Mercury 3 benchmarks: beats GPT-6 Luna and Haiku 5.5 at 1,068 tok/s
StefanoErmon · x · 2026-10-20
Mercury 3 already powers agentic apps in code review, tutoring and browser use, with early adopters including TinyFish, Lorikeet and Bauplan. Inception says it scales text diffusion: 40x larger than Mercury 1 yet just as fast. The shared benchmark chart shows 1,068 tok/s output vs 130/240 for rivals, with wins on SWE-Bench Atlas (51.08), IFBench (76.84), GPQA Diamond (89.23) and BrowseComp+ (55.18).
Related event: Inception Launches Mercury 3: Diffusion LLM Hits 1000+ Tokens/s(8 posts)→
More from Models
- New decision model basal-omni-1.0-ultra claims near-frontier intelligence at much lower cost — tristanbob · 2026-10-20
- Reasoning models can steer their chain of thought far better than earlier tests suggested, paper finds — dair_ai · 2026-10-20
- Same sources, same question: how Claude, NotebookLM and ChatGPT differ on one knowledge base — kbavandi · 2026-10-20
- 434 Days Later: ChatGPT and Claude Still Can't Render JavaScript Content — gaganghotra_ · 2026-10-20
- Dream-1 claims new Pareto frontier for robot control: 16x cheaper, 1.7x faster, 59 vs 48 on RoboDojo — scott_e_reed · 2026-10-20
- $0.08 test finds DeepSeek's new search API scores by host, leaks spam despite filters — gaganghotra_ · 2026-10-20