← Benchmark report cards
Measured benchmarks
ARC-AGI-2
Published by ARC Prize. Source page ↗ · Data we read (file download) ↗
ARC Prize publishes the public set and keeps a semi-private set for verified scores.
Facts
| Fact | Value | Where it comes from |
|---|---|---|
| Who runs the evaluation | an independent organisation | curated by aiqbench, reviewed 2026-10-09 |
| Test set exposure | part public, part held out | curated by aiqbench, reviewed 2026-10-09 |
| Data licence | CC-BY-4.0 | the board's attribution record |
| Newest published result | Sep 29, 2026 | the ingested rows |
| Last pulled by aiqbench | 12 minutes ago · every 12 h | the sync log |
| Models on this axis | 267 | the ingested rows |
| Rows with a published interval | none published | the ingested rows |
| Headroom at the top | Best 95.0%, 5.0% below the ceiling; top 10 within 3.3%. | computed from the ingested rows |
| Axes it tracks closely |
| Spearman ρ over shared models (see Clusters) |
Last frontier jumps
- Sep 13, 2026 · gpt-6-astra · 95.0%
- Sep 13, 2026 · claude-opus-5 · 90.4%
- Sep 13, 2026 · claude-fable-5-1 · 90.0%
Where it appears
Weighted in the built-in templates: All sources ×1, Reasoning ×2.
View this axis alone in the console →Attribution
Source: Epoch AI, 'AI Benchmarking Hub'. Published online at epoch.ai. Retrieved from https://epoch.ai/benchmarks. Licensed under CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/). Modified by aiqbench: normalised into aiqbench's common board format; we ingest the 'arc_agi_2_external.csv' table and rescale its 0-1 scores to percent. Underlying results published by ARC Prize — https://arcprize.org/leaderboard, transcribed by Epoch AI.