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

Claude Opus 4.5 vs Qwen2.5 Instruct 72B

AnthropicvsAlibaba22 shared benchmarks211 head-to-head
BenchmarkClaude Opus 4.5Qwen2.5 Instruct 72B
AA Intelligence41.910
AA-LCR7620.3
AA-Omniscience14-52.2
Artificial Analysis Coding Index47.811.9
C-Eval92.289.2
critpt4.60
Fortress13.656.4
GPQA Diamond8749.1
HLE30.84.2
IFBench5836.9
livebench7652.3
LiveCodeBench8755.5
longbench_v264.439.4
mmlu_redux95.686.8
MMLU-Pro9071.6
mmmlu90.874.8
OmniScience Accuracy46.617.6
OmniScience Non-Hallucination3915.3
scicode5026.7
SWE-bench Verified81.523.8
Terminal-Bench Hard474.5
τ²-Bench Telecom (AA run)89.534.5

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.