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 Max vs Qwen3 VL 4B (Reasoning)

AlibabavsAlibaba22 shared benchmarks220 head-to-head
BenchmarkQwen3.7 MaxQwen3 VL 4B (Reasoning)
AA Agentic Index30.914.4
AA Intelligence46.77.7
AA-LCR74.723
AA-Omniscience13.5-68.4
Artificial Analysis Coding Index666.7
critpt13.40
gdpval38.513.8
GPQA Diamond92.464.1
HLE41.44.6
IFBench80.536.6
ifeval94.382.6
include86.264.6
LiveCodeBench v691.651.3
mmlu_prox8765
mmlu_redux9586
MMLU-Pro89.673.6
OmniScience Accuracy31.112.2
OmniScience Non-Hallucination74.48.2
scicode53.517.1
supergpqa73.646.8
Terminal-Bench Hard50.81.5
τ²-Bench Telecom (AA run)94.715.5

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.