evaluation-framework · Source-linked discovery

lm-evaluation-harness

Widely used evaluation harness covering a broad collection of language-model tasks.

Open interactive record →
OriginEleutherAITopicsEvaluation integrity · General capabilityStatuscatalogued

Can support

Not independently assessed by FronteraEval yet.

Cannot support by itself

No inference beyond the upstream source should be made until the protocol is reviewed.

Original sources