Lease abstraction
Extract key lease terms and schedules into structured output.
Provisional leader
gpt-5-2025-08-07
Current leader based on limited benchmark evidence. Treat this ranking as directional until coverage improves.
24.5%
Best benchmark score
34.1%
Confidence
All ranked models — top 3
Ranked Models
30
Evidence Quality
80%
Evidence Points
30
Top Signal
LEXam Leaderboard: average_score_pct
All Ranked Models
| Rank | Model | Score |
|---|---|---|
| 🥇 | gpt-5-2025-08-07 Strong on LEXam Leaderboard average_score_pct and FACTS Benchmark Suite facts_grounding_score_pct | 24.5% |
| 🥈 | gemini-2.5-pro Strong on LEXam Leaderboard average_score_pct and FACTS Benchmark Suite facts_grounding_score_pct | 22.4% |
| 🥉 | gemini-3.1-pro-preview Strong on Vals Finance Agent overall_accuracy_pct and FACTS Benchmark Suite facts_search_score_pct | 21.1% |
| #4 | gpt-5-mini-2025-08-07 Strong on LEXam Leaderboard average_score_pct and Vals Finance Agent overall_accuracy_pct | 20.1% |
| #5 | gemini-3-pro-preview Strong on LEXam Leaderboard average_score_pct and Vals Finance Agent overall_accuracy_pct | 19.2% |
| #6 | gpt-4.1-20250414 Strong on MMLongBench-Doc Leaderboard acc_score_pct and Galileo Agent Leaderboard v2 Avg AC | 18.5% |
| #7 | Grok-4-0709 Strong on Vals CorpFin v2 overall_accuracy_pct and Vals Finance Agent overall_accuracy_pct | 16.6% |
| #8 | gemini-3-flash-preview Strong on Vals CorpFin v2 overall_accuracy_pct and FACTS Benchmark Suite facts_grounding_score_pct | 16.1% |
| #9 | gpt-5.2-2025-12-11 Strong on FACTS Benchmark Suite facts_grounding_score_pct and Vals CorpFin v2 overall_accuracy_pct | 15.6% |
| #10 | claude-sonnet-4 Strong on Galileo Agent Leaderboard v2 Avg AC and Vectara HHEM Leaderboard overall_hallucination_error_pct | 15.4% |
| #11 | gemini-3.1-flash-lite-preview Strong on FACTS Benchmark Suite facts_grounding_score_pct and Vectara HHEM Leaderboard overall_hallucination_error_pct | 14.8% |
| #12 | claude-sonnet-4.6 Strong on Vals Finance Agent overall_accuracy_pct and Vals CorpFin v2 overall_accuracy_pct | 14.7% |
| #13 | gpt-5.4-2026-03-05 Strong on Vectara HHEM Leaderboard overall_hallucination_error_pct and Vals CorpFin v2 overall_accuracy_pct | 13.8% |
| #14 | claude-opus-4-5-20251101 Strong on FACTS Benchmark Suite facts_grounding_score_pct and Vals CorpFin v2 overall_accuracy_pct | 13.5% |
| #15 | gemini-2.5-flash Strong on FACTS Benchmark Suite facts_grounding_score_pct and Vectara HHEM Leaderboard overall_hallucination_error_pct | 13.0% |
| #16 | gpt-5.1-2025-11-13 Strong on Vals Finance Agent overall_accuracy_pct and Vals CorpFin v2 overall_accuracy_pct | 12.5% |
| #17 | grok-4-fast-reasoning Strong on Vals CorpFin v2 overall_accuracy_pct and Vals Finance Agent overall_accuracy_pct | 12.4% |
| #18 | o3-20250416 Strong on Vals CorpFin v2 overall_accuracy_pct and SciArena Leaderboard rating_elo | 12.2% |
| #20 | deepseek-r1 Strong on LEXam Leaderboard average_score_pct and ContractEval Leaderboard contract_adherence_csr_pct | 11.5% |
| #22 | grok-4-1-fast-reasoning Strong on Vals CorpFin v2 overall_accuracy_pct and Vals Finance Agent overall_accuracy_pct | 11.1% |
| #28 | claude-opus-4-6-thinking Strong on Vals CorpFin v2 overall_accuracy_pct and Vals Finance Agent overall_accuracy_pct | 10.3% |
| #31 | kimi-k2.5-thinking Strong on Vals CorpFin v2 overall_accuracy_pct and Vals Finance Agent overall_accuracy_pct | 9.8% |
| #32 | grok-3 Strong on Vectara HHEM Leaderboard overall_hallucination_error_pct and Vals CorpFin v2 overall_accuracy_pct | 9.6% |
| #33 | claude-opus-4-5-20251101-thinking Strong on Vals Finance Agent overall_accuracy_pct and Vals CorpFin v2 overall_accuracy_pct | 9.5% |
| #35 | claude-sonnet-4-5-20250929-thinking Strong on Vals Finance Agent overall_accuracy_pct and Vals CorpFin v2 overall_accuracy_pct | 8.9% |
| #37 | grok-4.20-0309-reasoning Strong on Vals CorpFin v2 overall_accuracy_pct and Vals Finance Agent overall_accuracy_pct | 8.7% |
| #38 | glm-5-thinking Strong on Vals CorpFin v2 overall_accuracy_pct and Vals Finance Agent overall_accuracy_pct | 8.7% |
| #39 | gpt-4o Strong on LEXam Leaderboard average_score_pct and JSONSchemaBench Leaderboard medium_schema_compliance_pct | 8.7% |
| #40 | gpt-4.1 Strong on LEXam Leaderboard average_score_pct and LanguageBench overall:mean | 8.6% |
| #41 | grok-4-1-fast-non-reasoning Strong on Vals Finance Agent overall_accuracy_pct and Vectara HHEM Leaderboard overall_answer_rate_pct | 8.4% |
Compare Models
▶Ranking diagnostics & missing models
Source lift
Ranked
49
Sources
8
Quality
Low
Vals CorpFin v2
Vals Finance Agent
Vals Tax Eval v2
Vals Legal Bench
Missing frontier models
No obvious gaps right now.