Humanlike AIThe model index

Side by side

Gemini 3.5 vs Claude Opus 5

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

Google logo
Gemini 3.5
Google
Anthropic logo
Claude Opus 5
Anthropic
Cost of talking
Per minute$0.0083Estimate$0.096Estimate
Per hour$0.499$5.76
30-min interview$0.249$2.88
List price$1.25 / $10 per 1MEstimate$15 / $75 per 1MEstimate
Recruitment fit
Overall84/10091/100
VerdictThe cheapest credible way to process raw interview recordings without a separate transcription step.The best choice for rubric-based scoring, where consistency across a batch matters more than peak score.
Best for
Interview recording analysisMultilingual pipelinesBulk CV parsing
Structured scoringBias-audit passes over model outputCandidate feedback drafting
Watch out for
  • Reasoning trails Opus 5 and GPT-6 on rubric consistency
  • Opus pricing makes it unsuitable for first-pass parsing
  • Use Haiku for the cheap steps
Capabilities
Modalitiestext, audio, videotext
Context window1,000K200K
VariantsPro, Flash, Flash-LiteOpus 5, Sonnet 5, Haiku 4.5
On HumanLikeCoworkerNot yet
HumanLike evals
Greek transcription WER (Live sibling)0.03Our eval—

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