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 Sonnet 4.5 vs o1

AnthropicvsOpenAI26 shared benchmarks233 head-to-head
BenchmarkClaude Sonnet 4.5o1
AA Agentic Index50.631.1
AA Intelligence37.424
AA-LCR68.363.3
AA-Omniscience-0.1-10.6
AIME 20258881.7
AIR-Bench 202489.880
Artificial Analysis Coding Index52.139.7
critpt1.10.3
Fortress1719.4
gdpval40.411.5
GPQA Diamond83.475.7
HLE19.87.7
IFBench57.370.3
MathVista79.871.8
mmmlu89.187.7
MMMU79.677.6
OmniScience Accuracy32.934.7
OmniScience Non-Hallucination50.930.7
scicode4535.8
SEAL VISTA48.845.3
simplebench54.341.7
SWE-bench Verified8248.9
TAU-bench (airline)7050
TAU-bench (retail)86.270.8
Terminal-Bench Hard35.612.9
τ²-Bench Telecom (AA run)78.162.6

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.