GPT Astra 6 hits new BALROG heights with 13% NetHack progression, still "not AGI"
_rockt · x · 2026-09-19
BALROG's leaderboard adds three new entries: GPT 5.6 Sol at max effort remains within error of Gemini 3 and 3.1 Pro, while GPT Astra 6 at max reasoning effort reaches new heights, posting 13% average progression on the NetHack Learning Environment. Researcher rockt comments: "Great progress. Not yet AGI though."
More from Models
- Tencent Hunyuan Launches Hy4 with Vision, Claims Top Tier Among Open Models — TencentHunyuan · 2026-11-04
- Claude Code fixes game copyright refusal rule in 2.1.317: naming a game now works — apples_jimmy · 2026-11-04
- Microsoft Phi-4-mini: a 3.8B model with 128K context and 52.8 MMLU-Pro — goyalshaliniuk · 2026-11-04
- Mistral Ministral 3 3B ships in base, instruct and reasoning variants — goyalshaliniuk · 2026-11-04
- 7 small language models to watch in 2026–27, from Qwen3.5-4B to LFM2.5-1.2B — goyalshaliniuk · 2026-11-04
- Users report Claude Opus 5.5 quality seemingly degrading this week — ayushtweetshere · 2026-11-04