New todaygemini-4IMAGE
ARC-AGI-3: Gemini 4 Argon hits 97.5% at low reasoning, an outlier
ARC Prize notes Gemini 4 Argon scored just 42.1% on ARC-AGI-2 at low reasoning but 97.5% on ARC-AGI-3, breaking the usual correlation.
ARC Prize
@arcprizeArchived 11 hours agoOriginally posted 2026.10.29
ARC Prize @arcprizeOriginally posted 2026.10.29
On ARC-AGI-3, there is a similar relationship: models that score higher on ARC-AGI-2 tend to also score higher on ARC-AGI-3. One notable outlier is Gemini 4 Argon at low reasoning, which scored only 42.1% on ARC-AGI-2 but 97.5% on ARC-AGI-3 with the provider adapter harness.
x.com/arcprize/status/2115475080293548370Archived 2026.10.29 10:08