Benchmark Almanac

VDC Benchmark

Gemini-1.5 Pro (snapshot unspecified) 2.15 tops its leaderboard InternVL2-8B 1.96 leads the models we track
Not in model cards

Models describe the contents of a video in detail. The evaluation checks descriptions against human annotations using questions about the video.

Made by
Wenhao Chai and colleagues
Released
October 2024
Kind
Video captioning
Level
Everyday
Scored
Graded by a model
Answers
Open-ended
Tasks
All public
Measures
Capability
Language
English
In and out
Video → Text
Interaction
Single turn
Refresh
One fixed set
Run by
Anyone
In views
Vision
Last model added
August 2024
Scores refreshed
November 20th, 2026
16
Entries in its paper, 6 models we track

Gemini-1.5 Pro (snapshot unspecified) tops the leaderboard with 2.15 InternVL2-8B leads with 1.96 among models released by August 2024

Best score per entry from the benchmark's paper, read on November 20th, 2026. A paper’s table doesn’t add newer models. 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. The best model we track is InternVL2-8B, at 1.96. This view shows only models we track, each at its best.

The newest model with a score here came out in August 2024, and nobody has tested a newer one. Among the 20 highest-ranked models on the capability index, these have no score yet:

  1. 1 Gemini-1.5 Pro (snapshot unspecified) 2.15
  2. 2 AuroraCap -7B 1.98
  3. 3 InternVL2-8B 1.96
  4. 4 LLaVA-OneVision 7B 1.94
  5. 5 LLaVA-1.6-13B 1.85
  6. 6 LLaVA-1.6-7B 1.85
  7. 7 LLaVA-NeXT-V7B 1.85
  8. 8 sharegpt4video-8b 1.85
  9. 9 LLaVA-v1.5-13B 1.80
  10. 10 LongVA-7B 1.79
  11. 11 LLaVA-1.5-7B 1.76
  12. 12 Video-LLaVA-7B 1.72
  13. 13 VILA-7B 1.70
  14. 14 MovieChat-7B 1.64
  15. 15 LLaMA-VID 1.62
  16. 16 Video-ChatGPT-7B 1.62

Source: The VDC Benchmark paper

#EntryScoreSettingDateSource
1 Gemini-1.5 Pro (snapshot unspecified) 2.15 Official leaderboard
2 AuroraCap -7B 1.98 Official leaderboard
3 InternVL2-8B 1.96 Jul 2024 Official leaderboard
4 LLaVA-OneVision 7B 1.94 Aug 2024 Official leaderboard
5 LLaVA-1.6-13B 1.85 Official leaderboard
6 LLaVA-1.6-7B 1.85 Official leaderboard
7 LLaVA-NeXT-V7B 1.85 Official leaderboard
8 sharegpt4video-8b 1.85 May 2024 Official leaderboard
9 LLaVA-v1.5-13B 1.80 Oct 2023 Official leaderboard
10 LongVA-7B 1.79 Jun 2024 Official leaderboard
11 LLaVA-1.5-7B 1.76 Official leaderboard
12 Video-LLaVA-7B 1.72 Nov 2023 Official leaderboard
13 VILA-7B 1.70 Official leaderboard
14 MovieChat-7B 1.64 Official leaderboard
15 LLaMA-VID 1.62 Official leaderboard
16 Video-ChatGPT-7B 1.62 Official leaderboard
#ModelScoreSettingDateSource
1 InternVL2-8B 1.96 Jul 2024 Official leaderboard
2 LLaVA-OneVision 7B 1.94 Aug 2024 Official leaderboard
3 sharegpt4video-8b 1.85 May 2024 Official leaderboard
4 LLaVA-v1.5-13B 1.80 Oct 2023 Official leaderboard
5 LongVA-7B 1.79 Jun 2024 Official leaderboard
6 Video-LLaVA-7B 1.72 Nov 2023 Official leaderboard

Number one over time

Lab claims count from the day the card came out, independent runs from the model’s release.

Shanghai AI Lab
Benchmark paper Not tested since Oct 2024

Source: The VDC Benchmark paper

Scores over time

All the scores we have, one dot each, so a model tested at several settings appears more than once.

Plot with other benchmarks
In the benchmark’s paper
1.70 1.80 1.90 2.00 2024 1.70 1.80 1.90 2.00 2024

Source: Official VDC Benchmark 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

8 of 9 checks pass, 1 warning. Look first at the Newest score check. The newest came 2 years ago, in August 2024, for LLaVA-OneVision 7B. Every benchmark

Catalog record 2 pass
  • Pass Task access All tasks are public.
  • Pass Confidence Checked against a primary source.
Scores 1 warning 2 pass 2 notes
  • Pass Independent runs Scores from the benchmark’s paper (16 entries).
  • Pass Models scored 6 models we track, plus 10 other entries on its leaderboard.
  • Warning Newest score The newest came 2 years ago, in August 2024, for LLaVA-OneVision 7B.
  • Note Frontier models None of its models are on the capabilities index.
  • Note Headroom Scored as a plain number, with no fixed ceiling.
Leaderboard import 3 pass
  • Pass Importer We read the board on arxiv.org: 6 rows for models we track and 10 other entries at the last read.
  • 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