Humanlike AIThe model index

Side by side

GPT-6 vs Gemini 3.5

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

OpenAI logo
GPT-6
OpenAI
Google logo
Gemini 3.5
Google
Cost of talking
Per minute$0.012Estimate$0.0083Estimate
Per hour$0.698$0.499
30-min interview$0.349$0.249
List price$1.75 / $14 per 1MEstimate$1.25 / $10 per 1MEstimate
Recruitment fit
Overall93/10084/100
VerdictThe strongest general model for hiring work — but only worth its price on the judgement-heavy steps, not on parsing.The cheapest credible way to process raw interview recordings without a separate transcription step.
Best for
Structured interview scoring against a rubricComparing a shortlist against a job specDrafting candidate feedback that a human will edit
Interview recording analysisMultilingual pipelinesBulk CV parsing
Watch out for
  • Max effort is roughly 24× the cost of Mini — do not point bulk CV parsing at it
  • A frontier model is not a fairness guarantee: you still need audited rubrics and a human on the shortlist
  • Pricing is unpublished, so total cost of ownership is unmodellable today
  • Reasoning trails Opus 5 and GPT-6 on rubric consistency
Capabilities
Modalitiestext, audiotext, audio, video
Context window400K1,000K
VariantsMax effort, High, Medium, Low, MiniPro, Flash, Flash-Lite
On HumanLikeNot yetCoworker
HumanLike evals
CV field extraction (F1)0.94Estimate—
Time to first token (medium effort)640 msEstimate—
Greek transcription WER (Live sibling)—0.03Our eval
Published benchmarks
MMLU-ProTBDEstimate—
SWE-bench VerifiedTBDEstimate—

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