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 4.5 vs Kimi K3

AnthropicvsMoonshot40 shared benchmarks634 head-to-head
BenchmarkClaude Opus 4.5Kimi K3
AA Agentic Index59.654.3
AA Intelligence41.960
AA-LCR7682.7
AA-Omniscience1446
aime_202695.196.7
arc_agi_18265.7
ARC-AGI-237.612.4
arena_elo14731489
arena_text_factuality14581471
Artificial Analysis Coding Index47.876.2
browsecomp3791.2
charxiv_rq68.584.8
coding_arena_elo14951674
critpt4.623.4
cybergym50.680
deepsearchqa_f176.195
gdpval47.359.4
GPQA Diamond8793.5
HLE30.856
hmmt_feb_202685.397
livebench_agentic_coding39.762.2
livebench_coding79.781.5
livebench_data_analysis74.478.7
livebench_instruction_following62.571.4
livebench_language81.385.5
livebench_math90.484.4
livebench_reasoning80.190.7
mathvision77.197.8
MCP Atlas69.884.2
MMMU-Pro7483.4
MMVU77.382.1
OmniScience Accuracy46.647.6
OmniScience Non-Hallucination3949.1
OSWorld-Verified66.384.8
scicode5058.7
simplebench6260.7
simpleqa_verified41.842.7
toolathlon43.573.2
WorldVQA36.851
ZeroBench30.4

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.