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 Opus 4.6 vs Kimi K3

AnthropicvsMoonshot42 shared benchmarks933 head-to-head
BenchmarkClaude Opus 4.6Kimi K3
AA Agentic Index67.654.3
AA Intelligence44.960
AA-LCR74.382.7
AA-Omniscience13.746
aime_202696.796.7
apexAgents3341.3
arc_agi_19365.7
ARC-AGI-268.812.4
arena_elo14971489
arena_text_factuality14871471
Artificial Analysis Coding Index48.176.2
baby_vision14.885.7
baby_vision_with_python38.485.7
browsecomp86.891.2
charxiv_rq69.184.8
coding_arena_elo15451674
critpt12.623.4
cybergym73.880
deepsearchqa_f191.395
gdpval55.959.4
GPQA Diamond91.393.5
HLE53.156
hmmt_feb_202696.297
livebench_agentic_coding4962.2
livebench_coding78.281.5
livebench_data_analysis69.978.7
livebench_instruction_following63.371.4
livebench_language83.385.5
livebench_math89.384.4
livebench_reasoning88.790.7
matharena_visual_math_overall72.391.3
mathvision71.297.8
MCP Atlas76.884.2
MMMU-Pro77.383.4
officeqa_pro57.163.3
OmniScience Accuracy4747.6
OmniScience Non-Hallucination37.249.1
OSWorld-Verified72.784.8
scicode5258.7
simplebench67.660.7
simpleqa_verified46.542.7
toolathlon56.873.2

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.