Benchmark Almanac

SF20K Competition 2025

WXYZ 65.8% tops its leaderboard
Not in model cards

Models answer story questions about short films. GPT-4.1-nano compares their answers with human references. Films released during the competition determine the final rankings.

The organizers received 286 submissions from 22 teams across two tracks. The winning team used Qwen2.5-VL-7B.

Released
July 2025
Kind
Long videos
Level
Everyday
Scored
Graded by a model
Answers
Open-ended
Tasks
Public, plus a private test set
Measures
Capability
Language
English
In and out
Video, Text → Text
Interaction
Single turn
Refresh
Live
Run by
A host
Based on
SF20K-Test
In views
Vision, Kept fresh
8
Entries on its own leaderboard, 0 models we track

WXYZ tops the leaderboard with 65.8%

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 WXYZ 65.8%
  2. 2 sudook 65.3%
  3. 3 BASELINE 59.9%
  4. 4 R&T 58.5%
  5. 5 eg 53.5%
  6. 6 eloral-wxx 0%
  7. 7 hellowydwyd 0%
  8. 8 yuqian1013 0%

Source: Official SF20K Competition 2025 leaderboard

#EntryScoreSettingSubmitted byDateSource
1 WXYZ 65.8% WXYZ Oct 2025 Official leaderboard
2 sudook 65.3% sudook Oct 2025 Official leaderboard
3 BASELINE 59.9% BASELINE Oct 2025 Official leaderboard
4 R&T 58.5% R&T Oct 2025 Official leaderboard
5 eg 53.5% eg Oct 2025 Official leaderboard
6 eloral-wxx 0% eloral-wxx Oct 2025 Official leaderboard
7 hellowydwyd 0% hellowydwyd Oct 2025 Official leaderboard
8 yuqian1013 0% yuqian1013 Oct 2025 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 (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 huggingface.co: 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