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.
Related event: DeepSeek V4 Flash Tops ARC-AGI Cost-Performance(3 posts)→
More from Models
- Questioning AI Reasoning: Are Baseline Capabilities Still Climbing With Reasoning Turned Off? — inductionheads · 2026-08-08
- GPT-5.6 Sol Praised for Speeding Up Cybersecurity Incident Response — gdb · 2026-08-08
- OpenAI and ElevenLabs Adopt Google's SynthID Audio Watermarking Technology — pushmeet · 2026-08-08
- DeepSeek-V4-Flash Rolls Out on Ollama Cloud with 120+ Output TPS — ollama · 2026-08-08
- DeepSeek V4 Lacks Vision: Model Builds Brightness Grid to Self-Correct — teortaxesTex · 2026-08-08
- MiniMax H3 Training Hits a Wall: Community Reports Crashes on Large Datasets — Sorry_Warthog_4910 · 2026-08-08