NEPAQuAD
Models answer questions about environmental impact statements. The authors compare answers with a reference under several conditions, including retrieval and access to the relevant passage.
PermitAI’s Models and Benchmarks team evaluated five models. The paper reports 1,590 questions. The later NEPABench dataset lists 1,589.
- Released
- July 2024
- Kind
- Law
- Level
- University
- Scored
- Graded by a model
- Answers
- Open-ended
- Tasks
- All public
- Measures
- Capability
- Language
- English
- Interaction
- Single turn
- Items from
- Real work and use
- Refresh
- One fixed set
- Run by
- Anyone
- Last model added
- September 2023
- Scores refreshed
- November 20th, 2026
Gemini 1.5 Pro (snapshot unspecified) tops the leaderboard with 81.2% Mistral-7B-Instruct-v0.1 leads with 75.3%
Best score per entry from the benchmark's paper, read on November 20th, 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 Mistral-7B-Instruct-v0.1, at 75.3%. This view shows only models we track, each at its best.
- 1 Gemini 1.5 Pro (snapshot unspecified) Gold context 81.2%
- 2 Claude 3.5 Sonnet (snapshot unspecified) Gold context 76.8%
- 3 GPT-4 (snapshot unspecified) Gold context 76.6%
- 4
Mistral-7B-Instruct-v0.1 Gold context 75.3%
- 5 Llama3.1 RAG context 74%
Source: The NEPAQuAD paper
Source: The NEPAQuAD paper
| # | Entry | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | Gemini 1.5 Pro (snapshot unspecified) | 81.2% | Gold context | Official leaderboard | |
| 2 | Claude 3.5 Sonnet (snapshot unspecified) | 76.8% | Gold context | Official leaderboard | |
| 3 | GPT-4 (snapshot unspecified) | 76.6% | Gold context | Official leaderboard | |
| 4 | | 75.3% | Gold context | Sep 2023 | Official leaderboard |
| 5 | Llama3.1 | 74% | RAG context | Official leaderboard |
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | | 75.3% | Gold context | Sep 2023 | Official leaderboard |
Number one over time
Lab claims count from the day the card came out, independent runs from the model’s release.
Source: The NEPAQuAD paper
Scores over time
All the scores we have, one dot each, so a model tested at several settings appears more than once.
Source: Official NEPAQuAD 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
9 of 10 checks pass, 1 warning. Look first at the Newest score check. The newest came 3 years ago, in September 2023, for Mistral-7B-Instruct-v0.1. Every benchmark
Catalog record 2 pass
- Pass Task access All tasks are public.
- Pass Confidence Checked against a primary source.
Scores 1 warning 3 pass 1 note
- Pass Independent runs Scores from the benchmark’s paper (5 entries).
- Pass Models scored 1 model we track, plus 4 other entries on its leaderboard.
- Warning Newest score The newest came 3 years ago, in September 2023, for Mistral-7B-Instruct-v0.1.
- Note Frontier models None of its models are on the capabilities index.
- Pass Headroom The best is 75.3%, under 85%, so it still separates models.
Leaderboard import 3 pass
- Pass Importer We read the board on arxiv.org: 4 rows for models we track and 4 other entries at the last read.
- Pass Last read November 20th, 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.