MODEL SIGNAL · INCEPTION LABS
Mercury 2
Fastest model on the Artificial Analysis leaderboard by output speed. Diffusion-based LLM architecture enabling massively parallel token generation — entirely different inference paradigm from autoregressive models.
CATEGORYGeneral
CONTEXT32K
RELEASEDMarch 1, 2026
Key Features
- Fastest output speed (leaderboard #1)
- Diffusion-based LLM
- Parallel token generation
- Novel non-autoregressive architecture
- Ultra-low latency
Read the Model Signal report →
The Model Signal report for Mercury 2 is still compounding. It synthesizes automatically from Signal + Noise wire coverage and the provider announcement — check back as the wire mentions this model.