Understand this story
ARC Prize announced the results of DeepSeek V4.1 Flash 1017 on the ARC-AGI validation set: a score of 78.1% on ARC-AGI-2 at a cost of $0.16 per task, and a score of 94.5% on ARC-AGI-1 at a cost of $0.06 per task. The organization also listed the changes in the best scores of the DeepSeek Flash series on ARC-AGI-2: V4 Flash 0731 at 61.4%, V4.1 Flash at 72.9%, and V4.1 Flash 1017 rising to 78.1%. A day earlier, Guillermo Rauch announced that Vercel would add DeepSeek v4.1 Flash (1017) to Token Pass, using DeepSeek's new weights, supporting a 1M context window with no configuration changes required; he said the model is fast, extremely low-priced, and offers zero data retention, making it suitable for running subagents for tasks planned by larger, more expensive models. Currently, the public information consists of the above results and the addition to Token Pass.
AI-generated from public reports
Latest development · Report
DeepSeek V4.1 Flash 1017 scores 78.1% on ARC-AGI-2Developments
2 confirmed developments
ARC Prize announces the ARC-AGI verified score of DeepSeek V4.1 Flash 1017
Source:ARC Prize- Source:Guillermo Rauch
Reports and discussion timeline
Browse reports and discussion by time. Their evidence levels remain distinct.
Oct 23
ARC PrizeFirst-partySelected
DeepSeek V4.1 Flash 1017 scores 78.1% on ARC-AGI-2
ARC Prize announces the results of DeepSeek V4.1 Flash 1017 on the ARC-AGI validation set: ARC-AGI-2 score 78.1%, cost per task $0.16; ARC-AGI-1 score 94.5%, cost per task $0.06. The best score of the DeepSeek Flash series on ARC-AGI-2 rose from 61.4% for V4 Flash 0731 to 72.9% for V4.1 Flash, and then to 78.1% for V4.1 Flash 1017.
Oct 22
Guillermo Rauch
DeepSeek v4.1 Flash joins Vercel Token Pass
Vercel has added DeepSeek v4.1 Flash (1017) to Token Pass, using DeepSeek's new weights, supporting a 1M context window with no configuration changes required. Guillermo Rauch says the model is fast, extremely low-priced, and offers zero data retention (ZDR), making it suitable for running sub-agents whose tasks are planned by larger, more expensive models.