Fact · Speech recognition
7.4percent word error rate (Deepgram Flux, first partial)
In Artificial Analysis's 2026 streaming benchmark, the first partial transcript from Deepgram Flux had a word error rate of 7.4 percent, while ElevenLabs Scribe v2 Realtime's had 3.6 percent.
Checked against its source on October 17, 2026
In the source's own words
“ElevenLabs Scribe v2 Realtime 3.6% WER at both, Deepgram Nova-3 6.7% at both, Deepgram Flux 7.4% at both”
Announcing AA-WER Streaming (Artificial Analysis), Artificial Analysis, Artificial Analysis, 2026, Key results, paragraph on accuracy and first partial.
Open the original- What it measures
- Artificial Analysis reports the word error rate of each service's first partial and its first final transcript. For most of the streaming models it tested, the two were almost the same.
- What it does not show
- The percentages come from one benchmark on its own audio sets. A different set of recordings can rank the same services differently.