Benchmark Almanac

NLVR2

UNITER 80.4% tops its leaderboard
Not in model cards

Models judge whether a sentence is true of a pair of photographs. The benchmark measures agreement with annotated truth values.

Made by
NLVR2 team
Released
November 2018
Kind
General visual questions
Level
Everyday
Scored
Checked automatically
Answers
Prediction
Tasks
All public
Measures
Capability
Language
English
In and out
Images, Text → Text
Interaction
Single turn
Refresh
One fixed set
Run by
Anyone
In views
Vision
11
Entries on its own leaderboard, 0 models we track

UNITER tops the leaderboard with 80.4%

Best score per entry from the benchmark's own leaderboard, read on November 20th, 2026. 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 UNITER 80.4%
  2. 2 LXMERT 76.2%
  3. 3 VisualBERT 67.3%
  4. 4 MaxEnt 53.5%
  5. 5 CNN+RNN 53.2%
  6. 6 FiLM 53%
  7. 7 Image Only (CNN) 51.9%
  8. 8 N2NMN, policy search from scratch 51.5%
  9. 9 Majority Class 51.4%
  10. 10 Text Only (RNN) 51.4%
  11. 11 MAC-Network 51.2%

Source: Official NLVR2 leaderboard

#EntryScoreSettingSubmitted byDateLinkSource
1 UNITER 80.4% Microsoft Dynamics 365 AI Research Oct 2019 arxiv.org Official leaderboard
2 LXMERT 76.2% UNC Chapel Hill Aug 2019 arxiv.org Official leaderboard
3 VisualBERT 67.3% UCLA & AI2 & PKU Aug 2019 arxiv.org Official leaderboard
4 MaxEnt 53.5% Cornell University Nov 2018 arxiv.org Official leaderboard
5 CNN+RNN 53.2% Cornell University Nov 2018 arxiv.org Official leaderboard
6 FiLM 53% MILA, ran by Cornell University Nov 2018 arxiv.org Official leaderboard
7 Image Only (CNN) 51.9% Cornell University Nov 2018 arxiv.org Official leaderboard
8 N2NMN, policy search from scratch 51.5% UC Berkeley, ran by Cornell University Nov 2018 arxiv.org Official leaderboard
9 Majority Class 51.4% Cornell University Nov 2018 arxiv.org Official leaderboard
10 Text Only (RNN) 51.4% Cornell University Nov 2018 arxiv.org Official leaderboard
11 MAC-Network 51.2% Stanford University, ran by Cornell University Nov 2018 arxiv.org 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 Vision

All 636 in Vision
  • MMMU In use 11.5K college-level multimodal questions across 30 subjects. Multiple-choice and open accuracy. Qwen 3.6 Plus 86%
  • MMMU-Pro In use Harder MMMU: college-level multimodal questions with more options and vision-only inputs to remove text shortcuts. GPT-5.6 Sol 84.6%
  • CharXiv In use Chart understanding on real arXiv figures. Reasoning questions require synthesizing information from complex charts. Claude Fable 5 93.5%
  • MathVista In use Math reasoning in visual contexts (charts, geometry, puzzles) from 31 datasets. Answer accuracy. Seed2.1 Pro 90.7%
  • MATH-Vision (MathVision) In use 3,040 competition math problems with visual context. Answer accuracy. Qwen 3.8 Max 97.7%
  • MMStar In use Models answer 1,500 human-curated image questions that cannot be solved without the image, across 6 core capabilities. Scored by accuracy. Qwen 3.8 Max 85.9%

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 official leaderboard (11 entries).
  • Pass Models scored 11 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 lil.nlp.cornell.edu: 11 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