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 o1

AnthropicvsOpenAI27 shared benchmarks243 head-to-head
BenchmarkClaude Opus 4.5o1
AA Agentic Index59.631.1
AA Intelligence41.924
AA-LCR7663.3
AA-Omniscience14-10.6
AIME 202592.881.7
Artificial Analysis Coding Index47.839.7
critpt4.60.3
Fortress13.619.4
gdpval47.311.5
GPQA Diamond8775.7
HLE30.87.7
IFBench5870.3
livebench7652.3
MathVista80.271.8
metr_hcast73.442.6
metr_re_bench400
metr_swaa99.5100
mmmlu90.887.7
MMMU80.777.6
OmniScience Accuracy46.634.7
OmniScience Non-Hallucination3930.7
scicode5035.8
SEAL VISTA46.445.3
simplebench6241.7
SWE-bench Verified81.548.9
Terminal-Bench Hard4712.9
τ²-Bench Telecom (AA run)89.562.6

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.