Model results
ARC-AGI
Choose a shared evaluation protocol to compare model scores. Versions, sources and configurations stay separate.
Atlas snapshot captured 10/19/2026, 10:20:28 AM UTC. This is an import timestamp, not the evaluation date. Coverage may be incomplete.
Reviewed recommendation and limits
A useful test of unfamiliar-rule learning, with published testing policy and configurations.
ARC-AGI-1, 2 and 3 are distinct protocols. Imported groups below may use different protocols; this review does not certify each run. A strong ARC result does not establish workplace competence. Keep standard and provider-adapter runs apart.
ARC-AGI
- Source
- ARC-AGI (reviewed publisher results)
- Version
- v2_Semi_Private
- Measurement date
- Not reported
- Metric
- % · Higher is better
- Evaluation scope
- ARC-AGI-2 semi-private; Claude Opus 4.6 (120K, Low); CoT; Evaluation conducted with a 120K thinking budget and a maximum context window of 128K tokens and 'low' output effort.; cost per task $2.2507; ; result date not supplied; source captured 2026-09-10
Fewer than two comparable models. No ranking is assigned. Missing metadata is shown as unreported; matching imported metadata is not independent verification of the protocol.
Claude Opus 4.6
anthropic/claude-opus-4-6
64.58%
View modelEvidence independent