Skip to content
TheChatArchiveThe Chat Archive
Perplexitysonar· PerplexityHugging Face LMArena Search Arena 24K

deepseek v3 0324 gpqa benchmark? Answer in short.

From a Chatbot Arena battleThe same person sent this prompt to two anonymous models at once. Compare it with gpt-4o-search-preview’s answer.
  1. User

    deepseek v3 0324 gpqa benchmark? Answer in short.

  2. Perplexity Assistant

    DeepSeek-V3, specifically the version 0324, has shown significant improvements in various benchmarks. However, specific GPQA benchmark results for this exact version are not detailed in the provided search results. The closest information available is that DeepSeek-V3 generally achieved a score of 59.1 on GPQA, reflecting strong reasoning and factual knowledge, and later updates improved this score to 68.4[3][13].

    For the DeepSeek-V3-0324 model, there is no explicit mention of its performance on the GPQA benchmark. However, given the model's overall improvements and competitive performance with other leading models, it is likely that it would perform well on challenging benchmarks like GPQA.

Responses were produced in different, uncontrolled contexts (system prompts, settings, prior turns). This is not a benchmark.