Inception Labs releases Mercury 3, a diffusion large language model reaching 1068 tokens/second
Diffusion at Scale: Introducing Mercury 3
AI BriefingInception Labs releases Mercury 3, a diffusion-based large language model, claiming it surpasses GPT-6 Luna and Claude Haiku 5.5 on multiple benchmarks, reaches 1,068 tokens per second, and has more than 40 times the parameters of Mercury 1.
Also reported by 2 other sources
- Inception Releases Mercury 3 Diffusion Language Model, Claiming to Surpass GPT-6 Luna and Claude Haiku 5.5 on Some BenchmarksThe Decoder:AI News · 26 days ago
- Inception releases Mercury 3, a diffusion language model with speeds of up to 1,068 tok/sMarkTechPost · 27 days ago
Source: Inception Labs: Blog · inceptionlabs.ai
Event follow-up2
View all event coverage- Inception Labs releases Mercury 3, a diffusion large language model reaching 1068 tokens/secondInception Labs:Blog · 28 days ago
- Inception's diffusion model Mercury 3 launches on OpenRouterOpenRouter · 28 days ago