Artificial Analysis places StepAudio 3 ASR at 88x real-time transcription

AArtificial Analysis9/22/2026, 12:51:56

Artificial Analysis reports that StepAudio 3 ASR transcribes at a speed factor of 88x real time. It places that result behind MAI-Transcribe-2 at 374x, Smallest AI Pulse Pro at 285x and Grok Voice Transcribe 2.0 at 154x.

In the same comparison, StepAudio 3 ASR is roughly level with ElevenLabs Scribe v2 at 84x and Gemini 3.5 Transcribe at 91x, and ahead of Fun-Realtime-ASR-preview at 20x.

#stepaudio-3-asr #speech-to-text #benchmarks #artificial-analysis

View original post ↗

Previous articleExpedia will join Muse so AI agents can sort travel plans Next articleStepFun releases StepAudio 3 ASR at 1.7% WER on the AA-WER Index

Related AI news

Artificial Analysis scores Claude Haiku 5.5 at 43 on its Intelligence Index

Artificial Analysis scored Claude Haiku 5.5 at 43, up 26 points from the previous Haiku, and reported a 1 million token context window. Its results also cover token use, terminal tasks, factual accuracy, and an AutomationBench score the firm says is likely understated.

AArtificial Analysis•10/7/2026, 12:33:25•

#claude-haiku-5.5 #artificial-analysis #anthropic #benchmarks #intelligence-index

Mistral Large 4 evaluated by Artificial Analysis with 512k context and API pricing

Artificial Analysis evaluated Mistral Large 4 Preview, which scored 38 on the Intelligence Index and 50% on the Cyber Index. Mistral AI is offering the 512k-context model at $1.36 per 1M input tokens and $4.18 per 1M output tokens, with a 50% discount during its first two weeks.

AArtificial Analysis•10/6/2026, 06:56:36•

#mistral-large #mistral-ai #artificial-analysis #benchmarks

Ant Group releases Ling 3.1 Flash, scoring 41 on Artificial Analysis Intelligence Index

Ant Group has released Ling 3.1 Flash, a reasoning model featuring 560 billion total parameters and a 1 million token context window. Artificial Analysis evaluated the model at 41 on its Intelligence Index v4.3, highlighting notable improvements in agentic performance and token efficiency.

AArtificial Analysis•10/6/2026, 05:26:46•

#ant-group #ling-3.1-flash #artificial-analysis #benchmarks

Artificial Analysis measures OpenAI Web Search Time per Task at about 31 seconds

Artificial Analysis benchmarked OpenAI Web Search at roughly 31 seconds of Time per Task, ranking 14th among 26 tested products. Because OpenAI does not report search latency directly, the team measured it through stream events.

AArtificial Analysis•10/5/2026, 22:55:36•

#artificial-analysis #openai #openai-web-search #benchmarks

Artificial Analysis ranks OpenAI Web Search at 74 on Search Index

Artificial Analysis benchmarked OpenAI Web Search on its Search Index, where the tool scored 74 to place as the 5th best provider and 7th among 26 tested products. Running on GPT-5.6 Luna with medium reasoning, the built-in search tool averaged about $0.05 per task.

AArtificial Analysis•10/5/2026, 22:56:21•

#openai #artificial-analysis #web-search #benchmarks

Reset history AI News FAQ Usage limits RSS feeds API MCP Skill

News is compiled from public information. The data is for reference only, and this site has no affiliation with OpenAI.

Data & original project: Did Codex Reset · Licoy