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

Gemini 3.1 Pro vs Qwen2.5 Instruct 72B

GooglevsAlibaba22 shared benchmarks211 head-to-head
BenchmarkGemini 3.1 ProQwen2.5 Instruct 72B
AA Intelligence47.710
AA-LCR7920.3
AA-Omniscience32.9-52.2
Artificial Analysis Coding Index68.811.9
Chinese SimpleQA (C-SimpleQA)85.952.2
Codeforces305224.8
critpt17.70
Fortress29.856.4
GPQA Diamond94.349.1
HLE51.44.2
IFBench77.136.9
livebench79.952.3
LiveCodeBench91.755.5
mmlu92.686.1
MMLU-Pro9171.6
mmmlu92.674.8
OmniScience Accuracy55.317.6
OmniScience Non-Hallucination50.115.3
scicode5926.7
SWE-bench Verified80.623.8
Terminal-Bench Hard68.54.5
τ²-Bench Telecom (AA run)99.334.5

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.