PARCEL
Models decide whether a New York court opinion supports, contradicts, or fails to address a cited claim. The benchmark contains 3,396 labeled claims.
- Made by
- University at Albany, SUNY
- Released
- October 2026
- Kind
- Law
- Level
- University
- Scored
- Checked automatically
- Answers
- Multiple choice
- Tasks
- All public
- Measures
- Capability
- Subject
- Law
- Language
- English
- Interaction
- Single turn
- Items from
- Real work and use
- Refresh
- One fixed set
- Run by
- Anyone
- In views
- Law and finance
- Strongest model tested
-
Gemini 3 Flash #60 on the capability index
- Last model added
- December 2025
- Scores refreshed
- November 20th, 2026
Gemini 3 Flash leads with 97% among models released by December 2025
Best score per model 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.
The newest model with a score here came out in December 2025, and nobody has tested a newer one. Among the 20 highest-ranked models on the capability index, these have no score yet:
- GPT-6.2 Astra
- Claude Fable 5.2
-
Gemini 4 Carbon
- GPT-6 Astra
- and 16 more
- 1
Gemini 3 Flash 97%
- 2 Kimi K2 Thinking 95%
- 3 GLM-4.7 94%
- 4
Qwen3-235B-A22B-Instruct Jul 2025 93%
- 5 gpt-oss-120b 90%
- 6
Gemini 2.5 Flash Sep 2025 90%
- 7
Llama 3.3 70B Instruct 81%
Source: The PARCEL paper
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | | 97% | Dec 2025 | Official leaderboard | |
| 2 | Kimi K2 Thinking | 95% | Nov 2025 | Official leaderboard | |
| 3 | GLM-4.7 | 94% | Dec 2025 | Official leaderboard | |
| 4 | | 93% | Jul 2025 | Official leaderboard | |
| 5 | gpt-oss-120b | 90% | Aug 2025 | Official leaderboard | |
| 6 | | 90% | Sep 2025 | Official leaderboard | |
| 7 | | 81% | Dec 2024 | Official leaderboard |
Rankings by part
We read 3 parts from the benchmark’s paper: Supported F1, Refuted F1 and Not Found F1. Each ranks models on one part of the test. Gemini 3 Flash leads every one of them. Arrows show how far a model moved from its overall rank among the models we track.
Supported F1
7 models we track have a score here.
- 1
Gemini 3 Flash 95%
- 2 Kimi K2 Thinking 94%
- 3 GLM-4.7 94%
- 4
Qwen3-235B-A22B-Instruct Jul 2025 91%
- 5 gpt-oss-120b 87%
- 6
Gemini 2.5 Flash Sep 2025 87%
- 7
Llama 3.3 70B Instruct 72%
Refuted F1
7 models we track have a score here.
- 1
Gemini 3 Flash 98%
- 2 Kimi K2 Thinking 97%
- 3
Qwen3-235B-A22B-Instruct Jul 2025 ↑1 96%
- 4 GLM-4.7 ↓1 96%
- 5 gpt-oss-120b 94%
- 6
Llama 3.3 70B Instruct ↑1 93%
- 7
Gemini 2.5 Flash Sep 2025 ↓1 93%
Not Found F1
7 models we track have a score here.
- 1
Gemini 3 Flash 97%
- 2 Kimi K2 Thinking 91%
- 3
Qwen3-235B-A22B-Instruct Jul 2025 ↑1 89%
- 4
Gemini 2.5 Flash Sep 2025 ↑2 89%
- 5 gpt-oss-120b 88%
- 6 GLM-4.7 ↓3 88%
- 7
Llama 3.3 70B Instruct 61%
Number one over time
Lab claims count from the day the card came out, independent runs from the model’s release.
Source: The PARCEL paper
Qwen3-235B-A22B-Instruct on the official leaderboard passed 85% in July 2025
Models released before it came out already scored that high. All the scores we have, one dot each, so a model tested at several settings appears more than once.
Source: Official PARCEL 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
All 8 checks pass. Every benchmark
Catalog record 2 pass
- Pass Task access All tasks are public.
- Pass Confidence Checked against a primary source.
Scores 2 pass 3 notes
- Pass Independent runs Scores from the benchmark’s paper (7 entries).
- Pass Models scored 7 models we track.
- Note Newest score The newest came 11 months ago, in December 2025, for GLM-4.7. That’s expected for a saturated test.
- Note Frontier models None of the top 10 has a score, which is fine for a retired test. The strongest tested is Gemini 3 Flash (#60).
- Note Headroom Saturated. The best is 97%, past 85% since July 2025.
Leaderboard import 3 pass
- Pass Importer We read the board on arxiv.org: 7 rows for models we track 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.