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

DeepSeek-R1 vs GPT-4o mini

DeepSeekvsOpenAI29 shared benchmarks272 head-to-head
BenchmarkDeepSeek-R1GPT-4o mini
AA Agentic Index3.11
AA Intelligence18.67
aider_polyglot71.63.6
AIR-Bench 202452.956.3
anthropic_red_team99.198.3
ARC-AGI-21.30
Artificial Analysis Coding Index24.611.4
bbq96.688.2
Fortress74.448.1
gdpval1.50
GPQA Diamond8142.6
harmbench54.684.9
HLE17.74.2
IFBench3931
LiveCodeBench84.435.5
livecodebench_easy99.281.7
livecodebench_hard63.64.3
livecodebench_medium90.925.2
MATH97.380.2
mmlu92.981.8
scicode35.722.9
simple_safety_tests98.397.8
simplebench40.810.7
simpleqa92.39.9
SWE-bench Verified57.68.7
TauBench V3 - Banking6.42.9
Terminal-Bench 2.119.15.6
xstest98.896
τ³-Bench6.42.9

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.