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 Qwen3.7 Max

MoonshotvsAlibaba27 shared benchmarks225 head-to-head
BenchmarkKimi K2 (Reasoning)Qwen3.7 Max
AA Agentic Index47.930.9
AA Intelligence33.546.7
AA-LCR70.374.7
AA-Omniscience-21.413.5
Artificial Analysis Coding Index34.866
critpt2.613.4
gdpval24.538.5
GPQA Diamond84.592.4
HealthBench5854.5
HLE23.941.4
HLE (with tools)44.953.5
hmmt_nov_202589.295
IFBench68.180.5
imo_answer_bench78.690
LiveCodeBench v683.191.6
longbench_v245.165.3
mmlu_redux94.495
MMLU-Pro84.689.6
OmniScience Accuracy30.931.1
OmniScience Non-Hallucination25.874.4
scicode44.853.5
simplebench39.670.4
SWE-bench Multilingual61.178.3
SWE-bench Verified71.380.4
Terminal-Bench 2.035.769.7
Terminal-Bench Hard31.150.8
τ²-Bench Telecom (AA run)9394.7

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.