Benchmark Almanac

CrochetBench

Claude Sonnet 4 60.9 leads since November 2025
Not in model cards

Models identify stitches, select instructions that match a photo, write crochet patterns, and translate patterns into programs for a crochet simulator.

The FoundationChain team tested eight vision-language models on the translation task. It measured how often programs compiled and compared rendered shapes with photographs.

Released
November 2025
Kind
General visual questions
Level
University
Scored
Checked automatically
Answers
Open-ended
Tasks
All public
Measures
Capability
Subject
Arts
Language
English
In and out
Text, Images → Text, Code
Interaction
Single turn
Refresh
One fixed set
Run by
Anyone
In views
Vision
Strongest model tested
Claude Sonnet 4 #113 on the capability index
Last model added
September 2025
Scores refreshed
November 20th, 2026
9
Entries in its paper, 7 models we track

Claude Sonnet 4 leads with 60.9 among models released by September 2025 Claude Sonnet 4 leads with 60.9 among models released by September 2025

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. This view shows only models we track, each at its best.

The newest model with a score here came out in September 2025, and nobody has tested a newer one. Among the 20 highest-ranked models on the capability index, these have no score yet:

  1. 1 Claude Sonnet 4 60.9
  2. 2 DeepSeek-VL-7B-Chat 60.6
  3. 3 Qwen2-VL-7B-Instruct 58.2
  4. 4 GPT-4o Mar 2025 58.0
  5. 5 Gemini 2.5 Flash-Lite Sep 2025 56.8
  6. 6 Qwen2-VL (72B) 50.2
  7. 7 BLIP-2 Flan-T5 XL (3B) 22.5
  8. 8 Gemma 3 27B 16.1
  9. 9 Gemma 3 4B 12.7

Source: The CrochetBench paper

#EntryScoreSettingDateSource
1 Claude Sonnet 4 60.9 May 2025 Official leaderboard
2 DeepSeek-VL-7B-Chat 60.6 Mar 2024 Official leaderboard
3 Qwen2-VL-7B-Instruct 58.2 Aug 2024 Official leaderboard
4 GPT-4o Mar 2025 58.0 Mar 2025 Official leaderboard
5 Gemini 2.5 Flash-Lite Sep 2025 56.8 Sep 2025 Official leaderboard
6 Qwen2-VL (72B) 50.2 Official leaderboard
7 BLIP-2 Flan-T5 XL (3B) 22.5 Official leaderboard
8 Gemma 3 27B 16.1 Mar 2025 Official leaderboard
9 Gemma 3 4B 12.7 Mar 2025 Official leaderboard
#ModelScoreSettingDateSource
1 Claude Sonnet 4 60.9 May 2025 Official leaderboard
2 DeepSeek-VL-7B-Chat 60.6 Mar 2024 Official leaderboard
3 Qwen2-VL-7B-Instruct 58.2 Aug 2024 Official leaderboard
4 GPT-4o Mar 2025 58.0 Mar 2025 Official leaderboard
5 Gemini 2.5 Flash-Lite Sep 2025 56.8 Sep 2025 Official leaderboard
6 Gemma 3 27B 16.1 Mar 2025 Official leaderboard
7 Gemma 3 4B 12.7 Mar 2025 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 Nov 2025

Source: The CrochetBench 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
20.0 40.0 60.0 2024 2025 20.0 40.0 60.0 2024 2025

Source: Official CrochetBench 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

8 of 9 checks pass, 1 warning. Look first at the Newest score check. The newest came 14 months ago, in September 2025, for Gemini 2.5 Flash-Lite. Every benchmark

Catalog record 2 pass
  • Pass Task access All tasks are public.
  • Pass Confidence Checked against a primary source.
Scores 1 warning 2 pass 2 notes
  • Pass Independent runs Scores from the benchmark’s paper (9 entries).
  • Pass Models scored 7 models we track, plus 2 other entries on its leaderboard.
  • Warning Newest score The newest came 14 months ago, in September 2025, for Gemini 2.5 Flash-Lite.
  • Note Frontier models None of the top 10 has a score. The strongest tested is Claude Sonnet 4 (#113).
  • Note Headroom Scored as a plain number, with no fixed ceiling.
Leaderboard import 3 pass
  • Pass Importer We read the board on aclanthology.org: 7 rows for models we track and 2 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