Technology · Culture · Change
Sign inJoin us
TechTrends NowFollow the next shiftTechnology · Culture · Change
← Latest news

From Dev.to

We Retracted Our Own 12.2 Benchmark. Here Is What Was Wrong With It.

TokenCap v1.6 shipped with a line we liked a lot: "12.2× fewer tokens, same answer." It came from benchmarks/run.js. It was wrong in five separate ways, and it is now retracted in docs/HONEST-NUMBERS....

Read the full report at Dev.to ↗