VECTOR WIREAI INTELLIGENCE
NVDA$1,847+3.2%MSFT$512+1.1%GOOGL$199-0.4%META$728+2.7%AMD$184-1.2%TSM$212+0.6%PLTR$98+4.1%AI IDX4,821+1.9%
PKT
SEEDRefresh Models Deals Regulatory Sources

MLVU

13 models tracked

MLVU (Multi-task Long Video Understanding) — Not merged w/ MLVU-MCQ (Acc) -- diff source/roster and MCQ-specific qualifier on the latter.

#ModelVendorBest scoreRunsLast seen
1Qwen3.7 Plus PreviewAlibaba87.412026-08-23
2Qwen3.5 122B A10BAlibaba87.312026-08-23
3Qwen3.5 397B A17BAlibaba86.712026-08-24
4Qwen3.6 PlusAlibaba86.712026-08-23
5Qwen3.6 27BAlibaba86.622026-08-24
6Qwen3.6 35B A3BAlibaba86.212026-08-23
7Qwen3.5 27BAlibaba85.922026-08-24
8Qwen3.5 35B A3BAlibaba85.612026-08-23
9Qwen3 VL 235B A22B InstructAlibaba84.312026-08-23
10Qwen3 VL 235B A22B ReasoningAlibaba83.812026-08-23
11Claude Opus 4.5Anthropic81.712026-08-24
12Gemini 3 ProGoogle80.712026-06-15
13Qwen3.5 9BAlibaba52.412026-06-15

Best tracked score per model (default configuration; source-attributed and verification-tiered). Open a model for its full benchmark surface, provenance and pricing.