Side by side

See the difference.

Scores, capabilities and costs for the models you’re considering.

Scroll to compare models →

Comparison of Nemotron-3-Diarization, drex-v2.0, abr-ai/niagara-84m-batch.en
3 modelsnvidiaNemotron-3-DiarizationRemove ×nace-aidrex-v2.0Remove ×abr-aiabr-ai/niagara-84m-batch.enRemove ×
What’s differentNemotron 3 Diarization is an open-weight streaming Sortformer model, engineered for low-latency speaker diarization across up to 8 speakers, ordered by arrival time. It powers meeting transcription, call…Drex v2.0 is a 35B mixture-of-experts decision model (3B active) from Nace.AI. Given a state (text or JSON) and typed questions (yes/no, multiple choice, or ordinal score), it returns a calibrated…0.084B parameters · 1 language · Encoder: State-space model · Decoder: CTC
DateSep 25, 2026ListedOct 8, 2026ListedOct 17, 2026Discovered
Listed rate$0.00001/ secondDeepInfra · all routes ↗Input audio second$0.06 in / $0.00 out/ 1M tokensDeepInfra · all routes ↗See provider quotes
Provider endpoints1 endpoint →1 endpoint →0 endpoints →
AMI-Cleaned WER ↗English short-form; normalization unversionedNot reportedNot reported12.01% WER ↗abr-ai/niagara-84m-batch.enLeaderboard entry
Earnings22-Cleaned-AA-chunked WER ↗English short-form; normalization unversionedNot reportedNot reported10.83% WER ↗abr-ai/niagara-84m-batch.enLeaderboard entry
Gigaspeech-Cleaned WER ↗English short-form; normalization unversionedNot reportedNot reported10.41% WER ↗abr-ai/niagara-84m-batch.enLeaderboard entry
LS Clean WER ↗English short-form; normalization unversionedNot reportedNot reported3.09% WER ↗abr-ai/niagara-84m-batch.enLeaderboard entry
LS Other WER ↗English short-form; normalization unversionedNot reportedNot reported7.6% WER ↗abr-ai/niagara-84m-batch.enLeaderboard entry
SPGISpeech WER ↗English short-form; normalization unversionedNot reportedNot reported2.61% WER ↗abr-ai/niagara-84m-batch.enLeaderboard entry
URGENT2024 WER ↗English short-form; normalization unversionedNot reportedNot reported20.16% WER ↗abr-ai/niagara-84m-batch.enLeaderboard entry
Voice Arena Monsoon WER ↗English short-form; normalization unversionedNot reportedNot reported8.82% WER ↗abr-ai/niagara-84m-batch.enLeaderboard entry
Voxpopuli-AA-Cleaned WER ↗English short-form; normalization unversionedNot reportedNot reported4.33% WER ↗abr-ai/niagara-84m-batch.enLeaderboard entry
Context window—131.1K—
Max output———
Parameters——0.084B
Audio inputNot reportedNot reportedSupported
TranscriptionNot reportedNot reportedSupported

Add another model

Search all models →