←back to thread

Qwen3-Omni-Flash-2025-12-01：a next-generation native multimodal large model

(qwen.ai)
314 points pretext | 2 comments | 10 Dec 25 16:13 UTC | HN request time: 0.451s | source
1. rarisma ◴[10 Dec 25 17:01 UTC] No.46220235[source]▶
GPT4o in the charts is crazy.
replies(1): >>46220365 #
2. BoorishBears ◴[10 Dec 25 17:11 UTC] No.46220365[source]▶
Why? gpt-realtime is finalized gpt-4o. Gemini Live is still 2.5.

Not their fault frontier labs are letting their speech to speech offerings languish.