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 4.8 vs Kimi K2 (Reasoning)

AnthropicvsMoonshot27 shared benchmarks261 head-to-head
BenchmarkClaude Opus 4.8Kimi K2 (Reasoning)
AA Agentic Index49.447.9
AA Intelligence57.333.5
AA-LCR7370.3
AA-Omniscience28.8-21.4
Artificial Analysis Coding Index74.334.8
browsecomp88.560.2
critpt20.92.6
frontiermath_tier_431.30
gdpval54.224.5
GPQA Diamond93.684.5
HealthBench59.358
HLE57.923.9
HLE (with tools)57.944.9
hmmt_nov_202596.589.2
IFBench62.268.1
imo_answer_bench83.578.6
longbench_v269.145.1
OmniScience Accuracy48.830.9
OmniScience Non-Hallucination60.725.8
ResearchRubrics73.556.2
scicode53.544.8
simplebench64.839.6
SWE-bench Multilingual84.461.1
SWE-bench Verified88.671.3
Terminal-Bench 2.074.635.7
Terminal-Bench Hard58.331.1
τ²-Bench Telecom (AA run)94.493

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.