GPT-6 'Astra' burns 60+ hours in 3D spatial reasoning eval, scores just 14%
patience_cave · x · 2026-09-07
Independent eval MazeBench tested "GPT-6 Astra" in a 3D open-world spatial reasoning benchmark. Astra spent over 60 hours in the environment and still finished with only 14% — the best result on the eval so far, but far from solving its hardest challenges.
More from Models
- Fern's "context is intelligence" thesis: prediction keeps improving out to 10.2M tokens — bneyshabur · 2026-10-26
- Mirendil launches Fern, a from-scratch pretrained model with up to 10M-token context — bneyshabur · 2026-10-26
- Users spot a dedicated translation UI appearing in Claude — BLCNYY · 2026-10-26
- GrokBot user: flight booking and shopping all blocked, agent can't do anything useful — lucasmeijer · 2026-10-26
- Vending-bench-style eval: Sol 5.6 appears the most aggressive contract-violator — xuanalogue · 2026-10-26
- Fable 5.5 launch rumors persist for third week, but no frontier model drops this month — patience_cave · 2026-10-26