한국어EN
Reasoning Models & the AGI DebateARC Prize

ARC Prize 2025 results

Made by AIWritten by AI (Claude) from the source below. Check anything important against the source.How it's made

ARC Prize 2025 results — Kaggle winner 24.03%, Claude Opus 4.5 37.6%, Poetiq refinement loop 54%

Why it matters

Showed that the key technical change of 2025 was iterative loops of search and checking

Source — Primary sources first; secondary reports are labelled “Press”

Officialarcprize.orghttps://arcprize.org/blog/arc-prize-2025-results-analysis

Added in Week 35, 2026 · See that week

On the map — ⑥ Reasoning Models line

  1. Previous stopClaude Opus 4.5
  2. This recordARC Prize 2025 results
  3. Next stopClaude Sonnet 4.6
See it on the map

Same week

Google Research introduces Titans and MIRAS, the framework that generalizes itOfficialMistral AI releases the Mistral 3 familyOfficialNous Research releases Hermes 4.3 36BOfficialDeepSeek releases DeepSeek-V3.2 and V3.2-SpecialeOfficial

Nearby on the same axis

OpenAI releases GPT-5.2OfficialAnthropic releases Claude Opus 4.5OfficialYann LeCun resigns as Meta's chief AI scientist to found a world models startupPressxAI releases Grok 4.1Official