{"schema":"postcutoff/event@1","as_of":"2026-11-22T13:32:00+01:00","url":"https://postcutoff.com/e/2026-01-29-metr-time-horizon-1-1/","md":"https://postcutoff.com/e/2026-01-29-metr-time-horizon-1-1/index.md","disclosure":{"written_by":"AI agents (Claude Opus 5.5 in Claude Code)","editor":"human editor","policy":"https://postcutoff.com/about/"},"license":null,"id":"2026-01-29-metr-time-horizon-1-1","date":"2026-01-29","date_precision":"day","short_title":"METR releases Time Horizon 1.1 with expanded long-task suite","deck":null,"takeaway":null,"category":"benchmark","category_label":"Benchmarks","importance":3,"confidence":"high","status":{"key":"confirmed","labels":["Confirmed"]},"sources":[{"n":1,"title":"METR: Time Horizon 1.1","url":"https://metr.org/blog/2026-1-29-time-horizon-1-1/","type":"official","group":"primary","domain":"metr.org"},{"n":2,"title":"METR: Task-completion time horizons of frontier AI models","url":"https://metr.org/time-horizons/","type":"official","group":"primary","domain":"metr.org"},{"n":3,"title":"METR: Clarifying limitations of time horizon","url":"https://metr.org/notes/2026-01-22-time-horizon-limitations/","type":"official","group":"primary","domain":"metr.org"}],"official":3,"filed":"2026-09-29","updated":"2026-09-29","orgs":["METR"],"title":"METR releases Time Horizon 1.1 with expanded long-task suite","summary":"METR updated its task-completion time-horizon methodology on 2026-01-29 (TH1.1), adding 34% more tasks (228 vs 170) and doubling 8h+ tasks (31 vs 14), tightening confidence intervals for frontier models; METR notes measurements above ~16 hours are unreliable with the current suite.","key_facts":["Tasks: 228 (TH1.1) vs 170 (TH1); tasks >=8 hours: 31 vs 14","Upper CI for Claude Opus 4.5 narrowed from 4.4x to 2.3x the point estimate","Measurements above 16 hours flagged as unreliable","Later 2026 measurements include GPT-5.3-Codex, Claude Opus 4.6 (Feb 20), GPT-5.4 (Apr 10), Gemini 3.1 Pro (Apr 15), early Claude Mythos Preview (May 8)","Community analyses suggest ~4-month doubling since 2024 vs 7 months 2019-2024"],"key_numbers":[],"tags":["agents","time-horizon","evaluation"],"science":null,"body_md":"## What happened\n\nMETR's time horizon — the human task length at which an AI succeeds 50% of the time — is the most-cited measure of agentic progress. TH1.1 extends the task suite to keep pace with models approaching day-long tasks.\n\n## Why it matters\n\nAs frontier horizons approach the top of the suite, METR's own caveat (unreliable >16h) signals the benchmark itself is near saturation.","disputed":[],"related":[],"people":[],"posts":[],"videos":[],"models":[],"changes":[{"date":"2026-09-29","type":"filed","text":"Created"}],"provenance":{"agents":[{"model":"Claude Opus 5.5","maker":"Anthropic","tool":"Claude Code"}],"filed":"2026-09-29","run":null,"sources_read":null,"updated":"2026-09-29","human_review":null,"version":{"date":"2026-10-04"}},"gaps":[{"model_id":"gpt-6-2-astra","name":"GPT-6.2 Astra","cutoff":"2026-05","days_after":null,"in_training_data":true},{"model_id":"claude-opus-5-5","name":"Claude Opus 5.5","cutoff":"2026-06","days_after":null,"in_training_data":true},{"model_id":"gemini-4-hydrogen","name":"Gemini 4 Hydrogen","cutoff":"2026-03","days_after":null,"in_training_data":true},{"model_id":"grok-4-7","name":"Grok 4.7","cutoff":"2026-05","days_after":null,"in_training_data":true}],"short_url":null}