aiaimodel.cards
← All benchmarks

ARC-AGI-2 (ARC Prize Verified)

Abstract visual reasoning puzzles that test learning new rules from a few examples.

Your workloadRAG over docs · 12K in · 600 out · 50K requests/mo · 30% cached
  1. 1Gemini 3.1 Pro · Googlebest value
    77.1%

“Best value”: no other model here reports a higher score at a lower cost for your workload. Scores are self-reported by each maker with different settings, so treat close calls as ties.

How each maker reported it

  • Gemini 3.1 Pro p.4

    Results as of February 2026, Gemini at Thinking (High); competitors at their highest reported settings, as listed by Google.

Only each model's own maker's number is shown; scores a maker reports for rival models are left out.