Indicators / series
metr.claude_3_5_sonnet_20241022_inspect.horizon_50.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 |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 1963199165cd8c93 | 20.5 min (10.1–40.8) | grade A, evidence tier 1 | 2024-10-22 | 2026-09-10 | 1 | reported | api | approved | 2026-09-10T00:51:13.090038Z | 200 | aae31902b051 | — | source page |
Raw snippets and dispute text
- 1963199165cd8c93 {"claude_3_5_sonnet_20241022_inspect": {"p50_horizon_length": {"ci_high": 40.82028, "ci_low": 10.144026, "estimate": 20.522872}, "release_date": "2024-10-22"}}