PulseAugur
中
实时 03:03:13
English(EN) 📊 Qwen2.5 Coder Instruct 32B measured independently: GPQA 41.7%, MMLU-Pro 63.5%, Humanity's Last Exam 3.5%, LiveCodeBench 29.5%. Not a self-report—these raw num

Qwen2.5 Coder Instruct 32B 在独立测试中基准分数揭晓

作者 PulseAugur 编辑部 · [1 个来源] ·

对 Qwen2.5 Coder Instruct 32B 模型进行的独立评估已得出具体的基准分数。该模型在 GPQA 上得分 41.7%，在 MMLU-Pro 上得分 63.5%，在 Humanity's Last Exam 上得分 3.5%，在 LiveCodeBench 上得分 29.5%。这些结果并非由模型创建者自行报告，提供了对其能力的不同视角。 AI

影响 为特定的专注于编码的 LLM 提供了客观的性能数据，帮助开发人员选择模型。

排序理由 开源 LLM 的独立基准测试结果。[lever_c_demoted from research: ic=1 ai=1.0]

在 Mastodon — mastodon.social 阅读 →

AI 生成摘要 · Google Gemini · 来自 1 个来源。 我们如何撰写摘要 →

Qwen2.5 Coder Instruct 32B 在独立测试中基准分数揭晓

本文如何被排名

Signal score
0 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Tool
开源 LLM 的独立基准测试结果。[lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration
Single-source cluster
Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics
model release, paper
Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance
High
Clearly on-topic for AI-industry coverage.
Story freshness
1 days old
Coverage has settled into its steady-state source set.

完整方法见我们的编辑标准。

报道来源 [1]

  1. Mastodon — mastodon.social TIER_1 English(EN) · opensourceaitech ·

    📊 Qwen2.5 Coder Instruct 32B 独立评测：GPQA 41.7%，MMLU-Pro 63.5%，Humanity's Last Exam 3.5%，LiveCodeBench 29.5%。非自报数据——这些原始数字

    📊 Qwen2.5 Coder Instruct 32B measured independently: GPQA 41.7%, MMLU-Pro 63.5%, Humanity's Last Exam 3.5%, LiveCodeBench 29.5%. Not a self-report—these raw numbers tell a different story. The full breakdown is right after here. https:// olud.ai/leaderboard.html # LLM # Benchmark…

    链接 olud.ai/leaderboard.html

相关实体

相关话题