VECTOR WIREAI INTELLIGENCE
⌘K
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 —

LVBench

29 models tracked

LVBench (long video understanding) — Distinct benchmark from LongVideoBench despite similar naming/domain.

#ModelVendorBest scoreRunsLast seen
1Gemini 3.7 FlashGoogle85.432026-08-24
2Gemini 3.6 FlashGoogle84.212026-08-14
3Qwen3.8 Max PreviewAlibaba81.812026-08-23
4GPT-5.6 TerraOpenAI78.912026-08-14
5Qwen3.7 Plus PreviewAlibaba76.212026-08-23
6Kimi K2.5Moonshot75.922026-08-23
7Qwen3.5 122B A10BAlibaba74.412026-08-23
8Qwen3.5 27BAlibaba73.612026-08-23
9Gemini 3 ProGoogle73.512026-06-15
10Qwen3.5 35B A3BAlibaba71.412026-08-23
11Qwen3.6 35B A3BAlibaba71.412026-08-23
12Claude Sonnet 5Anthropic68.512026-08-14
13Qwen3 VL 235B A22B InstructAlibaba67.712026-08-23
14Qwen3 VL 32B InstructAlibaba63.812026-08-23
15Qwen3 VL 235B A22B ReasoningAlibaba63.622026-08-23
16Qwen3 VL 32B ReasoningAlibaba62.612026-08-23
17Qwen3 VL 30B A3B InstructAlibaba62.512026-08-23
18Qwen3 VL 30B A3B ReasoningAlibaba59.212026-08-23
19Qwen3 VL 8B InstructAlibaba5812026-08-23
20Qwen3 VL 4B InstructAlibaba56.212026-08-23
21Qwen3 VL Thinking (8B)Alibaba55.812026-08-23
22Qwen3 VL 4B (Reasoning)Alibaba53.522026-08-23
23Qwen2.5 VL 32BAlibaba4912026-08-23
24Qwen2.5 VL 72BAlibaba47.322026-08-23
25Mage-VL-4BMicrosoft41.812026-07-26
26Nova Pro (Non-Reasoning)Amazon41.612026-08-23
27Nova Lite (Non-Reasoning)Amazon40.412026-08-23
28Phi 4 R V 15BMicrosoft34.412026-07-26
29Phi 4 MM 5.6BMicrosoft25.312026-07-26

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