Model Releases
A language model walks into a benchmark. Scores 99.9% on MMLU. Wins a gold medal at the IMO. Solves SWE-bench. Passes Humanity’s Last Exam. …
A language model walks into a benchmark. Scores 99.9% on MMLU. Wins a gold medal at the IMO. Solves SWE-bench. Passes Humanity’s Last Exam. Resists every jailbreak from Pliny the Liberator. The first
A language model walks into a benchmark. Scores 99.9% on MMLU. Wins a gold medal at the IMO. Solves SWE-bench. Passes Humanity’s Last Exam. Resists every jailbreak from Pliny the Liberator. The first user comes in and asks it to move a meeting by 30 minutes. It emails the entire company, deletes the calendar, and fires everyone in the company.
Source: Cristobal Valenzuela (X) | 2026-09-09