DeepSeek V4.1 Flash tops 3% on ARC-AGI-3 for under $1k, a first
fchollet · x · 2026-10-14
ARC Prize published DeepSeek V4.1 Flash's verified ARC-AGI results:
- ARC-AGI-3: 3.3% at $878 total evaluation cost (provider adapter harness); 0.9% at $1.2k on the standard harness
- First model evaluated on ARC-AGI-3 to score above 3% for under $1k
- The official leaderboard shows frontier models like GPT-6 Astra scoring 90%+ at tens of thousands of dollars, underscoring DeepSeek's cost-efficiency positioning
More from Models
- Arcee teases another model release tomorrow right after shipping its 24B — JosephJacks_ · 2026-10-14
- OpenRouter decision model market share: TypeSafe commands 82.8% — nischay_twt · 2026-10-14
- Anthropic's rumored Fable 5.5 model didn't ship this week as expected — imjustnewatai · 2026-10-14
- One prompt, three personalities: GPT, Gemini and Opus trade sparkling jokes — emollick · 2026-10-14
- Gemini Argon's table preference plunges to 31.5% from Flash's 85.9% in new test — dejanseo · 2026-10-14
- User blasts Claude for refusing to click a Terms & Conditions button — Angaisb_ · 2026-10-14