METR Q4 2026 Time Horizon - Higher Lifecycle Cost Tasks (50%): leaderboard
METR's Q4 2026 capability update (20 November 2026): the length of task, in hours of expert human work, that a model completes 50% of the time, fitted across tasks of different lengths. Fitted only on the half of the pooled TH1.1 + TH2 tasks that are costlier than their length predicts to build, run and score, by a model's cost estimate. Models score about 2.9 times lower here than on the cheaper half. Unbounded; higher is better. Reasoning effort and scaffold are not stated per model.
Metric: 50% Time Horizon (hours). Source: metr.org. Saturation forecast: Around December 2027. 15 models tracked. Updated 21 Nov 2026.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-6 Astra | 23.97 | #10 |
| 2 | Claude Opus 5.5 | 20.79 | #9 |
| 3 | Claude Fable 5.1 | 13.16 | #20 |
| 4 | Claude Opus 5 | 12.83 | #26 |
| 5 | Claude Fable 5 | 11.35 | #33 |
| 6 | GPT-5.6 Sol | 9.53 | #37 |
| 7 | GPT-5.5 | 8.54 | #54 |
| 8 | Claude Opus 4.8 | 8.08 | #65 |
| 9 | Claude Opus 4.7 | 4.63 | #85 |
| 10 | GPT-5.4 | 3 | #135 |
| 11 | Claude Opus 4.6 | 2.83 | #113 |
| 12 | Claude Opus 4.5 | 2.2 | #160 |
| 13 | GPT-5 | 1.44 | #178 |
| 14 | O1 | 0.2064 | #403 |
| 15 | GPT-4o | 0.0613 | #751 |
No result here: #1 Claude Fable 5.2, #3 Gemini 4 Neon, #4 GPT-6.2 Astra.
Interactive version: theaggregate.ai/benchmark?slug=metr-q4-2026-time-horizon-higher-lifecycle-cost-tasks-50 · How It Works · Data refreshed daily, snapshot 2026-11-21.