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 —

MMMU (val) (Pass@1)

30 models tracked

MMMU (Massive Multi-discipline Multimodal Understanding) — Same val/Pass@1 concept as MMMU, disjoint source family + lower band; kept separate.

#ModelVendorBest scoreRunsLast seen
1Qwen3 VL 235B A22B ReasoningAlibaba80.612026-08-23
2Qwen3 VL 235B A22B InstructAlibaba78.712026-08-23
3Qwen3 VL 32B ReasoningAlibaba78.112026-08-23
4Claude Sonnet 4.5Anthropic77.812026-08-23
5Qwen3 VL 32B InstructAlibaba7612026-08-23
6Qwen3 VL 30B A3B ReasoningAlibaba7612026-08-23
7Qwen3 VL 30B A3B InstructAlibaba74.212026-08-23
8Qwen3 VL Thinking (8B)Alibaba74.112026-08-23
9Qwen3 VL 4B (Reasoning)Alibaba70.812026-08-23
10Qwen3 VL 8B InstructAlibaba69.612026-08-23
11GPT-4oOpenAI69.112026-08-24
12Claude 3.5 SonnetAnthropic68.322026-08-24
13Qwen3 VL 4B InstructAlibaba67.412026-08-23
14Gemma 3 27BGoogle64.912026-08-23
15Qwen2-VL-72B-InstructAlibaba64.522026-08-24
16Gemma 3 12BGoogle59.612026-08-23
17Gemini 1.5 ProGoogle54.112026-08-24
18GPT-4o miniOpenAI52.112026-08-24
19Gemma 3 4BGoogle48.812026-08-23
20LFM2.5-VL-3BLiquid AI48.422026-08-23
21InternVL-2-8BOpenGVLab46.312026-08-24
22LFM2-VL-3BLiquid AI45.612026-08-22
23InternVL-2-4BOpenGVLab44.212026-08-24
24Phi 3.5 Vision InstructMicrosoft4312026-08-24
25InternVL3.5-1BOpenGVLab41.912026-08-09
26LFM2.5-VL-1.6BLiquid AI40.612026-08-09
27LFM2-VL-1.6BLiquid AI39.712026-08-09
28LFM2-VL-450MLiquid AI34.412026-08-09
29North-Micro-Vision-InstructCohere32.912026-08-23
30LFM2.5-VL-450M-ExtractLiquid AI32.712026-08-09

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