Mercury 3 launches as the most intelligent diffusion LLM, outpacing GPT-6 Luna at 1000+ tok/s
chrispiech · x · 2026-10-20
Stefano Ermon's team (Inception) released Mercury 3, calling it the most intelligent diffusion LLM ever released. The team claims it outperforms GPT-6 Luna and Haiku 5.5 on quality while running at 1000+ tokens/sec.
Diffusion LLMs generate text via parallel denoising rather than autoregressive decoding, making raw speed their key advantage. If the benchmarks hold up, this is a notable signal that the diffusion architecture is closing the quality gap with mainstream autoregressive models.
More from Models
- Deutsche Bank: Meta's Muse still leads ChatGPT in downloads and DAUs 36 days post-launch — alexandr_wang · 2026-10-20
- Uncensored DeepSeek V4.1 Flash FP8 finetune trends on Hugging Face — dealignai · 2026-10-20
- ChatGPT caught silently swapping GPT-5.6 High for GPT-6 at medium thinking — DepositameAMiBCP · 2026-10-20
- MiniMax M3.1 Flash goes live in Command Code with 1M context, free for now — MiniMax_AI · 2026-10-20
- User slams Xiaomi MiMo over hard-to-cancel $60 subscription — bookwormengr · 2026-10-20
- Strata 2 beta runs at half speed? Dual-4090 user reports 155→95 tok/s — Lost-Vermicelli-6252 · 2026-10-20