ARC Prize to evaluate DS V4.1 Flash after predecessor hit 61.4% on ARC-AGI-2
teortaxesTex · x · 2026-09-30
ARC Prize confirmed it will evaluate DS V4.1 Flash. Its predecessor V4-Flash-0731 scored 61.4% on ARC-AGI-2; two months later the new model is much larger, natively multimodal, with 29% more tokens, while Dots3-preview already hits 77%. The poster says <80% would be disappointing and wonders whether Dots simply hill-climbed ARC.
Related event: ARC Prize to Benchmark DeepSeek V4.1 Flash(2 posts)→
More from Models
- LLM Chain-of-Thought Contains Surprising Emotionally Expressive Language—and It May Be Functional — xuanalogue · 2026-09-30
- When the CoT Says 'Responding with Honest Feedback,' That's When You Worry — TheZvi · 2026-09-30
- Anthropic 'Drops a Banger Gift' for Claude Users, Says Popular AI Blogger — eyishazyer · 2026-09-30
- GPT 6.1 Sol cuts cached pricing 50% while Anthropic holds back models over safety — oran_ge · 2026-09-30
- OpenRouter data: token usage exploding, some open-weight models see 10x spend since January — AccBalanced · 2026-09-30
- GPT-6 Astra makes generating Minecraft mobs trivially easy — Angaisb_ · 2026-09-30