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 Sonnet 4.6 vs Kimi K2 (Reasoning)

AnthropicvsMoonshot25 shared benchmarks241 head-to-head
BenchmarkClaude Sonnet 4.6Kimi K2 (Reasoning)
AA Agentic Index61.647.9
AA Intelligence48.433.5
AA-LCR7470.3
AA-Omniscience12.2-21.4
Artificial Analysis Coding Index6334.8
browsecomp76.260.2
critpt3.12.6
frontiermath_tier_48.30
gdpval54.824.5
GPQA (unspecified)89.974.2
GPQA Diamond89.984.5
HLE4923.9
HLE (with tools)46.844.9
IFBench56.668.1
OmniScience Accuracy40.930.9
OmniScience Non-Hallucination51.625.8
scicode4744.8
SWE-bench Verified79.671.3
Terminal-Bench 2.059.135.7
Terminal-Bench Hard59.131.1
vectara_answer_rate99.998.6
vectara_avg_summary_length114.759.2
vectara_factual_consistency89.482.1
vectara_hallucination_rate10.617.9
τ²-Bench Telecom (AA run)97.993

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.