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 5 vs Kimi K3

AnthropicvsMoonshot34 shared benchmarks331 head-to-head
BenchmarkClaude Sonnet 5Kimi K3
AA Agentic Index49.754.3
AA Intelligence55.360
AA-LCR7782.7
AA-Omniscience16.446
arena_elo14631489
arena_text_factuality14531471
Artificial Analysis Coding Index71.576.2
browsecomp84.791.2
charxiv_rq7784.8
coding_arena_elo15401674
critpt16.923.4
DeepSWE 1.15469
gdpval54.859.4
GDPval-AA v216181687
GPQA Diamond91.193.5
HLE57.456
livebench_agentic_coding59.462.2
livebench_coding80.781.5
livebench_data_analysis71.778.7
livebench_instruction_following63.971.4
livebench_language7585.5
livebench_math92.984.4
livebench_reasoning88.790.7
MMMU-Pro77.383.4
officeqa_pro59.463.3
OmniScience Accuracy4047.6
OmniScience Non-Hallucination60.649.1
OSWorld-Verified81.284.8
scicode53.658.7
simplebench60.660.7
simpleqa_verified2542.7
TauBench V3 - Banking37.346
Terminal-Bench 2.180.588.3
toolathlon54.373.2

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.