Recent studyBlind TTS Elo is live. Compare two anonymous voice samples, vote after listening, and help separate real preference signal from noise.Vote in the study ->
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
RankModelTrustScoreYearLinksEdit
01Qwen3.5-Omni-Plusunverified792026Paper ↗Edit result
02Qwen3.5-397B-A17Bunverified77.62026Paper ↗Code ↗Edit result
03Qwen3.5-122B-A10Bunverified76.62026Paper ↗Code ↗Source ↗Edit result
04Qwen3-VL-235B-A22B-Instructunverified76.52025Paper ↗Code ↗Edit result
05Qwen3.6-27Bunverified75.52026Paper ↗Code ↗Edit result
06LongCat-Flash-Omniunverified75.22025Paper ↗Code ↗Edit result
07Qwen3-VL-235B-A22B-Thinkingunverified75.22025Paper ↗Code ↗Edit result
08Qwen3.5-35B-A3Bunverified74.82026Paper ↗Code ↗Source ↗Edit result
09Qwen3.6-35B-A3Bunverified74.62026Paper ↗Code ↗Edit result
10Qwen3.5-27Bunverified74.62026Paper ↗Code ↗Source ↗Edit result
11Qwen2-VL 72Bunverified73.62024Paper ↗Code ↗Edit result
12Qwen2.5-VL-72Bunverified70.42025Paper ↗Code ↗Edit result
13Ovis2.5-9Bunverified69.72025Paper ↗Code ↗Edit result
14VideoLLaMA3 7Bunverified69.72025Paper ↗Code ↗Edit result
15qwen2.5-vl-7bunverified69.62025Paper ↗Code ↗Edit result
16Qwen3-VL-8B-Instructunverified68.72025Paper ↗Code ↗Edit result
17Qwen2-VL 7Bunverified672024Paper ↗Code ↗Edit result
18Qwen2.5-VL-3Bunverified672025Paper ↗Code ↗Edit result
19LongVUunverified66.92024Paper ↗Code ↗Edit result
20Qwen2-VL-2Bunverified63.22024Paper ↗Code ↗Edit result
§ 04 · Submit a result

Add to the leaderboard.

← Back to Video Understanding