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

DeepSeek-R1 vs Kimi K2 (Reasoning)

DeepSeekvsMoonshot34 shared benchmarks826 head-to-head
BenchmarkDeepSeek-R1Kimi K2 (Reasoning)
AA Agentic Index3.147.9
AA Intelligence18.633.5
AA-LCR5670.3
AA-Omniscience-31.3-21.4
aider_polyglot71.659.1
AIME 202587.594.5
Artificial Analysis Coding Index24.634.8
browsecomp8.960.2
browsecomp_zh35.762.3
critpt0.62.6
gdpval1.524.5
GPQA Diamond8184.5
HLE17.723.9
HMMT 202579.489.4
hmmt_feb_202576.793.3
IFBench3968.1
LiveCodeBench84.479.2
longbench_v258.345.1
mmlu_redux93.494.4
MMLU-Pro8584.6
multichallenge4566.4
OmniScience Accuracy30.730.9
OmniScience Non-Hallucination10.525.8
scicode35.744.8
simplebench40.839.6
SWE-bench Multilingual30.561.1
SWE-bench Verified57.671.3
Terminal-Bench5.747.1
Terminal-Bench Hard6.131.1
vectara_answer_rate9798.6
vectara_avg_summary_length93.559.2
vectara_factual_consistency88.782.1
vectara_hallucination_rate11.317.9
τ²-Bench Telecom (AA run)11.493

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.