Every premium and members-only resource for $9.99/month, as a no-commitment subscription. See the plans

PalateKit

Sign in
Menu

Request a resource

Describe the resource you are missing in one sentence. We will email you when it is published.

0 / 280

A page, a video or an image online.

Unlock PalateKit

Unlock everything

Plan

Paying means accepting our terms of sale.

Secure payment by Stripe. Receipts and invoices sent by email.

Welcome back

Sign in to install, download or save this resource. A free account is enough for free resources.

Evaluating an LLM on more than 60 academic benchmarks v1.0.0

Use this resource to measure model quality on standard academic benchmarks and compare models

New

  • 494 downloads
  • 170 likes
  • 211 saves

Free

Install with the CLI

In a terminal, from the folder you want:

npx --yes palatekit@latest install llm-benchmark-evaluation-harness-2

With no option, the skill goes to ~/.agents/skills/; add --agent claude-code (or codex, cursor…) to target an agent.

First time: connect the CLI with

npx --yes palatekit@latest login

The agent guides you through installing lm-eval, running an evaluation on MMLU, GSM8K or HellaSwag, tracking progress during training and comparing several models. It works with Hugging Face, vLLM and APIs.

Mostly picked by

Updated November 2, 2026

Card for the “Evaluating an LLM on more than 60 academic benchmarks” skill

Details

Works in
Install guides
Generates with
Your agent's model
Licence
MIT

Similar resources

View all

What you get

  • SKILL.md: installation, standard evaluation and training progress tracking
  • references/benchmark-guide.md, custom-tasks.md, api-evaluation.md and distributed-eval.md: benchmark guide, custom tasks, API and distributed evaluation

Good fit for

  • You want to compare two models on a standard basis
  • You publish reproducible academic results

Not for

    Tags

    • evaluation
    • benchmarks
    • mmlu
    • comparison

    About

    You say

    “Evaluate Llama 2 7B on MMLU, GSM8K and HellaSwag, then compare it with my fine-tuned model.”

    Card for the “Evaluating an LLM on more than 60 academic benchmarks” skill

    Skill published by Orchestra Research under the MIT license, delivered in its original version.

    Show more

    How to use it

    1. Install the skill in your agent's skills folder
    2. Ask your agent to measure model quality on standard academic benchmarks and compare models
    3. Review and adjust the result

    Content preview

    Files

    • LICENSE1.1 KB
    • NOTICE-PALATEKIT.md0.5 KB
    • references/api-evaluation.md11.3 KB
    • references/benchmark-guide.md11 KB
    • references/custom-tasks.md13.4 KB
    • references/distributed-eval.md11.7 KB
    • SKILL.md12.1 KB

    Origin and licence

    Listed unmodified

    Author
    Orchestra Research
    Source
    github.com/orchestra-research/ai-research-skills/tree/773a52944ba4747a18bd4ae9ade53fff041adcbc/11-evaluation/lm-evaluation-harness
    Licence
    MIT

    Notice

    « evaluating-llms-harness » (Orchestra Research, MIT) livré dans sa version d'origine : fiche en français et en anglais par PalateKit.

    User reviews

    –

    No ratings yet

    Loading reviews…

    Delete your review?

    Your rating and comment will be removed from the page.