Contract redline summary
Summarize material changes between contract versions with clause refs.
Provisional leader
gemini-2.5-pro
Current leader based on limited benchmark evidence. Treat this ranking as directional until coverage improves.
32.8%
Best benchmark score
50.2%
Confidence
All ranked models โ top 3
Ranked Models
30
Evidence Quality
83%
Evidence Points
34
Top Signal
LEXam Leaderboard: average_score_pct
All Ranked Models
| Rank | Model | Score |
|---|---|---|
| ๐ฅ | gemini-2.5-pro Strong on LEXam Leaderboard average_score_pct and FACTS Benchmark Suite facts_grounding_score_pct | 32.8% |
| ๐ฅ | gpt-5-2025-08-07 Strong on LEXam Leaderboard average_score_pct and FACTS Benchmark Suite facts_grounding_score_pct | 31.6% |
| ๐ฅ | gpt-5-mini-2025-08-07 Strong on LEXam Leaderboard average_score_pct and Vals Case Law v2 overall_accuracy_pct | 31.5% |
| #4 | gemini-3.1-pro-preview Strong on SimpleQA Verified simpleqa_verified_score_pct and FACTS Benchmark Suite facts_grounding_score_pct | 30.5% |
| #5 | gemini-3-pro-preview Strong on LEXam Leaderboard average_score_pct and SimpleQA Verified simpleqa_verified_score_pct | 28.1% |
| #6 | claude-sonnet-4 Strong on Galileo Agent Leaderboard v2 Avg TSQ and Vals Legal Bench overall_accuracy_pct | 25.9% |
| #7 | gemini-2.5-flash Strong on FACTS Benchmark Suite facts_grounding_score_pct and Galileo Agent Leaderboard v2 Avg TSQ | 23.2% |
| #8 | gpt-4.1-20250414 Strong on Vals Case Law v2 overall_accuracy_pct and Vectara HHEM Leaderboard overall_hallucination_error_pct | 23.1% |
| #9 | Grok-4-0709 Strong on Vals Legal Bench overall_accuracy_pct and Vals Case Law v2 overall_accuracy_pct | 22.9% |
| #10 | gemini-3-flash-preview Strong on Vals Legal Bench overall_accuracy_pct and FACTS Benchmark Suite facts_grounding_score_pct | 22.8% |
| #11 | claude-sonnet-4.6 Strong on Vals Finance Agent overall_accuracy_pct and Vals Legal Bench overall_accuracy_pct | 22.2% |
| #12 | gemini-3.1-flash-lite-preview Strong on FACTS Benchmark Suite facts_grounding_score_pct and Vals Legal Bench overall_accuracy_pct | 21.5% |
| #13 | gpt-5.4-2026-03-05 Strong on Vals Legal Bench overall_accuracy_pct and Vectara HHEM Leaderboard overall_hallucination_error_pct | 21.3% |
| #14 | gpt-5.2-2025-12-11 Strong on FACTS Benchmark Suite facts_grounding_score_pct and Vals Legal Bench overall_accuracy_pct | 21.0% |
| #15 | claude-opus-4-5-20251101 Strong on FACTS Benchmark Suite facts_grounding_score_pct and Vals Legal Bench overall_accuracy_pct | 19.9% |
| #16 | grok-4-fast-reasoning Strong on Vals CorpFin v2 overall_accuracy_pct and Vals Legal Bench overall_accuracy_pct | 19.4% |
| #17 | gpt-5.1-2025-11-13 Strong on Vals Case Law v2 overall_accuracy_pct and Vals Legal Bench overall_accuracy_pct | 18.6% |
| #18 | deepseek-r1 Strong on LEXam Leaderboard average_score_pct and SYCON Bench (Table 2) sycon_unethical_tof_pct | 18.1% |
| #19 | grok-4-1-fast-reasoning Strong on Vals Legal Bench overall_accuracy_pct and Vals CorpFin v2 overall_accuracy_pct | 17.1% |
| #20 | o3-20250416 Strong on Vals Legal Bench overall_accuracy_pct and SimpleQA Verified simpleqa_verified_score_pct | 15.7% |
| #22 | gpt-4.1 Strong on LEXam Leaderboard average_score_pct and LEXam Leaderboard open_question_judge_score_pct | 15.4% |
| #23 | grok-3 Strong on Vectara HHEM Leaderboard overall_hallucination_error_pct and Vals Legal Bench overall_accuracy_pct | 15.0% |
| #24 | claude-opus-4-6-thinking Strong on Vals Legal Bench overall_accuracy_pct and Vals CorpFin v2 overall_accuracy_pct | 14.2% |
| #25 | mistral-large-2512 Strong on Vals Legal Bench overall_accuracy_pct and Vals CorpFin v2 overall_accuracy_pct | 13.8% |
| #26 | claude-opus-4-1-20250805 Strong on Vals Legal Bench overall_accuracy_pct and FACTS Benchmark Suite facts_grounding_score_pct | 13.6% |
| #27 | claude-opus-4-5-20251101-thinking Strong on Vals Legal Bench overall_accuracy_pct and Vals Finance Agent overall_accuracy_pct | 13.4% |
| #28 | claude-sonnet-4-5-20250929-thinking Strong on Vals Legal Bench overall_accuracy_pct and Vals Finance Agent overall_accuracy_pct | 12.7% |
| #29 | grok-4-1-fast-non-reasoning Strong on Vals Legal Bench overall_accuracy_pct and Vals Finance Agent overall_accuracy_pct | 12.7% |
| #32 | glm-5-thinking Strong on Vals Legal Bench overall_accuracy_pct and Vals CorpFin v2 overall_accuracy_pct | 12.0% |
| #33 | deepseek-v3 Strong on Vectara HHEM Leaderboard overall_hallucination_error_pct and SYCON Bench (Table 2) sycon_unethical_tof_pct | 11.8% |
Compare Models
โถRanking diagnostics & missing models
Source lift
Ranked
61
Sources
8
Quality
Low
Vals CorpFin v2
Vals Legal Bench
Vals Finance Agent
Vals Case Law v2
Missing frontier models
No obvious gaps right now.
โถTaxonomy & task details
Core tasks
Required modes
Domains
Related in Legal
Contract Drafting & Redlining
Drafting, reviewing, and suggesting edits to legal contracts and agreements.
Contract Q&A (RAG grounded)
Answer contract questions grounded in the actual contract text.
Regulatory summary
Summarize and compare regulatory text with conservative interpretation.
Clause playbook check
Check extracted terms against a playbook and flag deviations.