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 K2.6 vs Kimi K2 (Reasoning)

MoonshotvsMoonshot29 shared benchmarks290 head-to-head
BenchmarkKimi K2.6Kimi K2 (Reasoning)
AA Agentic Index58.747.9
AA Intelligence45.133.5
AA-LCR76.770.3
AA-Omniscience6.4-21.4
Artificial Analysis Coding Index61.834.8
browsecomp86.360.2
critpt82.6
frontiermath_tier_414.60
gdpval41.424.5
GPQA Diamond91.184.5
HLE37.523.9
HLE (with tools)5444.9
IFBench7668.1
imo_answer_bench8678.6
LiveCodeBench89.679.2
LiveCodeBench v689.683.1
MMLU-Pro87.184.6
OmniScience Accuracy32.830.9
OmniScience Non-Hallucination60.725.8
scicode53.544.8
SWE-bench Multilingual76.761.1
SWE-bench Verified80.271.3
Terminal-Bench 2.066.735.7
Terminal-Bench Hard43.931.1
vectara_answer_rate99.798.6
vectara_avg_summary_length116.759.2
vectara_factual_consistency89.282.1
vectara_hallucination_rate10.817.9
τ²-Bench Telecom (AA run)95.993

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.