Benchmark Almanac

Kinetics-600

EVA 89.8% tops its leaderboard
Not in model cards
Version 600

Models recognize one of 600 human actions in short video clips.

MTEB reports accuracy on its Kinetics600VA task.

Made by
DeepMind
Released
August 2018
Kind
Video understanding
Level
Everyday
Scored
Checked automatically
Answers
Prediction
Tasks
All public
Measures
Capability
Language
English
In and out
Video → Text
Interaction
Single turn
Run by
Anyone
Based on
Kinetics-400
In views
Vision
8
Entries on SOTA2 Research’s leaderboard, 0 models we track

EVA tops the leaderboard with 89.8%

Best score per entry from SOTA2 Research’s 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 EVA Pre-training Data: K-722 (merged K-400, K-600, K-700), protocol: fine-tuning 89.8%
  2. 2 mPLUG-2 Setting: Fine-tuning 89.8%
  3. 3 CoCa Evaluation Protocol: finetuned 89.4%
  4. 4 Florence Params: 647M, Pretraining Data: FLD-900M, Views: 4 x 3 87.8%
  5. 5 mPLUG-2Base Setting: Fine-tuning 86.7%
  6. 6 Mformer-HR GFLOPS × views: 958.8×3×10, Pretrain: IN-21K 82.7%
  7. 7 Mformer-L GFLOPS × views: 1185.1×3×10, Pretrain: IN-21K 82.2%
  8. 8 Mformer GFLOPS × views: 369.5×3×10, Pretrain: IN-21K 81.6%

Source: SOTA2 Research’s leaderboard

#EntryScoreSettingDateLinkSource
1 EVA 89.8% Pre-training Data: K-722 (merged K-400, K-600, K-700), protocol: fine-tuning sota2.com Official leaderboard
2 mPLUG-2 89.8% Setting: Fine-tuning sota2.com Official leaderboard
3 CoCa 89.4% Evaluation Protocol: finetuned sota2.com Official leaderboard
4 Florence 87.8% Params: 647M, Pretraining Data: FLD-900M, Views: 4 x 3 sota2.com Official leaderboard
5 mPLUG-2Base 86.7% Setting: Fine-tuning sota2.com Official leaderboard
6 Mformer-HR 82.7% GFLOPS × views: 958.8×3×10, Pretrain: IN-21K sota2.com Official leaderboard
7 Mformer-L 82.2% GFLOPS × views: 1185.1×3×10, Pretrain: IN-21K sota2.com Official leaderboard
8 Mformer 81.6% GFLOPS × views: 369.5×3×10, Pretrain: IN-21K sota2.com 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.

Versions

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 All tasks are public.
  • Pass Confidence Checked against a primary source.
Scores 2 pass 3 notes
  • Pass Independent runs Scores from the official leaderboard (8 entries).
  • Pass Models scored 8 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 SOTA2 Research: 8 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