DeepSeek V4.1 Flash 1017 Card - ZeroBench-main (with tools, Pass@5): leaderboard
ZeroBench main set of hard visual-reasoning questions, with tools allowed, scored pass@5. DeepSeek reported this on the DeepSeek-V4.1-Flash-1017 model card and API change log (October 17, 2026). Only DeepSeek's own runs of the dated 1017 checkpoint and the original V4.1 Flash are included; the card's comparator columns are left out, and reasoning effort is not stated. Metric: Pass@5 (%). Higher is better. Source: https://huggingface.co/deepseek-ai/DeepSeek-V4.1-Flash-1017/raw/1bae0e1088993b9b82de08f59de5be5a34e42170/README.md
Metric: Pass@5 (%). Source: huggingface.co. Saturation forecast: Around November 2027. 2 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | DeepSeek V4.1 Flash (1017) | 51 | #15 |
| 2 | DeepSeek V4.1 Flash | 49 | #35 |
No result here: #4 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=deepseek-v4-1-flash-1017-card-zerobench-main-with-tools-pass-5 · How It Works · Data refreshed daily, snapshot 2026-10-18.