Side by side

GPT-3.5 Turbo vs GPT-4

Up to 4 models, normalised onto the same cost basis and scored through the lens you pick.

Cost of talking
Per minute$0.0031$0.062
Per hour$0.187$3.75
30-min interview$0.094$1.87
List price$0.5 / $1.5 per 1MPublished$10 / $30 per 1MPublished
Recruitment fit
Overall22/10048/100
VerdictDo not screen candidates with this. Its judgement is not good enough to put in front of a hiring decision.Historic interest only — cheaper current models beat it on both quality and cost.
Best for
Nothing candidate-facing
Nothing new. Migrate existing pipelines.
Watch out for
  • 16K context cannot hold a full CV plus a job spec plus a rubric
  • Materially higher error rate on structured extraction
  • Costs more than GPT-5.6 while performing worse
Capabilities
Modalitiestexttext
Context window16.385K128K
VariantsTurbo (16K), InstructBase (8K), Turbo (128K), 32K
On HumanLikeNot yetNot yet
Published benchmarks
MMLU70%Published86.4%Published

Cost per hour assumes 150 wpm and a 40% AI speaking share. Hover a figure for its full derivation.