GOESB

GOESB — Global Open Edge Speech Benchmark · pronounced “goose-bee”

Leaderboard

Objective, reproducible benchmarks for local (edge) speech AI. Every result here re-verified its hash and signature before being accepted — see why you can trust the numbers. New here? Read the docs.

This is every verified result, filterable and sortable. Looking for a single best recommendation for your constraints instead? Try the homepage →

ConcurrencyLoad results only — how RTF/throughput hold up under N simultaneous requests, not accuracy.

RTF vs Concurrency level

0.000.250.500.751.001248RTFConcurrency level
nvidia-rtx-5090 · cuda · faster-whisper/whisper-basenvidia-rtx-5090 · cuda · faster-whisper/whisper-large-v3nvidia-rtx-5090 · cuda · faster-whisper/whisper-mediumnvidia-rtx-5090 · cuda · faster-whisper/whisper-smallnvidia-rtx-5090 · cuda · faster-whisper/whisper-tinyClick points to see full details