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 3.7 Sonnet vs Kimi K2.5

AnthropicvsMoonshot28 shared benchmarks325 head-to-head
BenchmarkClaude 3.7 SonnetKimi K2.5
AA Agentic Index3752.8
AA Intelligence27.636
AA-LCR62.373
AA-Omniscience-0.7-7.3
AIME 202554.896.1
arc_agi_113.665.3
ARC-AGI-2011.8
arena_vision11951247
Artificial Analysis Coding Index36.446.8
critpt0.93.1
Fortress3841.1
gdpval27.438.3
GPQA Diamond84.887.9
HLE9.750.2
hmmt_feb_202531.795.4
IFBench48.370.2
MMMU-Pro60.178.5
multichallenge51.661.4
MultiNRC27.835.2
OmniScience Accuracy28.235.2
OmniScience Non-Hallucination6050
scicode40.349
SEAL VISTA48.241.9
simplebench46.446.8
swe_bench_bash52.870.8
SWE-bench Verified70.376.8
Terminal-Bench Hard21.234.8
τ²-Bench Telecom (AA run)54.795.9

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.