Agentic AI Atlasby a5c.ai
/
GitHubDocsDiscord
iiRecord
Agentic AI Atlas · EleutherAI lm-evaluation-harness
eval-harness:lm-eval-harnessa5c.ai
II.
EvalHarness overview

eval-harness:lm-eval-harness

Reference · live

EleutherAI lm-evaluation-harness overview

Reference harness for benchmark suites such as MMLU, ARC, HellaSwag, GSM8K. Drives the Open LLM Leaderboard.

EvalHarnessOutgoing · 0Incoming · 1

Attributes

displayName
EleutherAI lm-evaluation-harness
harnessKind
lm-eval-harness
homepageUrl
https://github.com/EleutherAI/lm-evaluation-harness
description
Reference harness for benchmark suites such as MMLU, ARC, HellaSwag, GSM8K. Drives the Open LLM Leaderboard.

Outgoing edges

None.

Incoming edges

uses_harness1