---
title: "Comment by Andrew on \"Benchmark the Model–Harness Pair, Not the Model\" | Hashnode"
description: "Your row delta on tokens mixes the scaffold with what each ledger counted as a token. That mix is two bills stacked."
url: "https://hashnode.com/posts/3-benchmark-the-model-harness-pair/6a8bf9b917de0e315d9dcde4/comment/6a8d16e88a9885c4cc1823ff"
---

[Discussion](https://hashnode.com/posts/3-benchmark-the-model-harness-pair/6a8bf9b917de0e315d9dcde4)

Comment [Benchmark the Model–Harness Pair, Not the Model](https://hashnode.com/posts/3-benchmark-the-model-harness-pair/6a8bf9b917de0e315d9dcde4)

[Andrew](https://hashnode.com/@rizzdev)

[Aug 25](https://hashnode.com/posts/3-benchmark-the-model-harness-pair/6a8bf9b917de0e315d9dcde4/comment/6a8d16e88a9885c4cc1823ff)

Your row delta on tokens mixes the scaffold with what each ledger counted as a token. That mix is two bills stacked.

[Muhammad Azlaan Zubair](https://hashnode.com/@mdazlaanzubair)

[Aug 25](https://hashnode.com/posts/3-benchmark-the-model-harness-pair/6a8bf9b917de0e315d9dcde4/comment/6a8d16e88a9885c4cc1823ff#reply-6a8d64415cc32c7687b462b1)

Great callout. Ledger differences definitely add noise, and isolating accounting overhead from context growth is the right move for a cleaner analysis. Appreciate the feedback!