Every's Vibe Check: GPT-6.2 Astra and Sol handle bounded tasks but fall short on judgment
danshipper · x · 2026-11-19
Every published its Vibe Check of OpenAI's GPT-6.2 Astra and Sol, with a live re-test scheduled Nov 18 at 3pm ET. The verdict: both models handle bounded tasks efficiently, but the deep work requiring judgment and follow-through still demands more. The six-person testing team includes Dan Shipper, Katie Parrott, Jack Cheng, Kieran Klaassen and Mike Taylor; prior editions covered Gemini 4 Carbon, GPT-6 Astra and Fable 5.2.
More from Models
- Gemini-4-neon spotted alongside other Gemini 4 models, rumored to launch today — ivan_bezdomny · 2026-11-19
- 'Every single candidate chose Claude': researcher notes 100% tool preference in agentic evaluations — RylanSchaeffer · 2026-11-19
- Microsoft's 'can you trust open weights?' FUD slide mocked as 7 new MAI models land — victormustar · 2026-11-19
- DevOps user slams 6.2-astra as the worst model ever: 'total gibberish' — rickasaurus · 2026-11-19
- Counter-take to "LLs have peaked": new models much better at long-horizon tasks — minhnguyen · 2026-11-19
- Adaption powers inference for AI Singapore's SEA-LION sovereign models — sarahookr · 2026-11-19