Checked fact 517417 Nov 2026Research
On SWE-Bench (277 tasks, six repositories, five agent-model combinations) the researchers report mean cost per task fell 18.4% to 30.9%, and pass@1 rose in four of the five combinations.
The exact words it rests on
TokenEconomizer lowered the average cost by 18.4–30.9%.
What the source said when we opened it, on 16 Nov 2026.
The source
TokenEconomizer: Learning from Experience to Make AI Coding Agents More Efficient
Checked
Checked by the notis newsroom on , against the source above.
In the story
Cite this fact
Anyone may quote this address. It does not change; if we correct the story, this page says so.