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 vs GPT-4o mini

AnthropicvsOpenAI30 shared benchmarks291 head-to-head
BenchmarkClaude Sonnet 4GPT-4o mini
AA Agentic Index39.21
AA Intelligence29.87
aider_polyglot70.73.6
AIR-Bench 202488.356.3
anthropic_red_team99.298.3
ARC-AGI-213.60
Artificial Analysis Coding Index37.611.4
bbq97.988.2
Fortress24.448.1
gdpval31.20
GPQA Diamond7842.6
harmbench9884.9
HLE10.74.2
IFBench5531
LiveCodeBench68.535.5
livecodebench_easy98.881.7
livecodebench_hard32.64.3
livecodebench_medium7625.2
mmlu91.581.8
MMMU74.459.4
MMMU-Pro62.441.5
scicode4022.9
simple_safety_tests10097.8
simplebench45.510.7
simpleqa15.99.9
SWE-bench Verified80.28.7
TauBench V3 - Banking16.72.9
Terminal-Bench 2.136.35.6
xstest97.296
τ³-Bench13.82.9

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.