Model Releases
I had to look twice at this table. I know they are just numbers, but how the heck do you beat a competitor model released just a couple of d…
I had to look twice at this table. I know they are just numbers, but how the heck do you beat a competitor model released just a couple of days ago on some of the toughest benchmarks out there? Someth
I had to look twice at this table. I know they are just numbers, but how the heck do you beat a competitor model released just a couple of days ago on some of the toughest benchmarks out there? Something is different about GPT-6 Astra. GPT-6 Astra is state-of-the-art on FrontierMath Tier 4, ARC-AGI 3, and TerminalBench-4.0. GPT‑6 Astra is also a major advance for scientific discovery, with state-of-the-art performance on Terminal-Bench Science 0.1 and HealthBench Pro.
Related
- A 27B agent just beat Claude Opus 4.8 and GPT-5.5 on held-out research replication. Replica turns paper replication into a scalable RL task …
- Very interesting new work from Microsoft Research. (bookmark it) They show that a 4B model can be tuned to out-negotiate the GPT-5 family of…
- On benchmarking long-context agentic instruction following. Agent benchmarks mostly reward reaching the answer. This new benchmark measures …
Source: DAIR.AI (X) | 2026-09-03