Indicators / series
metr.gpt_4o_inspect.horizon_80.pt
Source: METR time horizons (v1.1) (METR) · METR; analysis code MIT at https://github.com/METR/eval-analysis-public · CSV
METR, Measuring AI Ability to Complete Long Tasks (Horizon v1.1)
| id | value | grade | as of date | published date | tier | audited vs reported | extraction method | review status | retrieved at | http status | content hash | supersedes id | url | flags |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 2dc1a032ed30619b | 1.27 min (0.56–3.02) | grade A, evidence tier 1 | 2024-05-13 | 2026-09-10 | 1 | reported | api | approved | 2026-09-10T00:51:13.090038Z | 200 | aae31902b051 | — | source page |
Raw snippets and dispute text
- 2dc1a032ed30619b {"gpt_4o_inspect": {"p80_horizon_length": {"ci_high": 3.01517, "ci_low": 0.562997, "estimate": 1.267009}, "release_date": "2024-05-13"}}