Benchmark Almanac

Hume AI

We track 4 benchmarks and 2 arenas that Hume AI made or helped make.

2 in use 2 with public code 1 with a leaderboard here

Benchmarks

Name Kind Released Best score Status
Real World VoiceEQ Voice systems recognize, produce and respond to acoustic information across speech recognition, speech to speech, speech understanding and text to speech tasks. Audio understanding and voice Jul 2026 0.92 Not in cards
Voice Controllability Leaderboard Text to speech systems create requested voices and follow delivery, emotion and role instructions. Blind human ratings and objective prosody measures score controllability. Speech recognition and translation Sep 2026 71.4 Not in cards
Voice Replication Leaderboard Text to speech systems reproduce reference speakers from short recordings. Human ratings score speaker identity, quality and naturalness, with an objective speaker similarity check. Speech recognition and translation Sep 2026 3.53 Not in cards
ACII DaiKon Challenge Models predict interpersonal influence, turn taking and rapport trajectories from multimodal dyadic conversations across five languages. Audio understanding and voice May 2026 Not in cards

Arenas

Name Kind Released Best score Status
Hume AI Overall Quality Index Listeners rate generated speech on reliability and expressiveness. The benchmark reports an overall quality index. Speech recognition and translation Sep 2026 0.9 In use
Hume AI Voice Design Benchmark Listeners rate generated voices for English voice design, multilingual control, accents and voice qualities. Speech recognition and translation Sep 2026 71.4 In use