HOT RADAR
llmHEAT 12.9°

AI CURATED HOT STORY · 11/11/2026

Berkeley Study Finds Model Routing Cuts Costs Up to 25x

1 reports archived1 independent sourcesupdated 11/11/2026, 01:37:37
Synthesis & Latest Updates
1 Sources Cross-Validated

UC Berkeley and partner labs released a large-scale model routing study spanning 452 candidate models and policies across 25 benchmarks, totaling 374,401 scored runs. Routers deliver their value mainly by shifting work to cheaper models, averaging 8.82x more quality per unit cost with under 0.5 points lost; on coding tasks routing reached 25.5x the cost efficiency of always calling Opus 4.6 at a 0.44-point loss. Yet learned routers gained only 0.3 points over the best single model, far below the 5.4-point theoretical ceiling.

LATEST/UC Berkeley and partner labs released a large-scale model routing study spanning 452 candidate models and policies across 25 benchmarks, totaling 374,401 scored runs. Routers deliver their value mainly by shifting work to cheaper models, averaging 8.82x more quality per unit cost with under 0.5 points lost; on coding tasks routing reached 25.5x the cost efficiency of always calling Opus 4.6 at a 0.44-point loss. Yet learned routers gained only 0.3 points over the best single model, far below the 5.4-point theoretical ceiling.

Hourly heat curve

10 fully observed hours
Now
12.9
Peak
16.202:00
24h change
–

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

Coverage timeline

Total 1 reports · Latest first