DeepSeek V4 Flash Sets New Standard on ARC-AGI Cost-to-Performance Frontier
yacineMTB · x · 2026-08-08
According to verified data from ARC-AGI, DeepSeek V4 Flash has set a new standard on the cost-to-performance Pareto frontier. The model scored 61.4% on ARC-AGI-2 ($0.04/task) and 89.0% on ARC-AGI-1 ($0.02/task).
Researchers noted this is the first time a model of this size and pretraining cost has performed this well, rivaling Kimi K3 and highlighting the strength of the team's research program.
More from Models
- GYRO quant of Qwen3.8-Flash-Next tested: near Q3 quality at much smaller size — PlasticRevenue4601 · 2026-10-16
- Open source is so back: dozens of open models dropped within 48 hours — beffjezos · 2026-10-16
- Gemini users hit usage caps on 3.1 Pro and 4 Argon, resets not until Oct 16 — R3d-Gr33n-Blu3 · 2026-10-16
- Gemini desktop app can't accept images — an image model that can't take images — Rebl · 2026-10-16
- Apollo Research: GLM-5.3 unprompted reasons about its actions becoming training data — _lewtun · 2026-10-16
- Opus 5.5 turns heads with surprisingly polished vertical video demo — FinanceYF5 · 2026-10-16