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 K3 vs Opus 5

MoonshotvsAnthropic37 shared benchmarks1224 head-to-head
BenchmarkKimi K3Opus 5
AA Agentic Index54.359.2
AA Intelligence6063.1
AA-LCR82.778.7
AA-Omniscience4637.1
arc_agi_165.797.5
ARC-AGI-212.490.4
arena_elo14891487
arena_text_factuality14711481
Artificial Analysis Coding Index76.278
browsecomp91.290.8
coding_arena_elo16741662
critpt23.429.1
DeepSWE 1.16968.8
Finance Agent v254.458.6
gdpval59.467.2
GDPval-AA v216871861
GPQA Diamond93.593.7
HLE5664.7
livebench_agentic_coding62.265.2
livebench_coding81.581.5
livebench_data_analysis78.774.5
livebench_instruction_following71.463.8
livebench_language85.588.7
livebench_math84.495.7
livebench_reasoning90.791.2
MCP Atlas84.285.8
MMMU-Pro83.484.7
officeqa_pro63.366.9
OmniScience Accuracy47.660.9
OmniScience Non-Hallucination49.140.5
OSWorld 2.058.370.6
OSWorld-Verified84.84
scicode58.755.7
simplebench60.780.6
simpleqa_verified42.756.7
TauBench V3 - Banking4644.7
Terminal-Bench 2.188.389.1

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.