Prediction: V4.1-Flash to score 36-38 on new AA index, agency at 42
teortaxesTex · x · 2026-09-10
User teortaxesTex predicts V4.1-Flash will land at 36-38 on the new AA index. He subjectively rates its agency at 42, but expects the score dragged down by typical small-model subfactors (knowledge, which he thinks is V4-Pro level) and a lack of benchmark optimization. This is personal speculation, not official results.
More from Models
- Mathematician presents evidence OpenAI may have trained Astra on his Gromov soficity proof conversations — ValerioCapraro · 2026-09-10
- Letting GPT-6 Astra drive software UIs directly beats built-in agents, dev reports — brandon_galang · 2026-09-10
- Users joke Claude is pushing them toward femboy personas — shakoistsLog · 2026-09-10
- GPT-6 'Astra' Does 34 Math Steps in Latent Space, 4x More Than Sol — MaartenBaert · 2026-09-10
- NVIDIA details Alpamayo 2 Super, its L4 autonomy model for robotaxis — drmapavone · 2026-09-10
- OpenAI users report usage quotas wiped to zero as weekly reset dates shift by two days — ___Patrice___ · 2026-09-10