独立基准测试揭示了几款大型语言模型在性能上的差异。Kimi K2 0905 在 GPQA 和 MMLU-Pro 上取得了高分，而 Qwen3 235B A22B 在这些指标上也表现良好，但在长上下文推理方面遇到困难。Exaone 4.0 在各项测试中得分较低，尤其是在推理任务方面。Qwen3 VL 4B 在其通用知识能力和处理困难推理挑战方面的表现之间存在显著差距。 AI
影响 这些基准测试突显了推理和上下文处理方面的性能差异，为未来的模型开发和选择提供了指导。
排序理由 该集群报告了多个 LLM 的基准测试结果，属于研究范畴。
在 Mastodon — fosstodon.org 阅读 →
AI 生成摘要 · Google Gemini · 来自 6 个来源。 我们如何撰写摘要 →
完整方法见我们的编辑标准。
📊 GLM-4.6 (Reasoning) — the actual numbers GPQA: 78% MMLU-Pro: 82.9% Humanity's Last Exam: 14.5% Long Context Reasoning: 55.3% 💰 30.4 intelligence points per dollar Measured independently, not self-reported → https:// olud.ai/leaderboard.html # LLM # Benchmarks # OpenSource # AI
📊 Granite 4.0 1B — the actual numbers GPQA: 28.1% MMLU-Pro: 32.5% Humanity's Last Exam: 4.8% Long Context Reasoning: 6% Measured independently, not self-reported → https:// olud.ai/leaderboard.html # LLM # Benchmarks # OpenSource # AI
📊 Kimi K2 0905 — the actual numbers GPQA: 76.7% MMLU-Pro: 81.9% Humanity's Last Exam: 6.4% Long Context Reasoning: 53.7% 💰 22.3 intelligence points per dollar Measured independently, not self-reported → https:// olud.ai/leaderboard.html # LLM # Benchmarks # OpenSource # AI
📊 Exaone 4.0 1.2B (Non-reasoning) — the actual numbers GPQA: 42.4% MMLU-Pro: 50% Humanity's Last Exam: 5.7% Long Context Reasoning: 0% Measured independently, not self-reported → https:// olud.ai/leaderboard.html # LLM # Benchmarks # OpenSource # AI
Qwen3 VL 4B (Reasoning) hits 70% on MMLU-Pro but only 4.6% on Humanity's Last Exam—a clear gap between strong general knowledge and truly hard reasoning. https:// olud.ai/leaderboard.html # LLM # Benchmarks # OpenSource # AI
📊 Qwen3 235B A22B (Reasoning) — the actual numbers GPQA: 70% MMLU-Pro: 82.8% Humanity's Last Exam: 11% Long Context Reasoning: 0% 💰 5.1 intelligence points per dollar Measured independently, not self-reported → https:// olud.ai/leaderboard.html # LLM # Benchmarks # OpenSource # A…