白泽（Whitzard）女娲实验室 ↗
NUWANUWA INDEX

搜索 NUWA Index

研究 · 测量协议 · 评测结果 · 观点

English
← NUWA Index

评测档案

METR Time Horizons

以人类专家完成时间表示的任务难度。

METR · Anthropic / Time Horizon 1.1; page updated 2026-09-08 / Capability · 任务能力

来源与出处 ↓ 阅读研究记录 →

证据补充 · 2026-10-28

模型辅助整理 · 独立证据及双语编辑复核待完成。以下数值为来源发现或材料计数，与趋势结果序列分开保存。

解释跨度图时，应同时检查模型拟合版本、任务集是否接近饱和及人类时长测量。方法修订导致的估计变化不等于模型能力下降；跨度也不能直接换算成研发提速或连续自主运行时间。

关联阅读

NUWA 阅读关联；不据此声称原文引用、实验复现或成绩等价。

本次解释的来源
  • Impact of modeling assumptions on time horizon results · Summary; model correction; uncertainty table; text lines 00043,00069,00240Original resource captured 2026-10-28T07:24:45.348612+00:00; sha256:9695043f6347be4a67091843e5b34b1db63f1ab11ee6a7956edcf1094182bd20
  • Clarifying limitations of time horizon · Research note and limitations; text lines 00072Original resource captured 2026-10-28T07:24:45.640517+00:00; sha256:caec62e207534efe7e6fbcb55bb6a12459264f8591145eef7d9cac011c571860

下载来源证据 · JSON ↓

跨报告监测

已发表证据

METR Time Horizons · 50% 任务完成跨度

跨来源报告的已发表测量。任务范围通过注释区分，配置差异保留在每条观测中。

26 条观测 · 21 已定位日期

● 条件匹配◇ 配置差异□ 部分条件未披露
50% 成功率任务跨度 (min) Claude Mythos Preview (early) · METR scaffold Claude Opus 4.6 · METR scaffold Gemini 3.1 Pro · METR scaffold GPT-5.2 · METR scaffold GPT-5.3-Codex · METR scaffold GPT-5.4 · METR scaffold Claude Opus 4.5 · METR scaffold Gemini 3 Pro · METR scaffold GPT-5.1 Codex Max · METR scaffold GPT-5 · METR scaffold o3 · METR scaffold Claude Opus 4.1 · METR scaffold 0 1,000 2,000 3,000 4,000 1,044.78 min 718.81 min 384.15 min 352.25 min 349.53 min 341.74 min 292.99 min 224.33 min 223.71 min 203.01 min 119.73 min 100.47 min

5 条观测尚无已核实的模型发布日期，可在数据与系统结果中查看。

选择图中数据点或表格行，查看条件与出处。

26 条观测

测量值与来源条件
系统／模型结果条件状态任务／条件评测方／报告日期
Claude Mythos Preview (early) · METR scaffoldClaude Mythos Preview (early)1,044.78 min50% 成功率任务跨度Source 95% CI [508.876789, 3304.261235] min条件不完整METR-Horizon-v1.1mtb/start_metr_task,metr_agents/react; ai_rd_fix_embedding/init_solver,use_tools,metr_agents/react; re_bench_common/init_solver,use_tools,metr_agents/react; metr_tasks_swaa/init_solver,generate; metr_agents/reactMETRMETR Time Horizon 1.1 — source data发布 —报告 —
Claude Opus 4.6 · METR scaffoldClaude Opus 4.6718.81 min50% 成功率任务跨度Source 95% CI [316.685725, 3633.786163] min条件不完整METR-Horizon-v1.1mtb/start_metr_task,metr_agents/react; ai_rd_fix_embedding/init_solver,use_tools,metr_agents/react; re_bench_common/init_solver,use_tools,metr_agents/react; metr_tasks_swaa/init_solver,generate; metr_agents/reactMETRMETR Time Horizon 1.1 — source data发布 2026-02-05报告 —
Gemini 3.1 Pro · METR scaffoldGemini 3.1 Pro384.15 min50% 成功率任务跨度Source 95% CI [233.50073, 694.750898] min条件不完整METR-Horizon-v1.1mtb/start_metr_task,triframe_inspect/triframe_agent; ai_rd_fix_embedding/init_solver,use_tools,triframe_inspect/triframe_agent; re_bench_common/init_solver,use_tools,triframe_inspect/triframe_agent; metr_tasks_swaa/init_solver,generate; triframe_inspect/triframe_agentMETRMETR Time Horizon 1.1 — source data发布 2026-02-19报告 —
GPT-5.2 · METR scaffoldGPT-5.2352.25 min50% 成功率任务跨度Source 95% CI [198.067494, 815.177445] min条件不完整METR-Horizon-v1.1mtb/start_metr_task,triframe_inspect/triframe_agent; ai_rd_fix_embedding/init_solver,use_tools,triframe_inspect/triframe_agent; re_bench_common/init_solver,use_tools,triframe_inspect/triframe_agent; metr_tasks_swaa/init_solver,generate; triframe_inspect/triframe_agentMETRMETR Time Horizon 1.1 — source data发布 2025-12-11报告 —
GPT-5.3-Codex · METR scaffoldGPT-5.3-Codex349.53 min50% 成功率任务跨度Source 95% CI [194.913134, 816.351994] min条件不完整METR-Horizon-v1.1mtb/start_metr_task,triframe_inspect/triframe_agent; ai_rd_fix_embedding/init_solver,use_tools,triframe_inspect/triframe_agent; re_bench_common/init_solver,use_tools,triframe_inspect/triframe_agent; metr_tasks_swaa/init_solver,generate; triframe_inspect/triframe_agentMETRMETR Time Horizon 1.1 — source data发布 2026-02-05报告 —
GPT-5.4 · METR scaffoldGPT-5.4341.74 min50% 成功率任务跨度Source 95% CI [186.581591, 768.779526] min条件不完整METR-Horizon-v1.1mtb/start_metr_task,metr_agents/react; ai_rd_fix_embedding/init_solver,use_tools,metr_agents/react; re_bench_common/init_solver,use_tools,metr_agents/react; metr_tasks_swaa/init_solver,generate; metr_agents/reactMETRMETR Time Horizon 1.1 — source data发布 2026-03-05报告 —
Claude Opus 4.5 · METR scaffoldClaude Opus 4.5292.99 min50% 成功率任务跨度Source 95% CI [161.717714, 623.704698] min条件不完整METR-Horizon-v1.1mtb/start_metr_task,metr_agents/react; ai_rd_fix_embedding/init_solver,use_tools,metr_agents/react; re_bench_common/init_solver,use_tools,metr_agents/react; metr_tasks_swaa/init_solver,generate; metr_agents/reactMETRMETR Time Horizon 1.1 — source data发布 2025-11-24报告 —
Gemini 3 Pro · METR scaffoldGemini 3 Pro224.33 min50% 成功率任务跨度Source 95% CI [139.565157, 379.235434] min条件不完整METR-Horizon-v1.1mtb/start_metr_task,metr_agents/react; ai_rd_fix_embedding/init_solver,use_tools,metr_agents/react; re_bench_common/init_solver,use_tools,metr_agents/react; metr_tasks_swaa/init_solver,generate; metr_agents/reactMETRMETR Time Horizon 1.1 — source data发布 2025-11-18报告 —
GPT-5.1 Codex Max · METR scaffoldGPT-5.1 Codex Max223.71 min50% 成功率任务跨度Source 95% CI [134.31077, 396.206723] min条件不完整METR-Horizon-v1.1mtb/start_metr_task,triframe_inspect/triframe_agent; ai_rd_fix_embedding/init_solver,use_tools,triframe_inspect/triframe_agent; re_bench_common/init_solver,use_tools,triframe_inspect/triframe_agent; metr_tasks_swaa/init_solver,generate; triframe_inspect/triframe_agentMETRMETR Time Horizon 1.1 — source data发布 2025-11-19报告 —
GPT-5 · METR scaffoldGPT-5203.01 min50% 成功率任务跨度Source 95% CI [112.641357, 405.551565] min条件不完整METR-Horizon-v1.1mtb/start_metr_task,triframe_inspect/triframe_agent; ai_rd_fix_embedding/init_solver,use_tools,triframe_inspect/triframe_agent; re_bench_common/init_solver,use_tools,triframe_inspect/triframe_agent; metr_tasks_swaa/init_solver,generate; triframe_inspect/triframe_agentMETRMETR Time Horizon 1.1 — source data发布 2025-08-07报告 —
o3 · METR scaffoldo3119.73 min50% 成功率任务跨度Source 95% CI [74.615398, 190.943818] min条件不完整METR-Horizon-v1.1mtb/start_metr_task,triframe_inspect/triframe_agent; ai_rd_fix_embedding/init_solver,use_tools,triframe_inspect/triframe_agent; re_bench_common/init_solver,use_tools,triframe_inspect/triframe_agent; metr_tasks_swaa/init_solver,generate; triframe_inspect/triframe_agentMETRMETR Time Horizon 1.1 — source data发布 2025-04-16报告 —
Claude Opus 4.1 · METR scaffoldClaude Opus 4.1100.47 min50% 成功率任务跨度Source 95% CI [59.272391, 159.451918] min条件不完整METR-Horizon-v1.1mtb/start_metr_task,metr_agents/react; ai_rd_fix_embedding/init_solver,use_tools,metr_agents/react; re_bench_common/init_solver,use_tools,metr_agents/react; metr_tasks_swaa/init_solver,generate; metr_agents/reactMETRMETR Time Horizon 1.1 — source data发布 2025-08-05报告 —
Claude Opus 4 · METR scaffoldClaude Opus 4100.37 min50% 成功率任务跨度Source 95% CI [59.994073, 163.454074] min条件不完整METR-Horizon-v1.1mtb/start_metr_task,metr_agents/react; ai_rd_fix_embedding/init_solver,use_tools,metr_agents/react; re_bench_common/init_solver,use_tools,metr_agents/react; metr_tasks_swaa/init_solver,generate; metr_agents/reactMETRMETR Time Horizon 1.1 — source data发布 2025-05-22报告 —
Claude 3.7 Sonnet · METR scaffoldClaude 3.7 Sonnet60.39 min50% 成功率任务跨度Source 95% CI [33.006168, 104.226017] min条件不完整METR-Horizon-v1.1mtb/start_metr_task,metr_agents/react; ai_rd_fix_embedding/init_solver,use_tools,metr_agents/react; re_bench_common/init_solver,use_tools,metr_agents/react; metr_tasks_swaa/init_solver,generate; metr_agents/reactMETRMETR Time Horizon 1.1 — source data发布 2025-02-24报告 —
o1 · METR scaffoldo138.83 min50% 成功率任务跨度Source 95% CI [21.164512, 64.95249] min条件不完整METR-Horizon-v1.1mtb/start_metr_task,triframe_inspect/triframe_agent; ai_rd_fix_embedding/init_solver,use_tools,triframe_inspect/triframe_agent; re_bench_common/init_solver,use_tools,triframe_inspect/triframe_agent; metr_tasks_swaa/init_solver,generate; triframe_inspect/triframe_agentMETRMETR Time Horizon 1.1 — source data发布 2024-12-05报告 —
Claude 3.5 Sonnet (October 2024) · METR scaffoldClaude 3.5 Sonnet (October 2024)20.52 min50% 成功率任务跨度Source 95% CI [10.144026, 40.82028] min条件不完整METR-Horizon-v1.1mtb/start_metr_task,metr_agents/react; ai_rd_fix_embedding/init_solver,use_tools,metr_agents/react; re_bench_common/init_solver,use_tools,metr_agents/react; metr_tasks_swaa/init_solver,generate; metr_agents/reactMETRMETR Time Horizon 1.1 — source data发布 2024-10-22报告 —
o1-preview · METR scaffoldo1-preview20.33 min50% 成功率任务跨度Source 95% CI [11.716193, 33.379877] min条件不完整METR-Horizon-v1.1duetMETRMETR Time Horizon 1.1 — source data发布 2024-09-12报告 —
Claude 3.5 Sonnet (June 2024) · METR scaffoldClaude 3.5 Sonnet (June 2024)11.4 min50% 成功率任务跨度Source 95% CI [5.489734, 22.384214] min条件不完整METR-Horizon-v1.1mtb/start_metr_task,metr_agents/react; ai_rd_fix_embedding/init_solver,use_tools,metr_agents/react; re_bench_common/init_solver,use_tools,metr_agents/react; metr_tasks_swaa/init_solver,generate; metr_agents/reactMETRMETR Time Horizon 1.1 — source data发布 2024-06-20报告 —
GPT-4o · METR scaffoldGPT-4o6.99 min50% 成功率任务跨度Source 95% CI [4.001482, 12.905741] min条件不完整METR-Horizon-v1.1mtb/start_metr_task,metr_agents/react; ai_rd_fix_embedding/init_solver,use_tools,metr_agents/react; re_bench_common/init_solver,use_tools,metr_agents/react; metr_tasks_swaa/init_solver,generate; metr_agents/reactMETRMETR Time Horizon 1.1 — source data发布 2024-05-13报告 —
GPT-4 November 2023 · METR scaffoldGPT-4 November 20234.04 min50% 成功率任务跨度Source 95% CI [1.866859, 8.443226] min条件不完整METR-Horizon-v1.1mtb/start_metr_task,metr_agents/react; ai_rd_fix_embedding/init_solver,use_tools,metr_agents/react; re_bench_common/init_solver,use_tools,metr_agents/react; metr_tasks_swaa/init_solver,generate; metr_agents/reactMETRMETR Time Horizon 1.1 — source data发布 2023-11-06报告 —
GPT-4 · METR scaffoldGPT-43.99 min50% 成功率任务跨度Source 95% CI [1.93292, 7.995283] min条件不完整METR-Horizon-v1.1modular-publicMETRMETR Time Horizon 1.1 — source data发布 2023-03-14报告 —
Claude 3 Opus · METR scaffoldClaude 3 Opus3.95 min50% 成功率任务跨度Source 95% CI [1.706313, 8.76484] min条件不完整METR-Horizon-v1.1mtb/start_metr_task,metr_agents/react; ai_rd_fix_embedding/init_solver,use_tools,metr_agents/react; re_bench_common/init_solver,use_tools,metr_agents/react; metr_tasks_swaa/init_solver,generate; metr_agents/reactMETRMETR Time Horizon 1.1 — source data发布 2024-03-04报告 —
GPT-4 Turbo · METR scaffoldGPT-4 Turbo3.73 min50% 成功率任务跨度Source 95% CI [1.980046, 6.736613] min条件不完整METR-Horizon-v1.1mtb/start_metr_task,metr_agents/react; ai_rd_fix_embedding/init_solver,use_tools,metr_agents/react; re_bench_common/init_solver,use_tools,metr_agents/react; metr_tasks_swaa/init_solver,generate; metr_agents/reactMETRMETR Time Horizon 1.1 — source data发布 —报告 —
GPT-3.5 Turbo Instruct · METR scaffoldGPT-3.5 Turbo Instruct0.6 min50% 成功率任务跨度Source 95% CI [0.255148, 1.115905] min条件不完整METR-Horizon-v1.1modular-publicMETRMETR Time Horizon 1.1 — source data发布 —报告 —
GPT-3 davinci-002 · METR scaffoldGPT-3 davinci-0020.14 min50% 成功率任务跨度Source 95% CI [0.093319, 0.221209] min条件不完整METR-Horizon-v1.1modular-publicMETRMETR Time Horizon 1.1 — source data发布 —报告 —
GPT-2 · METR scaffoldGPT-20.05 min50% 成功率任务跨度Source 95% CI [0.009994, 0.141825] min条件不完整METR-Horizon-v1.1—METRMETR Time Horizon 1.1 — source data发布 —报告 —

实际评测方: METR
报告发布方: METR

METR Time Horizon 1.1 来源已停止积极更新，最后更新于 2026 年 9 月 8 日。超过 16 小时的估计超出其可靠测量范围。

任务与测量

Benchmark 协议档案

任务／对象
在脚手架下完成软件任务的 AI 智能体
测量目标
软件任务分布上的拟合成功概率。
评分／结果口径
50% 成功率任务跨度 · 以人类专家分钟数计量、成功概率为 50% 和 80% 时的估计任务难度。
解释边界
该公开页面已停止持续更新；时间范围不是智能体运行时长或通用自动化指标。

一项已报告评测

来源评测 Claude 3.5 Sonnet (June 2024) · METR scaffold · METR-Horizon-v1.1.

报告指标: 50% 成功率任务跨度 · 11.40 min.

以人类专家分钟数计量、成功概率为 50% 和 80% 时的估计任务难度。 任务数和权重受来源任务及脚手架覆盖影响，见方法说明。

以人类专家分钟数计量、成功概率为 50% 和 80% 时的估计任务难度。

测量档案 · NUWA 解读

档案区分来源方法阅读与既有目录信息；已经公开不代表完成独立证据复核或双语编辑复核。

测量构念
以成功的人类基线用时衡量难度时，不同模型版本能够完成的软件任务范围如何变化？
任务与样本
论文结合 HCAST 软件任务、RE-Bench 研究工程任务和软件原子操作。多数任务由人类基线确定用时，部分任务使用研究者估计。连续评分按任务阈值转为二元成功；逻辑回归把成功率与人类用时的对数关联，其中点定义 50% 任务跨度，并按任务族加权。
判分与失效情形
终点是在给定成功概率下拟合的人类任务时长。50% 与 80% 跨度对应不同可靠性要求；后续 METR 1.1 模型的结果和不确定性属于独立版本的来源序列。
系统条件
论文结合 HCAST 软件任务、RE-Bench 研究工程任务和软件原子操作。多数任务由人类基线确定用时，部分任务使用研究者估计。连续评分按任务阈值转为二元成功；逻辑回归把成功率与人类用时的对数关联，其中点定义 50% 任务跨度，并按任务族加权。
统计含义
逻辑回归依赖人类时长与任务族加权；原论文区间和后续看板的不确定性分别保留各自版本方法。
效度与解释
用时取决于专业经验和上下文；维护者与外部承包者的时长可能明显不同。自动评分、主要静态的环境缺少许多资源约束、交互和高代价错误。阈值、加权均是建模选择，原论文与后续 1.1 看板不能视为完全相同的任务集。
适用研究问题
模型建议：用跨度选择任务难度及可靠性目标，附上任务集版本与区间，并独立核查干预响应。

跨报告证据

相同 Benchmark 名称可能对应不同任务、计分规则和系统配置。各来源分别保留，比较组说明具体对齐了哪些条件。

METR

METR Time Horizon 1.1 — source data →

实际评测方: METR

26 条结果记录 · 26 个报告系统名称

协议与比较依据 (12)
任务完成跨度 · 50% 成功率任务跨度source-report · 范围已审查
任务完成跨度 · 80% 成功率任务跨度source-report · 范围已审查
METR Time Horizons：50% 成功率任务跨度 · METRsource-report · 范围已审查
METR Time Horizons：50% 成功率任务跨度 · METRsource-report · 范围已审查
METR Time Horizons：50% 成功率任务跨度 · METRsource-report · 范围已审查
METR Time Horizons：50% 成功率任务跨度 · METRsource-report · 范围已审查
METR Time Horizons：50% 成功率任务跨度 · METRsource-report · 范围已审查
METR Time Horizons：80% 成功率任务跨度 · METRsource-report · 范围已审查
METR Time Horizons：80% 成功率任务跨度 · METRsource-report · 范围已审查
METR Time Horizons：80% 成功率任务跨度 · METRsource-report · 范围已审查
METR Time Horizons：80% 成功率任务跨度 · METRsource-report · 范围已审查
METR Time Horizons：80% 成功率任务跨度 · METRsource-report · 范围已审查
原始来源图表与材料
METR Time Horizons — Figure 3
Figure 3 · 原文 Figure 3。请结合下方的协议范围与局限阅读。 查看原图 ↗

评估出处

METR Time Horizon 1.1 → · 外部报告

相关研究问题

参考文献

  1. [1] OpenAI — introducing gpt 5 4 ; Publication date and availability section; Parameter counts not disclosed in launch article
  2. [2] Claude Opus 4.6 — Anthropic ; Publication date and availability section; Official launch article; parameter counts not disclosed
  3. [3] OpenAI — introducing gpt 5 ; Publication date and availability section; Parameter counts not disclosed in launch article
  4. [4] Introducing Claude 4 — Anthropic ; Publication date and availability section; Official launch article; parameter counts not disclosed
  5. [5] Claude 3.5 Sonnet on Vertex AI ; June 20, 2024: newly released model now generally available on Vertex AI
  6. [6] Computer use, Claude 3.5 Sonnet, and Claude 3.5 Haiku — Anthropic ; Publication date and availability section; Official launch article; parameter counts not disclosed
  7. [7] Claude 3.7 Sonnet and Claude Code — Anthropic ; Publication date and availability section; Official launch article; parameter counts not disclosed
  8. [8] Introducing the next generation of Claude — Anthropic ; Publication date and availability section; Official launch article; parameter counts not disclosed
  9. [9] Claude Opus 4.1 — Anthropic ; Publication date and availability section; Official launch article; parameter counts not disclosed
  10. [10] Introducing Claude Opus 4.5 — Anthropic ; Publication date and availability section; Official launch article; parameter counts not disclosed
  11. [11] OpenAI — introducing gpt 5 3 codex ; Publication date and availability section; Parameter counts not disclosed in launch article
  12. [12] Gemini 3: Introducing the latest Gemini AI model from Google ; Publication date and availability section; Official launch article; parameter counts not disclosed
  13. [13] Gemini 3.1 Pro: Announcing our latest Gemini AI model ; Publication date and availability section; Official launch article; parameter counts not disclosed
  14. [14] OpenAI — gpt 4 research ; Publication date and availability section; Parameter counts not disclosed in launch article
  15. [15] OpenAI DevDay ; Dated launch: GPT-4 Turbo preview available today
  16. [16] OpenAI — hello gpt 4o ; Publication date and availability section; Parameter counts not disclosed in launch article
  17. [17] OpenAI — gpt 5 1 codex max ; Publication date and availability section; Parameter counts not disclosed in launch article
  18. [18] OpenAI — introducing gpt 5 2 ; Publication date and availability section; Parameter counts not disclosed in launch article
  19. [19] OpenAI — introducing chatgpt pro ; Publication date and availability section; Parameter counts not disclosed in launch article
  20. [20] OpenAI — introducing openai o1 preview ; Publication date and availability section; Parameter counts not disclosed in launch article
  21. [21] OpenAI — introducing o3 and o4 mini ; Publication date and availability section; Parameter counts not disclosed in launch article
  22. [22] METR Time Horizon 1.1 — source data ; results.claude_3_5_sonnet_20240620_inspect; results.claude_3_5_sonnet_20241022_inspect; results.claude_3_7_sonnet_inspect
  23. [23] Thomas Kwa, Ben West 等. Task-Completion Time Horizons of Frontier AI Models. 2026-09-08
  24. [24] Thomas Kwa, Ben West 等. Measuring AI Ability to Complete Long Software Tasks. 2026-09-08 ; Author affiliations on the original paper title page; Figure 3