Benchmark Almanac

New Yorker Caption Contest Humor Understanding

GPT-4 (snapshot unspecified) 84.5% tops its leaderboard T5-11B 70.8% leads the models we track
Not in model cards

Models match a cartoon to its caption, choose the funnier of two captions, and explain a joke. They receive the cartoon or its description.

The authors report matching and ranking accuracy across five splits. Their Hugging Face dataset has 78 likes.

Released
September 2022
Kind
General visual questions
Level
Everyday
Scored
Checked automatically
Answers
Multiple choice
Tasks
Public, plus a private test set
Measures
Capability
Language
English
In and out
Images, Text → Text
Interaction
Single turn
Refresh
One fixed set
Run by
Anyone
In views
Vision
Last model added
October 2019
Scores refreshed
November 20th, 2026
7
Entries in its paper, 2 models we track

GPT-4 (snapshot unspecified) tops the leaderboard with 84.5% T5-11B leads with 70.8%

Best score per entry from the benchmark's paper, read on November 20th, 2026. A paper’s table doesn’t add newer models. The paper reports no overall score, so this headline is the matching accuracy column, which is the first task. 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 T5-11B, at 70.8%. This view shows only models we track, each at its best.

  1. 1 GPT-4 (snapshot unspecified) 5-shot 84.5%
  2. 2 GPT3-175B finetuned 75.1%
  3. 3 T5-11B from pixels 70.8%
  4. 4 GPT 3.5 (snapshot unspecified) 5-shot 63.8%
  5. 5 CLIP ViT-L/14@336px finetuned 62.3%
  6. 6 T5-Large from pixels 59.6%
  7. 7 Caption Only (T5-11B) 19.4%

Source: The New Yorker Caption Contest Humor Understanding paper

Source: The New Yorker Caption Contest Humor Understanding paper

#EntryScoreSettingDateSource
1 GPT-4 (snapshot unspecified) 84.5% 5-shot Official leaderboard
2 GPT3-175B 75.1% finetuned Official leaderboard
3 T5-11B 70.8% from pixels Oct 2019 Official leaderboard
4 GPT 3.5 (snapshot unspecified) 63.8% 5-shot Official leaderboard
5 CLIP ViT-L/14@336px 62.3% finetuned Official leaderboard
6 T5-Large 59.6% from pixels Official leaderboard
7 Caption Only (T5-11B) 19.4% Official leaderboard
#ModelScoreSettingDateSource
1 T5-11B 70.8% from pixels Oct 2019 Official leaderboard
2 T5-Large 59.6% from pixels Official leaderboard

Scores over time

All the scores we have, one dot each, so a model tested at several settings appears more than once.

In the benchmark’s paper
0% 20% 40% 60% 80% 100% 2020 Near the ceiling (85%) T5-11B 0% 20% 40% 60% 80% 100% 2020 Near the ceiling (85%) T5-11B

Source: Official New Yorker Caption Contest Humor Understanding 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

9 of 10 checks pass, 1 warning. Look first at the Newest score check. The newest came 7 years ago, in October 2019, for T5-11B. 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 3 pass 1 note
  • Pass Independent runs Scores from the benchmark’s paper (7 entries).
  • Pass Models scored 2 models we track, plus 5 other entries on its leaderboard.
  • Warning Newest score The newest came 7 years ago, in October 2019, for T5-11B.
  • Note Frontier models None of its models are on the capabilities index.
  • Pass Headroom The best is 70.8%, under 85%, so it still separates models.
Leaderboard import 3 pass
  • Pass Importer We read the board on aclanthology.org: 2 rows for models we track and 5 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.

How we check