ARC-AGI-1 · ARC Prize Foundation private dataset · Benchmark definition and scores
ARC-AGI-1 · ARC Prize Foundation private dataset has benchmark disclosures or scores across 4 model releases.
Benchmark versions and metrics
Aliases ARC-AGI-1
- Accuracy · % · Higher is better
Latest models by series · reported scores
The latest models in each named series have no scores to display in this scope. Recorded historical data appears below.
History · 4 releases
- Claude Fable 5.11 score record for this release, including 1 exact value (may include historical records)
- Claude Opus 4.72 score records for this release, including 2 exact values (may include historical records)
- Claude Sonnet 4.62 score records for this release, including 2 exact values (may include historical records)
- Claude Opus 4.51 score record for this release, including 1 exact value (may include historical records)