Artificial Analysis releases full streaming STT leaderboard and methodology
ArtificialAnlys · x · 2026-10-02
Artificial Analysis published full results and methodology for its streaming speech-to-text benchmark. The AA-WER Streaming index uses 8 hours of audio weighted across AA-AgentTalk (50%), VoxPopuli (25%) and Earnings22 (25%), covering diverse accents, domain language and tough acoustics, comparing 37+ models on WER, latency after end of speech and price, with a Pareto-frontier view split by proprietary vs open weights.
More from Models
- Google hides Gemini model label in AI Mode, rolls Gemini 4 Carbon to Pro subscribers — gaganghotra_ · 2026-11-16
- Open-weight Karpo-Decision-31B tops Decision Index at 73.9, one forward pass per answer — CodeByPoonam · 2026-11-16
- Stealth Anthropic model spotted in Devin build as METR chart shows frontier pace up 1.4x — daniel_mac8 · 2026-11-16
- Eval Firm Trajectory Told 40 Agents "NEVER Stop" in Harness Without Telling Epoch — peterwildeford · 2026-11-16
- Unsloth Q8 crushes default Q3 in a self-hosted test over 331 financial PDFs — No_Cartographer3953 · 2026-11-16
- METR time-horizon chart updated: doubling every 1.7 months since Opus 4.5, 'Model 4' ~38h — ben_j_todd · 2026-11-16