LibriSpeech WERactiveAudio
LibriSpeech WER: LibriSpeech WER (test-clean)
Metric: WER (%) (lower is better)Introduced: 2015
Word Error Rate on the LibriSpeech test-clean benchmark, using read English speech from audiobooks. The industry's long-standing clean-speech baseline for ASR; top models now reach sub-2% WER. Lower is better.
Models ranked
2
tracked on this benchmark
Score band
1.3 – 1.3
best → lowest tracked
Snapshot trend
+0.08
Mar 7 → Apr 30 · 1 models
Leaderboard
Tracked models ranked by WER (%) (lower is better).
#Model variant and provenanceRelative to leaderScore
1
Cohere Transcribe (03-2026)
1.3Version: test-cleanHarness: Not recordedEvaluator: Not recordedObserved: Mar 7, 2026Confidence: Not recordedSource
2
Granite Speech 4.1 2B
1.3Version: test-cleanHarness: Not recordedEvaluator: Not recordedObserved: Apr 30, 2026Confidence: Not recordedSource
How to read this benchmark
This benchmark scores models where lower is better. Use scores for directional filtering and shortlisting, not universal quality ranking; then validate pricing, context window, provider availability, and fit for your workload.
Trust this score when
- There is a fresh timestamped snapshot (or multiple snapshots) for this benchmark.
- The model list covers the same version family you can actually deploy today.
- Top candidates overlap with your required routing and feature requirements.
Be cautious when
- There is only one benchmark snapshot or the dataset appears stale.
- The benchmark metric direction is opposite of your decision objective.
- The score difference between options is narrow and likely within implementation variance.
Related benchmarks
Last reviewed: Jun 7, 2026