Benchmark Almanac

Ego4D State Change Object Detection

Red Panda 37.2% tops its leaderboard
Not in model cards

Models locate the object that changes in a first-person video. The official test scores its bounding box in the frame where the change begins.

VideoIntern won with a Swin-L detector and scored 37.19 average precision on the official test. A later GLIP study used the official validation set.

Released
October 2021
Kind
Video understanding
Level
Everyday
Scored
Checked automatically
Answers
Prediction
Tasks
Public, plus a private test set
Measures
Capability
Language
English
In and out
Video → Images
Interaction
Single turn
Items from
Another benchmark
Refresh
One fixed set
Run by
A host
5
Entries on its own leaderboard, 0 models we track

Red Panda tops the leaderboard with 37.2%

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 Red Panda 37.2%
  2. 2 DETR 15.4%
  3. 3 FasterRCNN 13.3%
  4. 4 100DOH 10.7%
  5. 5 CenterNet 6.32%

Source: Official Ego4D State Change Object Detection leaderboard

#EntryScoreSettingSubmitted byDateSource
1 Red Panda 37.2% Red Panda Sep 2022 Official leaderboard
2 DETR 15.4% Host_6243_Team Mar 2022 Official leaderboard
3 FasterRCNN 13.3% Host_6243_Team Mar 2022 Official leaderboard
4 100DOH 10.7% Host_6243_Team Mar 2022 Official leaderboard
5 CenterNet 6.32% Host_6243_Team Mar 2022 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 Audio and video

All 695 in Audio and video
  • Video-MMMU In use 300 expert-level lecture videos with questions testing perception, comprehension and adaptation of knowledge. Accuracy. Qwen 3.8 Max 88.7%
  • LVBench In use Hours-long video understanding with multiple-choice questions on reasoning, grounding and summarization. Gemini 4 Argon 91.7%
  • MMVU In use 3,000 expert-annotated questions on videos across 27 disciplines. Multiple-choice and open-ended accuracy. Qwen 3.8 Max 82.4%
  • MLVU In use Multi-task long video understanding (minutes to hours) with multiple-choice and generation tasks. Accuracy. Qwen 3.8 Max 90.8%
  • FLEURS In use Models transcribe read speech in 102 languages built from FLoRes-101 sentences. Model cards usually report word error rate, so lower scores are better. Phi-4-multimodal 4.00%
  • VoiceBench In use Spoken instructions with speaker, environment and content variation. Voice assistant responses scored by GPT judge or rules. Qwen3.5-Omni-Plus 93.1%

Data audit

All 8 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 2 pass 3 notes
  • Pass Independent runs Scores from the official leaderboard (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 eval.ai: 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