Benchmark Almanac

EPIC-KITCHENS VISOR Hand Object Segmentation

lidanxu 95.8% tops its leaderboard
Not in model cards

Models outline each hand and the object it touches in a kitchen image. They also identify which hand appears and whether it touches anything.

A*STAR combined PointRend with Segment Anything and reported 64.85% average precision for the combined hand and object mask on the test set.

Released
August 2022
Kind
Detection and captioning
Level
Everyday
Scored
Checked automatically
Answers
Prediction
Tasks
Public, plus a private test set
Measures
Capability
In and out
Images → Images, Text
Interaction
Single turn
Refresh
One fixed set
Run by
A host
4
Entries on its own leaderboard, 0 models we track

lidanxu tops the leaderboard with 95.8%

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 lidanxu 95.8%
  2. 2 zuoyi 95.7%
  3. 3 I2R-VI-FF 95.7%
  4. 4 visor-hos-baseline 95.4%

Source: Official EPIC-KITCHENS VISOR Hand Object Segmentation leaderboard

#EntryScoreSettingSubmitted byDateSource
1 lidanxu 95.8% lidanxu Jun 2023 Official leaderboard
2 zuoyi 95.7% zuoyi Jun 2023 Official leaderboard
3 I2R-VI-FF 95.7% I2R-VI-FF May 2023 Official leaderboard
4 visor-hos-baseline 95.4% visor-hos-baseline Jan 2023 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 7 checks pass. 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 pass 4 notes
  • Pass Independent runs Scores from the official leaderboard (4 entries).
  • Note Models scored 4 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 codalab.lisn.upsaclay.fr: 4 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