Storia in 2 fonti

Same Model, 13.3% to 38.3%

OpenAI changed two API settings on ARC-AGI-3 and GPT-5.6 Sol went from 13.3% to 38.3% while spending six times fewer output tokens. Same model, same weights, same benchmark.

Raccontata da

thenextweb.com

dev.to

Confronto fonti

2 prospettive sulla stessa storia

AI · summaries

dev.toStai leggendo2 g fa

Same Model, 13.3% to 38.3%

OpenAI changed two API settings on ARC-AGI-3 and GPT-5.6 Sol went from 13.3% to 38.3% while spending six times fewer output tokens. Same model, same weights, same benchmark.

originale

thenextweb.com4 g fa

Astra's AGI score came from a harness, not the model

ARC Prize scored GPT-6 Astra at 62.7% on ARC-AGI-3 with its own harness and 99.9% with OpenAI's, then revised five metrics after launch.

Leggi questa versione → originale

Timeline cronologica

domenica 6 settembre 2026·thenextweb.com
Astra's AGI score came from a harness, not the model
ARC Prize scored GPT-6 Astra at 62.7% on ARC-AGI-3 with its own harness and 99.9% with OpenAI's, then revised five metrics after launch.
martedì 8 settembre 2026·dev.to
Same Model, 13.3% to 38.3%
OpenAI changed two API settings on ARC-AGI-3 and GPT-5.6 Sol went from 13.3% to 38.3% while spending six times fewer output tokens. Same model, same weights, same benchmark.