Mind2Web
AssessTechniques
A web navigation benchmark for evaluating browser-use and agent behavior.
Why it's here
Placed in Assess: 1 article(s) of evidence from 1 source(s), led by model releases, with 1 in the last 30 days. Confidence 24%. Low accumulated evidence, so it defaults conservatively pending more signal.
Evidence (1)
- 8Hacker News·10/19/2026model_releaseMercury 3 brings diffusion LLMs to scale
Mercury 3 is a new diffusion-based LLM that the company says matches or exceeds frontier speed-optimized models on several benchmarks while running at over 1,000 tokens per second. The launch highlights a 1M-token context window, lower pricing, and early production use in agents, tutoring, search, and customer support.