ARC-AGI-3 shows a striking outlier: Argon low jumps from 42.1% to 97.5%
GregKamradt · x · 2026-10-29
ARC Prize reports early ARC-AGI-3 results: scores on ARC-AGI-2 and ARC-AGI-3 are broadly correlated, with stronger v2 models also scoring higher on v3.
One notable outlier stands out: Gemini 4 Argon at low reasoning scored only 42.1% on ARC-AGI-2 but 97.5% on ARC-AGI-3 under the provider adapter harness — far above what its v2 result would suggest. Greg Kamradt says he's still trying to understand why some data points break away from the expected v2/3 trend.
More from Models
- You.com: agentic search failures are behavior problems, fixed in Nemotron 3.5 Lightning — RichardSocher · 2026-10-29
- How I AI agent bench: Grok Bot wins big at 93%, Claude Duet trails at 79% — lennysan · 2026-10-29
- DeepMind slammed for announcing models weeks before availability amid Gemini Xenon chatter — adonis_singh · 2026-10-29
- Alphabet Q3 call: Gemini Carbon frontier model, MCP apps in Search, AI Mode ads expand — lilyraynyc · 2026-10-29
- gpt-6.1-terra runs 4-hour browser session at ~1 action/second on 10% of quota — prd_008 · 2026-10-29
- AA Index revamp right before Gemini Carbon release raises benchmark timing eyebrows — stablequan · 2026-10-29