all the models — AI benchmark observatory
← Models

DeepSeek-V3.2-Exp

DeepSeek · open weight · deepseek-v3.2-exp

DeepSeek-V3.2-Exp is an experimental iteration introducing DeepSeek Sparse Attention (DSA) to improve long-context training and inference efficiency while keeping output quality on par with V3.1. It explores fine-grained sparse attention for extended sequence processing.

SimpleQAAIME 2025MMLU-ProGPQAAider-PolyglLiveCodeBenc

Benchmark scores

Pricing

  • No provider pricing.

AA metrics

No Artificial Analysis link yet.

Arena Elo

  • No Arena snapshot linked.
DeepSeek-V3.2-Exp Benchmarks · all the models