test-local / README.md
dvilasuero's picture
Upload README.md with huggingface_hub
94c4a6b verified
metadata
title: Arc Easy
emoji: 📊
colorFrom: blue
colorTo: purple
sdk: docker
sdk_version: latest
pinned: false

arc_easy

This eval was run using evaljobs.

Command

evaljobs inspect_evals/arc_easy \
  --model hf-inference-providers/openai/gpt-oss-20b:fastest,hf-inference-providers/openai/gpt-oss-120b:fastest \
  --name test-local \
  --limit 1

Run with other models

To run this eval with a different model, use:

evaljobs inspect_evals/arc_easy \
  --model <your-model> \
  --name <your-name> \
  --flavor cpu-basic

Inspect eval command

The eval was executed with:

inspect eval-set inspect_evals/arc_easy \
  --model hf-inference-providers/openai/gpt-oss-20b:fastest,hf-inference-providers/openai/gpt-oss-120b:fastest \
  --limit 1 \
  --log-shared \
  --log-buffer 100