Benchmark Almanac

Meta-Album

ProtoNet 65.8% tops its leaderboard
Not in model cards

Models classify unfamiliar images after seeing a few labeled examples. Tasks span ten domains, including microscopy, remote sensing and wildlife.

Passes test 4. Independent competition teams ran cross-domain classification on Meta-Album. Imageomics evaluated seven named component datasets with vision models. The original paper reports 30 datasets.

Released
June 2022
Kind
General visual questions
Level
School
Scored
Checked automatically
Answers
Prediction
Tasks
All public
Measures
Capability
In and out
Images → Text
Interaction
Single turn
Items from
Another benchmark
Refresh
One fixed set
Run by
Anyone
5
Entries in its paper, 0 models we track

ProtoNet tops the leaderboard with 65.8%

Best score per entry from the benchmark's paper, read on November 20th, 2026. A paper’s table doesn’t add newer models. Mean accuracy across the 30 paper datasets gives each dataset equal weight, with 1,800 test tasks per dataset. 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 ProtoNet Within domain, 5-way 20-shot 65.8%
  2. 2 MatchingNet Within domain, 5-way 20-shot 63.1%
  3. 3 Finetuning Within domain, 5-way 20-shot 61.3%
  4. 4 FO-MAML Within domain, 5-way 20-shot 56.6%
  5. 5 TrainFromScratch Within domain, 5-way 20-shot 40.7%

Source: The Meta-Album paper

#EntryScoreSettingDateSource
1 ProtoNet 65.8% Within domain, 5-way 20-shot Official leaderboard
2 MatchingNet 63.1% Within domain, 5-way 20-shot Official leaderboard
3 Finetuning 61.3% Within domain, 5-way 20-shot Official leaderboard
4 FO-MAML 56.6% Within domain, 5-way 20-shot Official leaderboard
5 TrainFromScratch 40.7% Within domain, 5-way 20-shot 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 benchmark’s paper (5 entries).
  • Pass Models scored 5 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 arxiv.org: 5 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