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 GPT-4o mini

AnthropicvsOpenAI22 shared benchmarks211 head-to-head
BenchmarkClaude Sonnet 4.5GPT-4o mini
AA Agentic Index50.61
AA Intelligence37.47
AI2D8775.2
AIR-Bench 202489.856.3
ARC-AGI-213.60
Artificial Analysis Coding Index52.111.4
Fortress1748.1
gdpval40.40
GPQA Diamond83.442.6
HLE19.84.2
IFBench57.331
LiveCodeBench7135.5
MathVista79.856.7
MMMU79.659.4
MMMU (val) (Pass@1)77.852.1
MMMU-Pro68.741.5
scicode4522.9
simplebench54.310.7
SWE-bench Verified828.7
TauBench V3 - Banking24.52.9
Terminal-Bench 2.155.85.6
τ³-Bench192.9

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.