AI EVALUATION, IN CONTEXT.BY EQUALITY MACHINE
Benchmark Radar.Benchmarks. Model results. Original sources.
/

Artificial Analysis

AA-AnalystAgent

原始来源英文简介

Quantitative analysis on spreadsheets & documents

收录来源

已收录的评测资料

这条来源记录收录了 30 条数值成绩。来源区分了 30 个模型身份或配置。同一模型可能有多条记录；比较前请核对具体版本、工具和运行预算。 查看成绩及逐条证据 →

指标方向
数值越高越好

从这些资料开始

引用文档及日期（1）

目录采集于 2026-08-25，资料入口与字段反映当时保存的来源。

评测信息与证据

来源
Artificial Analysis
发布者
未收录
评测发布日期
未收录
采集日期
2026-08-25
模态
未收录

本站保留来源报告的结果，不代表独立复测。请先核对任务版本、评测协议、分数单位和报告日期；不同运行条件不能直接合并为统一排名。

报告成绩 30

按来源中的观察顺序展示，顺序不代表排名。日期保留原始精度。

模型数值单位协议报告日期与口径来源
Gemini 3.7 Flash (high)0.6未收录未收录2026-08-13 · model_announcementArtificial Analysis
Claude Opus 5 (Adaptive Reasoning, Max Effort)0.5375未收录未收录2026-07-24 · model_announcementArtificial Analysis
GPT-5.5 (xhigh)0.5未收录未收录2026-04-23 · model_announcementArtificial Analysis
Claude Fable 5 (Adaptive Reasoning, Max Effort, Opus 4.8 Fallback)0.4875未收录未收录2026-06-09 · model_announcementArtificial Analysis
GPT-5.6 Sol (max)0.475未收录未收录2026-07-09 · model_announcementArtificial Analysis
Claude Sonnet 5 (Adaptive Reasoning, Max Effort)0.4625未收录未收录2026-06-30 · model_announcementArtificial Analysis
Gemini 3.5 Flash (high)0.45未收录未收录2026-05-19 · model_announcementArtificial Analysis
Claude Opus 4.8 (Adaptive Reasoning, Max Effort)0.45未收录未收录2026-05-28 · model_announcementArtificial Analysis
Claude Opus 4.7 (Adaptive Reasoning, Max Effort)0.4375未收录未收录2026-04-16 · model_announcementArtificial Analysis
Gemini 3.1 Pro Preview0.4125未收录未收录2026-02-19 · model_announcementArtificial Analysis
Grok 4.6 (high)0.4125未收录未收录2026-08-12 · model_announcementArtificial Analysis
Kimi K3 (max)0.3875未收录未收录2026-07-16 · model_announcementArtificial Analysis
Grok 4.5 (high)0.35未收录未收录2026-07-08 · model_announcementArtificial Analysis
Inkling Small0.275未收录未收录2026-07-30 · model_announcementArtificial Analysis
DeepSeek V4 Flash (Reasoning, Max Effort)0.25未收录未收录2026-04-24 · model_announcementArtificial Analysis
Inkling (xhigh)0.2375未收录未收录2026-07-15 · model_announcementArtificial Analysis
MiMo-V2.5-Pro0.2未收录未收录2026-04-22 · model_announcementArtificial Analysis
Claude Sonnet 4.6 (Adaptive Reasoning, Max Effort)0.2未收录未收录2026-02-17 · model_announcementArtificial Analysis
Qwen3.7 Max0.1875未收录未收录2026-05-19 · model_announcementArtificial Analysis
DeepSeek V4 Pro (Reasoning, Max Effort)0.1875未收录未收录2026-04-24 · model_announcementArtificial Analysis
Claude 4.5 Haiku (Reasoning)0.15未收录未收录2025-10-15 · model_announcementArtificial Analysis
GPT-5.4 mini (xhigh)0.15未收录未收录2026-03-17 · model_announcementArtificial Analysis
Mistral Medium 3.50.125未收录未收录2026-04-29 · model_announcementArtificial Analysis
MiniMax-M2.70.1125未收录未收录2026-03-18 · model_announcementArtificial Analysis
MiniMax-M30.1未收录未收录2026-06-01 · model_announcementArtificial Analysis
Gemini 3.1 Flash-Lite0.0875未收录未收录2026-03-03 · model_announcementArtificial Analysis
Grok 4.3 (high)0.0875未收录未收录2026-04-30 · model_announcementArtificial Analysis
GPT-5.5 (Non-reasoning)0.075未收录未收录2026-04-23 · model_announcementArtificial Analysis
Nemotron 3 Ultra 550B A55B (Reasoning)0.0625未收录未收录2026-06-04 · model_announcementArtificial Analysis
Mistral Small 4 (Reasoning)0.0125未收录未收录2026-03-16 · model_announcementArtificial Analysis

相关评测探索

按共享资料或来源分类推荐，不代表同一评测或经审核的身份关联。

AA-Briefcase来源分类相同 →AutomationBench-AA来源分类相同 →EnterpriseOps-Gym-AA来源分类相同 →APEX-Agents-AA来源分类相同 →Terminal-Bench v2.1来源分类相同 →ITBench-AA来源分类相同 →τ³-Banking来源分类相同 →GDPval-AA v2 (normalized score)来源分类相同 →

继续阅读

工具与智能体评测推理与数学评测

继续探索

按这条记录的来源标签检索目录；搜索匹配不代表相同评测。

agentic →business →reasoning →Artificial Analysis · 全部记录 →