OpenAI GPT 4.1 mini
By OpenAI
Live
Model Type
Large Language Model
Parameters
Proprietary
Model Controls
Model Evaluation
Benchmarks
Benchmarks included in the evaluation of this model
MMLU
Evaluates knowledge across subjects including STEM, humanities, and more
HumanEval
Tests code generation ability
MGSM
Evaluates mathematical problem-solving and reasoning skills
Model Red Team Coverage
