Storia in 2 fonti

Astra's Adapter Beat the Reasoning Dial on ARC-AGI-3

On 3 Sep ARC Prize scored GPT-6 Astra at 62.7% in the shared harness and 99.9% in OpenAI's adapter.

Raccontata da

dev.to

cryptobriefing.com

Confronto fonti

2 prospettive sulla stessa storia

AI · summaries

dev.toStai leggendo4 h fa

Astra's Adapter Beat the Reasoning Dial on ARC-AGI-3

Astra scored 99.9% on ARC-AGI-3 using OpenAI's Adapter but 62.7% in Standard harness—the gap stems from state preservation, not model weights. Managers: benchmark results are runtime-dependent; the 99.9% is not reproducible without specific scaffolding.

originale

cryptobriefing.com2 g fa

OpenAI's GPT-6 Astra scores 97.6% on FrontierMath after internal version started at just 17%

OpenAI's GPT-6 Astra scores 97.6% on FrontierMath Tier 4 after an internal version started at just 17%, marking a massive leap in AI math

Leggi questa versione → originale

Timeline cronologica

martedì 8 settembre 2026·dev.to
GPT-6 Astra scores 95% on one robot task, 10% on another
Robocurve ran GPT-6 Astra and Claude Fable 5.1 on real robot arms. Astra hit 19 of 20 on the easy task and 2 of 20 on the hard one.
martedì 8 settembre 2026·cryptobriefing.com
OpenAI's GPT-6 Astra scores 97.6% on FrontierMath after internal version started at just 17%
OpenAI's GPT-6 Astra scores 97.6% on FrontierMath Tier 4 after an internal version started at just 17%, marking a massive leap in AI math

Astra's Adapter Beat the Reasoning Dial on ARC-AGI-3

OpenAI's GPT-6 Astra scores 97.6% on FrontierMath after internal version started at just 17%

Timeline cronologica

GPT-6 Astra scores 95% on one robot task, 10% on another

OpenAI's GPT-6 Astra scores 97.6% on FrontierMath after internal version started at just 17%

GPT-6 Astra Isn't AGI. It's a For-Loop With Better PR

Astra's Adapter Beat the Reasoning Dial on ARC-AGI-3