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

Kimi K2 (Reasoning) vs Qwen2.5 Instruct 72B

MoonshotvsAlibaba19 shared benchmarks190 head-to-head
BenchmarkKimi K2 (Reasoning)Qwen2.5 Instruct 72B
AA Intelligence33.510
AA-LCR70.320.3
AA-Omniscience-21.4-52.2
aider_polyglot59.17.6
Artificial Analysis Coding Index34.811.9
critpt2.60
GPQA Diamond84.549.1
HLE23.94.2
IFBench68.136.9
LiveCodeBench79.255.5
longbench_v245.139.4
mmlu_redux94.486.8
MMLU-Pro84.671.6
OmniScience Accuracy30.917.6
OmniScience Non-Hallucination25.815.3
scicode44.826.7
SWE-bench Verified71.323.8
Terminal-Bench Hard31.14.5
τ²-Bench Telecom (AA run)9334.5

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.