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

GPT-5.4 vs Qwen2.5 Instruct 72B

OpenAIvsAlibaba17 shared benchmarks170 head-to-head
BenchmarkGPT-5.4Qwen2.5 Instruct 72B
AA Intelligence53.110
AA-LCR77.720.3
AA-Omniscience5.8-52.2
Artificial Analysis Coding Index71.111.9
Chinese SimpleQA (C-SimpleQA)76.852.2
Codeforces316824.8
critpt23.40
GPQA Diamond9349.1
HLE43.74.2
IFBench73.936.9
livebench80.352.3
MMLU-Pro87.571.6
OmniScience Accuracy50.917.6
OmniScience Non-Hallucination17.415.3
scicode56.626.7
Terminal-Bench Hard57.64.5
τ²-Bench Telecom (AA run)87.134.5

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.