corpus.blog
41554 blogs · 4,417,066 posts Claim your blog
Record · corpus.blog/posts/01a07df3-ecc9-70ed-9df1-2ee53606a157

Understanding the 4 Main Approaches to LLM Evaluation (From Scratch)

Ahead of AI · published 5 October 2025

A record is what was published and who pointed at it. The text of the post is not held here: read it at the source, or at its Wayback capture.

Read the post at magazine.sebastianraschka.com Wayback capture
3blogs citing
First cited
20 Oct 2025
Most recent
2 Sept 2026
Rank this month
not ranked
Links from this post
33
Words captured
6,805

Cited by

Blog
In the post
Date
blog.kjamistan.com
Privacy Evaluations for AI Systems Read at the source ↗
2 Sept 2026
@adlrocha Beyond The Code | Substack
@adlrocha - Beyond Benchmaxxing: Why the Future of AI is Inference-Time Search Read at the source ↗
4 Jan 2026
shostack.org
Prompt Engineering Requires Evaluation Read at the source ↗
20 Oct 2025

Links from this post

Link
Host
https://mng.bz/Nwr7
mng.bz
https://substackcdn.com/image/fetch/$s_!Q_QP!,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fb34a8123-ef28-48bb-8ea2-28404b08d013_2461x997.png
substackcdn.com
https://substackcdn.com/image/fetch/$s_!nwaB!,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fc26764a9-6a26-4467-bb03-74b6cd1ed72b_1050x363.png
substackcdn.com
https://substackcdn.com/image/fetch/$s_!WmmA!,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F8d5f7998-21be-4144-bfc2-57b2e0a4b1c4_1040x608.png
substackcdn.com
https://github.com/rasbt/reasoning-from-scratch/tree/main/chF/02_mmlu
github.com
Understanding and Implementing Qwen3 From Scratch Read at the source ↗
magazine.sebastianraschka.com
https://github.com/rasbt/reasoning-from-scratch/blob/main/reasoning_from_scratch/qwen3.py
github.com
https://github.com/rasbt/reasoning-from-scratch/blob/main/reasoning_from_scratch
github.com
https://github.com/rasbt/reasoning-from-scratch/blob/main/chF/02_mmlu/1_letter_matching.py
github.com
https://substackcdn.com/image/fetch/$s_!HSuI!,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F098958b6-4a5b-4070-a350-8f318abcede2_1815x1143.png
substackcdn.com
https://substackcdn.com/image/fetch/$s_!MM--!,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fe5fb712c-10f1-4240-b3e6-2cbf7ccfc356_1389x857.png
substackcdn.com
https://substackcdn.com/image/fetch/$s_!RL2q!,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F0304413b-aa78-4488-a157-841d6399d3e6_975x986.png
substackcdn.com
https://github.com/rasbt/reasoning-from-scratch/blob/main/ch03/01_main-chapter-code/ch03_main.ipynb
github.com
https://substackcdn.com/image/fetch/$s_!P2NG!,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F74860b8a-d12a-4781-8362-d5eb06feb389_1406x656.png
substackcdn.com
https://substackcdn.com/image/fetch/$s_!nm_T!,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F36c6779c-5eb0-4cfd-88fd-b1b68f44b227_1114x457.png
substackcdn.com
https://lmarena.ai/
lmarena.ai
https://substackcdn.com/image/fetch/$s_!m7Un!,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Fa1a1816e-790d-421c-a364-48efe66ae622_1600x1220.png
substackcdn.com
https://substackcdn.com/image/fetch/$s_!KhbK!,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F2eb7522f-34c1-4d0a-8f54-d5276a77e740_1115x818.png
substackcdn.com
https://en.wikipedia.org/wiki/Elo_rating_system
en.wikipedia.org
https://github.com/rasbt/reasoning-from-scratch/tree/main/chF/03_leaderboards
github.com
https://substackcdn.com/image/fetch/$s_!hCOf!,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F57300005-93c2-4984-b099-475e4c7d6aac_1301x688.png
substackcdn.com
https://substackcdn.com/image/fetch/$s_!o8kH!,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F4b646f80-a08d-40f4-ae65-eb7b850c7ccd_1503x1337.png
substackcdn.com
https://arxiv.org/abs/2405.08029
arxiv.org
https://ollama.com
ollama.com
https://github.com/ggerganov/llama.cpp
github.com
https://substackcdn.com/image/fetch/$s_!NeHY!,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F475023aa-2070-4533-9776-fba77b711052_911x1313.png
substackcdn.com
https://github.com/rasbt/reasoning-from-scratch/tree/main/chF/04_llm-judge
github.com
https://substackcdn.com/image/fetch/$s_!e5fC!,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F04869674-1018-4da5-b287-100920e21b9b_1332x864.png
substackcdn.com
https://substackcdn.com/image/fetch/$s_!vxlv!,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2Faacd21b7-bf77-4cdc-bdb4-efe254a7e1b1_1586x1317.png
substackcdn.com
https://amzn.to/4fqvn0D
amzn.to
https://substackcdn.com/image/fetch/$s_!RCl_!,f_auto,q_auto:good,fl_progressive:steep/https%3A%2F%2Fsubstack-post-media.s3.amazonaws.com%2Fpublic%2Fimages%2F27a118a0-5da6-4486-b1f0-3743754d0a77_8106x4044.webp
substackcdn.com
https://www.amazon.com/Build-Large-Language-Model-Scratch/dp/1633437167
amazon.com
https://huggingface.co/datasets/cais/mmlu
huggingface.co