Inkling Small is the highest-scoring open-weight model evaluated by ARC Prize

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.

Inkling Small from - Full results: 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. Join the conversation