DraftNEPABench
Agents draft sections of environmental impact statements using technical and regulatory source documents. Model judges score the drafts against rubrics, and specialists assess a sample.
OpenAI reports its joint evaluation with PermitAI. The technical paper compares Codex CLI, Claude Code and Gemini CLI with retrieval baselines.
- Made by
- Pacific Northwest National Laboratory and OpenAI
- Released
- February 2026
- Kind
- Law
- Level
- Expert
- Scored
- Graded by a model
- Answers
- Agent task
- Tasks
- Public, plus a private test set
- Measures
- Capability
- Subject
- Earth and environmental sciences, Law
- Language
- English
- Interaction
- Agentic
- Environment
- Terminal
- Items from
- Real work and use
- Refresh
- One fixed set
- Run by
- A host
- In views
- Agents, Law and finance
- Strongest model tested
- GPT-5 #71 on the capability index
- Last model added
- September 2025
- Scores refreshed
- November 21st, 2026
Claude Code tops the leaderboard with 3.75 GPT-5 leads with 2.41
Best score per entry from the benchmark's paper, read on November 21st, 2026. A paper’s table doesn’t add newer models. Where a model ran with several settings or harnesses, we keep its best. Names in gray aren't in our model list: fine-tunes, agent systems, products and older models. They don't count toward leaders. The best model we track is GPT-5, at 2.41. This view shows only models we track, each at its best.
- 1 Claude Code 3.75
- 2 Codex CLI 3.27
- 3 Gemini CLI 2.90
- 4 GPT-5 2.41
- 5 Claude Sonnet 4.5 2.22
- 6 Gemini 2.5 Pro (snapshot unspecified) 2.21
Source: The DraftNEPABench paper
- 1 GPT-5 2.41
- 2 Claude Sonnet 4.5 2.22
Source: The DraftNEPABench paper
| # | Entry | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | Claude Code | 3.75 | Official leaderboard | ||
| 2 | Codex CLI | 3.27 | Official leaderboard | ||
| 3 | Gemini CLI | 2.90 | Official leaderboard | ||
| 4 | GPT-5 | 2.41 | Aug 2025 | Official leaderboard | |
| 5 | Claude Sonnet 4.5 | 2.22 | Sep 2025 | Official leaderboard | |
| 6 | Gemini 2.5 Pro (snapshot unspecified) | 2.21 | Official leaderboard |
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | GPT-5 | 2.41 | Aug 2025 | Official leaderboard | |
| 2 | Claude Sonnet 4.5 | 2.22 | Sep 2025 | Official leaderboard |
Scores over time
All the scores we have, one dot each, so a model tested at several settings appears more than once.
Source: Official DraftNEPABench leaderboard
No lab model card reports it yet
We read the headline results of 540 launch posts from 57 labs, and none of them list this benchmark.
More in Law, finance and medicine
- MedXpertQA-MM In use Models answer expert-level medical exam questions that combine images with clinical records and test results. Scoring is accuracy.
Qwen 3.8 Max 80.4%
- HealthBench Professional In use 525 physician-authored tasks from real clinician chats (care consult, documentation, research) with physician-adjudicated rubrics. Claude Sonnet 5.5 69.2%
- HealthBench In use 5,000 realistic health conversations graded against physician-written rubrics. A length-adjusted variant penalizes verbosity. GPT-5 67.2%
- FinSearchComp In use Agents search the web to fetch live financial data, look up history, and run multi-step investigations, across 635 expert-written questions. Scored by answer accuracy.
Ling-3.1-flash 81.7%
- KorMedMCQA In use Models answer 7,469 multiple-choice questions from Korean licensing exams for doctors, nurses, pharmacists and dentists, held from 2012 to 2024. o1-preview 92.7%
- Harvey LAB-AA v1.1 In use Artificial Analysis's run of Harvey's Legal Agent Benchmark on Harvey's newer private set of 120 tasks across 24 practice areas. A deliverable with a material hallucination scores zero, and the headline is the share of judges who find every rubric criterion passed. GPT-6.2 Astra 15%
Data audit
8 of 9 checks pass, 1 warning. Look first at the Newest score check. The newest came 14 months ago, in September 2025, for Claude Sonnet 4.5. Every benchmark
Catalog record 2 pass
- Pass Task access Public tasks, plus a private test set.
- Pass Confidence Checked against a primary source.
Scores 1 warning 2 pass 2 notes
- Pass Independent runs Scores from the benchmark’s paper (6 entries).
- Pass Models scored 2 models we track, plus 4 other entries on its leaderboard.
- Warning Newest score The newest came 14 months ago, in September 2025, for Claude Sonnet 4.5.
- Note Frontier models None of the top 10 has a score. The strongest tested is GPT-5 (#71).
- Note Headroom Scored as a plain number, with no fixed ceiling.
Leaderboard import 3 pass
- Pass Importer We read the board on github.com: 2 rows for models we track and 4 other entries at the last read.
- Pass Last read November 21st, 2026.
- Pass Read worked The last read worked.
Consistency 1 pass 1 note
- Note Lab claims No model has both a lab number and an independent run.
- Pass Known issues No published audit found problems.