Benchmark Almanac

Humor in AI: Cartoon Captioning

Claude 3 Opus 73.9% leads since June 2024
Not in model cards

Models write captions for New Yorker cartoons. Human judges and language models compare the captions with contest entries from different ranking groups.

The HOMER team compared generated captions with human entries ranked 1 to 10, 200 to 209, and 1,000 to 1,009.

Released
June 2024
Kind
Creative writing
Level
Everyday
Scored
Graded by a model
Answers
Open-ended
Tasks
All public
Measures
Preference
Subject
Arts
Language
English
In and out
Images → Text
Interaction
Single turn
Refresh
One fixed set
Run by
Anyone
In views
Vision
Strongest model tested
Claude 3 Opus #173 on the capability index
Last model added
February 2024
Scores refreshed
November 20th, 2026
5
Entries in its paper, 2 models we track

Claude 3 Opus leads with 73.9% Claude 3 Opus leads with 73.9%

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 four Overall Win Rates against human caption groups, so the headline is their plain mean. 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. This view shows only models we track, each at its best.

  1. 1 Claude 3 Opus 73.9%
  2. 2 GPT-4o (snapshot unspecified) 69.9%
  3. 3 GPT-3.5 Turbo (snapshot unspecified) 56.3%
  4. 4 Mistral-7B-Instruct-v0.1 BoN 20.1%
  5. 5 LLaVA SFT 7.55%

Source: The Humor in AI: Cartoon Captioning paper

Source: The Humor in AI: Cartoon Captioning paper

#EntryScoreSettingDateSource
1 Claude 3 Opus 73.9% Feb 2024 Official leaderboard
2 GPT-4o (snapshot unspecified) 69.9% Official leaderboard
3 GPT-3.5 Turbo (snapshot unspecified) 56.3% Official leaderboard
4 Mistral-7B-Instruct-v0.1 20.1% BoN Sep 2023 Official leaderboard
5 LLaVA 7.55% SFT Official leaderboard
#ModelScoreSettingDateSource
1 Claude 3 Opus 73.9% Feb 2024 Official leaderboard
2 Mistral-7B-Instruct-v0.1 20.1% BoN 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.

Anthropic
Benchmark paper Not tested since Jun 2024

Source: The Humor in AI: Cartoon Captioning paper

Scores over time

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

Plot with other benchmarks
In the benchmark’s paper Best so far
0% 20% 40% 60% 80% 100% 2024 Near the ceiling (85%) Claude 3 Opus Mistral-7B-Instruct-v0.1 0% 20% 40% 60% 80% 100% 2024 Near the ceiling (85%) Claude 3 Opus Mistral-7B-Instruct-v0.1

Source: Official Humor in AI: Cartoon Captioning 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 Writing and taste

All 65 in Writing and taste
  • Design Bench (Moonshot) In use Models make graphic designs from direct prompts or few-shot reference images. An automated grader rates the results as Elo scores. Kimi K3.1 Pro 957
  • WritingBench Fading Models complete 1,000 real-world writing requests across 6 domains and 100 subdomains. A judge model scores each reply on five query-specific criteria. GPT-5 83.9
  • Creative Writing (MiniMax in-house) Only in system cards Models write creative pieces for real Hailuo AI user requests. Automatic assessments score the writing. MiniMax-Text-01 81.3%
  • DeepSeek Chinese functional writing evaluation Only in system cards Models answer 3,170 everyday Chinese writing prompts such as reports, emails and speeches. Pairwise judging against a baseline model gives a win rate. DeepSeek-V4-Pro 62.6%
  • Slide generation human evaluation (Z.ai) Only in system cards People compare HTML slide decks from two models on content, layout and visual quality. Metric is overall win rate. GLM-5 67.5%
  • Task-dependent output homogenization evaluation Only in system cards Models answer prompts several times. A judge scores functional diversity where it is wanted and consistency where one answer is right. Muse Spark 0.21

Data audit

9 of 10 checks pass, 1 warning. Look first at the Newest score check. The newest came 2 years ago, in February 2024, for Claude 3 Opus. 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 2 models we track, plus 3 other entries on its leaderboard.
  • Warning Newest score The newest came 2 years ago, in February 2024, for Claude 3 Opus.
  • Note Frontier models None of the top 10 has a score. The strongest tested is Claude 3 Opus (#173).
  • Pass Headroom The best is 73.9%, under 85%, so it still separates models.
Leaderboard import 3 pass
  • Pass Importer We read the board on arxiv.org: 6 rows for models we track and 3 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