quality

78%

Scoring

Benchmark-backed

Top Signal

MMLongBench-Doc Leaderboard: acc_score_pct

All Ranked Models

Open weights only

Max params:

Min confidence:

30 of 30

Rank	Model	Score	Confidence	Evidence	Top Benchmarks
#1	gpt-4.1-20250414 Strong on MMLongBench-Doc Leaderboard acc_score_pct (75%) and Galileo Agent Leaderboard v2 Avg TSQ (64%)	20.5%	29.5%	19	MMLongBench-Doc Leaderboard acc_score_pct (Mar 16, 2026) Galileo Agent Leaderboard v2 Avg TSQ (Mar 16, 2026)
#2	Grok-4-0709 Strong on Galileo Agent Leaderboard v2 Avg TSQ (85%) and Galileo Agent Leaderboard v2 Avg AC (57%)	13.4%	18.7%	18	Galileo Agent Leaderboard v2 Avg TSQ (Mar 16, 2026) Galileo Agent Leaderboard v2 Avg AC (Mar 16, 2026)
#4	claude-sonnet-4-20250514	13.4%	18.0%	17	Galileo Agent Leaderboard v2 Avg TSQ (Mar 16, 2026) Galileo Agent Leaderboard v2 Avg AC (Mar 16, 2026)
#5	gemini-2.5-flash	13.3%	16.8%	14	Galileo Agent Leaderboard v2 Avg TSQ (Mar 16, 2026) LanguageBench overall:mean (Mar 12, 2026)
#6	gemini-2.5-pro	13.3%	21.3%	21	Galileo Agent Leaderboard v2 Avg TSQ (Mar 16, 2026) Galileo Agent Leaderboard v2 Avg AC (Mar 16, 2026)
#7	gpt-4o-20241120	13.1%	21.1%	12	MMLongBench-Doc Leaderboard acc_score_pct (Mar 16, 2026) DuckDB NSQL Leaderboard all_execution_accuracy (Mar 16, 2026)
#11	qwen-2.5-72b-instruct	12.6%	17.3%	10	Galileo Agent Leaderboard v2 Avg TSQ (Mar 16, 2026) DuckDB NSQL Leaderboard all_execution_accuracy (Mar 16, 2026)
#17	gemini-3-pro-preview	11.2%	14.4%	21	FACTS Benchmark Suite average_score_pct (Mar 16, 2026) Vals Mortgage Tax overall_accuracy_pct (Mar 16, 2026)
#23	google/gemini-3.1-pro-preview	10.2%	11.5%	16	Vals Mortgage Tax overall_accuracy_pct (Mar 16, 2026) Vals GPQA overall_accuracy_pct (Mar 16, 2026)
#24	gpt-4o	9.8%	11.8%	11	JSONSchemaBench Leaderboard medium_schema_compliance_pct (Mar 12, 2026) DuckDB NSQL Leaderboard all_execution_accuracy (Mar 16, 2026)
#27	gpt-5-2025-08-07	9.4%	11.3%	16	Vals MedQA overall_accuracy_pct (Mar 16, 2026) Vals Legal Bench overall_accuracy_pct (Mar 16, 2026)
#28	openai/gpt-5.4-2026-03-05	9.2%	10.8%	15	Vectara HHEM Leaderboard overall_hallucination_error_pct (Mar 12, 2026) Vals MedQA overall_accuracy_pct (Mar 16, 2026)
#29	gpt-4.1-mini-20250414	9.1%	13.2%	10	Galileo Agent Leaderboard v2 Avg TSQ (Mar 16, 2026) Galileo Agent Leaderboard v2 Avg AC (Mar 16, 2026)
#30	gpt-5.1-2025-11-13	9.0%	11.3%	16	Vals Case Law v2 overall_accuracy_pct (Mar 16, 2026) Vals MedScribe overall_accuracy_pct (Mar 16, 2026)
#31	anthropic/claude-sonnet-4.6	8.9%	10.8%	15	Vals Finance Agent overall_accuracy_pct (Mar 16, 2026) Vals Tax Eval v2 overall_accuracy_pct (Mar 16, 2026)
#32	claude-opus-4-5-20251101	8.8%	11.3%	16	Vals Mortgage Tax overall_accuracy_pct (Mar 16, 2026) Vals MedQA overall_accuracy_pct (Mar 16, 2026)
#35	gpt-5-mini-2025-08-07	8.6%	12.0%	17	Vals MedQA overall_accuracy_pct (Mar 16, 2026) Vals LiveCodeBench overall_accuracy_pct (Mar 16, 2026)
#37	gemini-3-flash-preview	8.4%	10.6%	15	Vals Legal Bench overall_accuracy_pct (Mar 16, 2026) Vals MedQA overall_accuracy_pct (Mar 16, 2026)
#40	openai/gpt-4o-mini-2024-07-18	7.7%	16.5%	11	DuckDB NSQL Leaderboard all_execution_accuracy (Mar 16, 2026) LLM Trustworthy Leaderboard privacy (Mar 16, 2026)
#41	kimi/kimi-k2.5-thinking	7.5%	10.6%	15	Vals CorpFin v2 overall_accuracy_pct (Mar 16, 2026) Vals MedQA overall_accuracy_pct (Mar 16, 2026)
#42	xai-org/grok-4-fast-reasoning	7.3%	10.8%	15	Vals CorpFin v2 overall_accuracy_pct (Mar 16, 2026) Vals Tax Eval v2 overall_accuracy_pct (Mar 16, 2026)
#43	google/gemini-2.0-flash-001	7.3%	11.0%	10	LanguageBench overall:mean (Mar 12, 2026) DuckDB NSQL Leaderboard all_execution_accuracy (Mar 16, 2026)
#45	gpt-4o-2024-08-06	7.0%	11.8%	13	DuckDB NSQL Leaderboard all_execution_accuracy (Mar 16, 2026) Vectara HHEM Leaderboard overall_hallucination_error_pct (Mar 12, 2026)
#46	google/gemini-3.1-flash-lite-preview	7.0%	10.1%	14	Vals Mortgage Tax overall_accuracy_pct (Mar 16, 2026) Vectara HHEM Leaderboard overall_hallucination_error_pct (Mar 12, 2026)
#48	xai-org/grok-4-1-fast-reasoning	6.9%	10.8%	15	Vals CorpFin v2 overall_accuracy_pct (Mar 16, 2026) Vals MedQA overall_accuracy_pct (Mar 16, 2026)
#50	deepseek/deepseek-r1	6.7%	11.5%	13	DuckDB NSQL Leaderboard all_execution_accuracy (Mar 16, 2026) Aider Polyglot Leaderboard percent_correct_pct (Mar 16, 2026)
#54	Meta-Llama-3-8B-Instruct	5.7%	11.8%	5	LLM Trustworthy Leaderboard fairness (Mar 16, 2026) LLM Trustworthy Leaderboard privacy (Mar 16, 2026)
#56	xai-org/grok-4-1-fast-non-reasoning	4.8%	10.1%	14	Vals Legal Bench overall_accuracy_pct (Mar 16, 2026) Vals Finance Agent overall_accuracy_pct (Mar 16, 2026)
#58	GPT-4.1-nano-2025-04-14	4.3%	12.5%	9	Galileo Agent Leaderboard v2 Avg AC (Mar 16, 2026) Galileo Agent Leaderboard v2 Avg TSQ (Mar 16, 2026)
#60	gpt-4o-2024-05-13	4.0%	11.3%	7	LLM Trustworthy Leaderboard privacy (Mar 16, 2026) LM Arena Hard Auto v0.1 score (Mar 16, 2026)

Head-to-Head: #1 vs #2

Top Pick

gpt-4.1-20250414

Strong on MMLongBench-Doc Leaderboard acc_score_pct (75%) and Galileo Agent Leaderboard v2 Avg TSQ (64%)

20.5%

Conf 29.5%

Grok-4-0709

Strong on Galileo Agent Leaderboard v2 Avg TSQ (85%) and Galileo Agent Leaderboard v2 Avg AC (57%)

13.4%

Conf 18.7%

Full Comparison with Benchmark Evidence →

Full Use-Case Page Browse All Use Cases How We Score

Related Lookups

Best LLM for Code Generation

Benchmark-backed ranking of models for generating correct, secure code from requirements.

Best LLM for Debugging

Find the top-ranked models for localizing bugs and proposing fixes with explanations.

Best LLM for Unit Test Generation

Ranked models for generating meaningful unit tests and edge cases from code.

Best LLM for Code Review

Compare models for automated PR review covering correctness, security, and maintainability.

Best LLM for Refactoring

Ranked models for safely refactoring code while preserving behavior and improving clarity.

Best LLM for IDE Code Completion

Compare models for fast, accurate local-context code completion and snippet generation.