Benchmark Almanac

ContractNLI

DeBERTa v2xlarge span identification 89.2% tops its leaderboard
Not in model cards

Models decide whether a contract supports, contradicts, or omits a claim. The original benchmark also asks them to identify the passages that justify their decision.

In November 2021, DeBERTa v2 xlarge with span-identification training led the backbone comparison at 89.2% classification accuracy. The authors also tested BERT base and large.

Released
October 2021
Kind
Law
Level
Expert
Scored
Checked automatically
Answers
Multiple choice
Tasks
All public
Measures
Capability
Subject
Law
Language
English
In and out
Text → Text
Interaction
Single turn
Items from
Real work and use
Refresh
One fixed set
Run by
Anyone
In views
Law and finance
8
Entries in its paper, 0 models we track

DeBERTa v2xlarge span identification tops the leaderboard with 89.2%

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.

  1. 1 DeBERTa v2xlarge span identification 89.2%
  2. 2 DeBERTa v2xlarge 88.5%
  3. 3 BERTlarge 87.5%
  4. 4 BERTlarge NDAs 87.5%
  5. 5 BERTbase NDAs 86.4%
  6. 6 BERTbase 83.8%
  7. 7 BERTbase case law 83.1%
  8. 8 BERTbase case law and contract 79.4%

Source: The ContractNLI paper

#EntryScoreSettingDateSource
1 DeBERTa v2xlarge span identification 89.2% Official leaderboard
2 DeBERTa v2xlarge 88.5% Official leaderboard
3 BERTlarge 87.5% Official leaderboard
4 BERTlarge NDAs 87.5% Official leaderboard
5 BERTbase NDAs 86.4% Official leaderboard
6 BERTbase 83.8% Official leaderboard
7 BERTbase case law 83.1% Official leaderboard
8 BERTbase case law and contract 79.4% Official 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

All 637 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 (8 entries).
  • Pass Models scored 8 entries on its leaderboard, none a model we track.
  • Note Newest score No scores yet.
  • Note Frontier models No models scored yet.
  • Note Headroom No scores yet.
Leaderboard import 3 pass
  • Pass Importer We read the board on aclanthology.org: 8 entries at the last read, none a model we track.
  • 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.

How we check