{"slug": "inkling-small-is-the-highest-scoring-open-weight-model-evaluated-by-arc-prize", "title": "Inkling Small is the highest-scoring open-weight model evaluated by ARC Prize", "summary": "Inkling Small, an open-weight model from Thinky, achieved the highest score among open-weight models on the ARC Prize leaderboard, nearly matching GPT-5.2 high. The ARC-AGI-3 evaluations are ongoing, with full results rolling out over the next few weeks.", "body_md": "Inkling Small from\n\n- Full results:\n[arcprize.org/results/thinky…](https://arcprize.org/results/thinky-inkling-small)ARC-AGI-3 evaluations are more operationally intensive, so results will roll out over the next few weeks.- Leaderboard:[arcprize.org/leaderboard](https://arcprize.org/leaderboard)- Reproduce the public results:[github.com/arcprize/arc-a…](https://github.com/arcprize/arc-agi-benchmarking)- Testing policy:[arcprize.org/policy](https://arcprize.org/policy)- Full Inkling Small results:[arcprize.org/results/thinky…](https://arcprize.org/results/thinky-inkling-small) - Wow almost on par with gpt 5.2 high! For such a small model, it's incredible.\n# Join the conversation", "url": "https://wpnews.pro/news/inkling-small-is-the-highest-scoring-open-weight-model-evaluated-by-arc-prize", "canonical_source": "https://twitter.com/arcprize/status/2082925303601459347", "published_at": "2026-07-30 23:32:23+00:00", "updated_at": "2026-07-30 23:52:23.893343+00:00", "lang": "en", "topics": ["artificial-intelligence", "ai-research", "ai-products"], "entities": ["Inkling Small", "Thinky", "ARC Prize", "ARC-AGI-3", "GPT-5.2"], "alternates": {"html": "https://wpnews.pro/news/inkling-small-is-the-highest-scoring-open-weight-model-evaluated-by-arc-prize", "markdown": "https://wpnews.pro/news/inkling-small-is-the-highest-scoring-open-weight-model-evaluated-by-arc-prize.md", "text": "https://wpnews.pro/news/inkling-small-is-the-highest-scoring-open-weight-model-evaluated-by-arc-prize.txt", "jsonld": "https://wpnews.pro/news/inkling-small-is-the-highest-scoring-open-weight-model-evaluated-by-arc-prize.jsonld"}}