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

Qwen3.7 Plus Preview vs Qwen3 VL 4B (Reasoning)

AlibabavsAlibaba31 shared benchmarks310 head-to-head
BenchmarkQwen3.7 Plus PreviewQwen3 VL 4B (Reasoning)
AA Agentic Index20.814.4
AA Intelligence39.47.7
AA-LCR6923
AA-Omniscience2.4-68.4
Artificial Analysis Coding Index55.96.7
critpt9.10
ERQA69.847.3
gdpval22.213.8
GPQA Diamond90.364.1
HLE35.64.6
IFBench79.136.6
ifeval94.682.6
include8364.6
LiveCodeBench v689.651.3
LVBench76.253.5
mathvision90.360
mmlu_prox85.465
mmlu_redux94.586
MMLU-Pro88.573.6
MMMU-Pro80.557
OmniScience Accuracy22.512.2
OmniScience Non-Hallucination74.58.2
OSWorld-Verified73.331.4
RealWorldQA86.973.2
scicode51.317.1
screenspot_pro_no_tools7949.2
supergpqa71.446.8
Terminal-Bench Hard471.5
Video-MME8859.7
VideoMMMU85.469.4
τ²-Bench Telecom (AA run)9315.5

Best tracked score per model per benchmark (default configuration; source-attributed). ↓ marks lower-is-better metrics. Open either model for its full surface, provenance and pricing.