Kimi K3.1 Pro 发布，智能指数 55 分位列第四

Kimi K3.1 Pro 在 Artificial Analysis 智能指数上以 55 分位列第四，在智能体性能上大幅提升；一旦权重发布，它将成为领先的开源权重模型 @Kimi_Moonshot 的新推理模型比 Kimi K3（max，44 分）提升 11 分。在智能指数上，它仅落后于 Claude Opus 5.5（max with fallback，58 分）、Claude Sonnet 5.5（max with fallback，56 分）和 Muse Wonder Full（max，56 分）。 一旦 K3.1 Pro 的权重发布，它将成为得分最高的开源权重模型，开源权重模型与专有模型在智能指数上的差距将从 12 分缩小到 3 分。 主要结果： ➤ 智能体性能大幅提升：Kimi K3.1 Pro 在 GDPval-AA 上以 1,846 Elo 位列第三，比 Kimi K3 提升 312 Elo，仅次于 Claude Opus 5.5（1,866 Elo）和 Muse Wonder Full（1,857 Elo）。Kimi K3.1 Pro 还在 Terminal-Bench 4.0 上取得所有模型中的最高分。K3.1 Pro 得分为 67%，高于 Kimi K3 的 13%，并领先于 Claude Sonnet 5.5（64%）。测试智能体 SaaS 工作流的 AutomationBench-AA 从 58% 升至 73%。 ➤ 其他评测的提升较为温和：Humanity's Last Exam 从 47% 升至 52%，CritPt 从 23% 升至 25%，SciCode 从 59% 升至 61%。AA-Omniscience 指数从 20 升至 30，幻觉率从 53% 降至 44%，准确率从 48% 升至 51%。 ➤ 每任务成本与 Kimi K3 大致相当，为每任务 $1.98：K3.1 Pro 在每个智能指数任务上使用 55K 输出 token，比 Kimi K3 的 48K 多 14%，而其第一方 token 价格低 33%。 其他模型详情： ➤ 上下文窗口：1M tokens。 ➤ 规模：总参数 2.8T，激活参数 104B ➤ 输入模态：文本和图像 ➤ 权重与许可证：权重目前尚未发布，预计 Moonshot 将在发布后不久放出权重 ➤ 定价：每 1M 输入/输出/缓存命中 token 分别为 $2/$10/$0.20，三项费率均比 Kimi K3 低 33%。 祝贺 @Kimi_Moonshot 团队发布！

查看原文

Kimi K3.1 Pro launches at 4th on the Artificial Analysis Intelligence Index scoring 55, making large gains in agentic performance; it will be the leading open-weights model once its weights are published @Kimi_Moonshot's new reasoning model gains 11 points over Kimi K3 (max, 44). It trails only Claude Opus 5.5 (max with fallback, 58), Claude Sonnet 5.5 (max with fallback, 56), and Muse Wonder Full (max, 56) on the Intelligence Index. Once the weights for K3.1 Pro are released it will be the highest-scoring open weights model and the gap between the leading open weights and proprietary models on the Intelligence Index will narrow from 12 points to 3. Key results: ➤ Large gains in agentic performance: Kimi K3.1 Pro scores 3rd on GDPval-AA with 1,846 Elo, up 312 Elo from Kimi K3, behind only Claude Opus 5.5 (1,866 Elo) and Muse Wonder Full (1,857 Elo). Kimi K3.1 Pro also achieves the highest score of any model on Terminal-Bench 4.0. K3.1 Pro scores 67%, up from 13% for Kimi K3 and ahead of Claude Sonnet 5.5 (64%). AutomationBench-AA, which tests agentic SaaS workflows, rises from 58% to 73%. ➤ Gains in other evals are more moderate: Humanity's Last Exam rises from 47% to 52%, CritPt from 23% to 25%, and SciCode from 59% to 61%. AA-Omniscience Index rises from 20 to 30, as the hallucination rate falls from 53% to 44% and accuracy rises from 48% to 51%. ➤ Cost per Task roughly equal to Kimi K3 at $1.98 per Task: K3.1 Pro uses 55K output tokens per Intelligence Index task, 14% more than Kimi K3 at 48K, while its first-party token prices are 33% lower. Additional model details: ➤ Context window: 1M tokens. ➤ Size: 2.8T total, 104B active parameters ➤ Input modalities: Text and image ➤ Weights and license: Weights currently not published, Moonshot is expected to release the weights soon after launch ➤ Pricing: $2/$10/$0.20 per 1M input/output/cache hit tokens, 33% lower than Kimi K3 on all three rates. Congratulations to the team at @Kimi_Moonshot on the release!