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

o4-mini vs Qwen2.5 Instruct 72B

OpenAIvsAlibaba24 shared benchmarks185 head-to-head
Benchmarko4-miniQwen2.5 Instruct 72B
AA Intelligence26.110
AA-LCR6020.3
AA-Omniscience-35.7-52.2
aider_polyglot727.6
AIR-Bench 202478.559
anthropic_red_team98.299.6
Artificial Analysis Coding Index25.611.9
bbq9495.4
critpt0.60
Fortress21.556.4
GPQA Diamond81.449.1
GSM8K095.8
harmbench9772.8
HLE16.54.2
IFBench68.736.9
LiveCodeBench84.555.5
OmniScience Accuracy24.817.6
OmniScience Non-Hallucination19.515.3
scicode46.526.7
simple_safety_tests100100
SWE-bench Verified68.123.8
Terminal-Bench Hard15.24.5
xstest97.497.9
τ²-Bench Telecom (AA run)55.634.5

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.