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 3.5 Sonnet vs Kimi K2 (Reasoning)

AnthropicvsMoonshot16 shared benchmarks114 head-to-head
BenchmarkClaude 3.5 SonnetKimi K2 (Reasoning)
AA Intelligence1033.5
aider_polyglot45.359.1
AIME 20257.494.5
Artificial Analysis Coding Index30.234.8
frontiermath_tier_400
GPQA Diamond67.284.5
HLE3.923.9
hmmt_feb_20251.793.3
LiveCodeBench32.879.2
LiveCodeBench v637.283.1
longbench_v24145.1
mmlu_redux88.994.4
MMLU-Pro7884.6
scicode36.644.8
simplebench41.439.6
SWE-bench Verified50.871.3

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.