Codesota · Benchmark · MVBenchHome/Leaderboards/Vision & Documents/Video Understanding/MVBench
Unknown

MVBench.

Multi-task video understanding with 20 temporal reasoning tasks

Paper Leaderboard
§ 01 · SOTA history

Year over year.

§ 02 · Leaderboard

Results by metric.

Found a wrong score or missing run?
Use row edits to send a sourced correction into moderation.
Add / edit result Report issue

Accuracy

Accuracy is the reported evaluation metric for MVBench. Codesota tracks published model scores on this metric so readers can compare state-of-the-art results across sources and model families.

Higher is better

Trust tiers for Accuracyverifiedpapervendorcommunityunverified

Muted rows were not state of the art when published — an earlier or same-year result already scored better.

RankModelTrustScoreYearLinksFix
01Qwen3.5-Omni-Plusunverified792026Paper ↗Looks wrong?
02Qwen3.5-397B-A17Bunverified77.62026Paper ↗Code ↗Looks wrong?
03Qwen3.5-122B-A10Bunverified76.62026Paper ↗Code ↗Source ↗Looks wrong?
04Qwen3-VL-235B-A22B-Instructunverified76.52025Paper ↗Code ↗Looks wrong?
05Qwen3.6-27Bunverified75.52026Paper ↗Code ↗Looks wrong?
06LongCat-Flash-Omniunverified75.22025Paper ↗Code ↗Looks wrong?
07Qwen3-VL-235B-A22B-Thinkingunverified75.22025Paper ↗Code ↗Looks wrong?
08Qwen3.5-35B-A3Bunverified74.82026Paper ↗Code ↗Source ↗Looks wrong?
09Qwen3.6-35B-A3Bunverified74.62026Paper ↗Code ↗Looks wrong?
10Qwen3.5-27Bunverified74.62026Paper ↗Code ↗Source ↗Looks wrong?
11Qwen2-VL 72Bunverified73.62024Paper ↗Code ↗Looks wrong?
12Qwen2.5-VL-72Bunverified70.42025Paper ↗Code ↗Looks wrong?
13Ovis2.5-9Bunverified69.72025Paper ↗Code ↗Looks wrong?
14VideoLLaMA3 7Bunverified69.72025Paper ↗Code ↗Looks wrong?
15qwen2.5-vl-7bunverified69.62025Paper ↗Code ↗Looks wrong?
16Qwen3-VL-8B-Instructunverified68.72025Paper ↗Code ↗Looks wrong?
17Qwen2-VL 7Bunverified672024Paper ↗Code ↗Looks wrong?
18Qwen2.5-VL-3Bunverified672025Paper ↗Code ↗Looks wrong?
19LongVUunverified66.92024Paper ↗Code ↗Looks wrong?
20Qwen2-VL-2Bunverified63.22024Paper ↗Code ↗Looks wrong?
§ 04 · Submit a result

Add to the leaderboard.

← Back to Video Understanding