Lisan al Gaib· @scaling01 · X·· 1 小时前AI 评分58
AI 导读
Artificial Analysis 发布 Intelligence Index v5，新增 FrontierCode 2.0 和 Terminal-Bench-Science 两项基准，并升级 HLE-Diamond、AA-Omniscience v1.1 和 CritPt v2，60% 的指数改为基于私有测试集或留出答案。榜单中 Claude Opus 5.5（max）以 58 分居首，GPT-6 Astra（max，57）和 GPT-6.1 Sol（max，55）紧随其后，Gemini 4 Argon（high）以 50 分排在后面。开源权重模型与榜首的差距从 3 分扩大到 12 分，Kimi K3.1 Pro 以 46 分领跑开源权重模型但权重尚未发布，已发布权重中 DeepSeek V4.1 Flash 1017（max）和 GLM-5.3（max）以 32 分领先。前十模型中每任务成本相差超过 13 倍，GPT-6.1 Terra（max）最低为 0.96 美元，Claude Fable 5.1（max）最高为 13.04 美元。
正文
This is probably the best version so far
Announcing Artificial Analysis Intelligence Index v5, featuring 2 new benchmarks and 3 upgrades. For the first time, the majority of the Index is built on private datasets The Artificial Analysis Intelligence Index is our composite measure of model capabilities across tasks reflecting real-world usage today. v5 is our biggest upgrade since v4 launched in January. With v5, 60% of the Index is now based on evaluations with private test sets or held-out answers. Alongside Intelligence Index v5, we’re launching the Artificial Analysis Progress Index v1, which tracks model capability over time on one continuous scale. New to the Intelligence Index: ➤ FrontierCode 2.0: Cognition's newly-launched private benchmark of real-world coding tasks, graded on whether a repository maintainer would merge the agent's change ➤ Terminal-Bench-Science: 70 agentic scientific research tasks, run in a terminal environment Upgraded: ➤ HLE-Diamond (replacing Humanity's Last Exam): a refined 1,000-question version of Humanity's Last Exam, split evenly between reasoning and knowledge questions ➤ AA-Omniscience v1.1: An updated dataset with saturated and public set questions removed, new questions added, and ambiguous or erroneous questions revised ➤ CritPt v2: a private, 40-question hard subset of CritPt v2, revised by the CritPt authors and run with a code-execution tool Staying in the Index: AA-Briefcase, AutomationBench-AA, GDP.pdf and Terminal-Bench 4.0 Removed from the Index: GDPval-AA v2.1, SciCode, and AA-LCR v1.1 Key results: ➤ Claude Opus 5.5 (max) leads at 58, ahead of GPT-6 Astra (max, 57) and GPT-6.1 Sol (max, 55): Anthropic and OpenAI hold the top five models. Gemini 4 Argon (high) is next at 50 ➤ The open weights gap widens from 3 points to 12: Kimi K3.1 Pro (weights not yet released) is the top open weights model at 46. Among released weights, DeepSeek V4.1 Flash 1017 (max) and GLM-5.3 (max) lead at 32 - 26 points behind the leader and below Claude Haiku 5.5 (max, 36) ➤ Cost per task varies by more than 13x among the leading models: of the 10 highest-scoring models shown, GPT-6.1 Terra (max) is the cheapest at $0.96 per Intelligence Index task and Claude Fable 5.1 (max) the most expensive at $13.04在 X 查看被引用的帖子
来源：Lisan al Gaib · x.com