HOT RADAR
llmHEAT 8.5°

AI CURATED HOT STORY · 11/21/2026

METR Updates AI Task-Horizon Plot with Open-Ended Benchmarks

1 reports archived1 independent sourcesupdated 11/21/2026, 02:15:15
Synthesis & Latest Updates
1 Sources Cross-Validated

AI evaluation nonprofit METR has updated its widely cited time-horizon plot, adding longer and more open-ended tasks. The trend of frontier models doubling the length of tasks they can complete roughly every four months appears to hold, but models remain weaker on judgment-heavy work than on coding. METR cautions that open-ended evaluation is still far from settling whether, or how fast, automated AI R&D might arrive.

LATEST/AI evaluation nonprofit METR has updated its widely cited time-horizon plot, adding longer and more open-ended tasks. The trend of frontier models doubling the length of tasks they can complete roughly every four months appears to hold, but models remain weaker on judgment-heavy work than on coding. METR cautions that open-ended evaluation is still far from settling whether, or how fast, automated AI R&D might arrive.

Hourly heat curve

15 fully observed hours
Now
8.5
Peak
11.803:00
24h change
-28%

The line compares only sources observed throughout; gap hours are interpolated to keep the trend continuous.

Coverage timeline

Total 1 reports · Latest first