Kaggle Benchmarks
A benchmark hosting and execution service provided by the Kaggle platform, supporting researchers in building, running, and sharing model evaluation benchmarks.
Timeline (last 90 days)
This benchmark uses 10 original short documents of 200 to 250 words each, with 18 planted anomalies, 37 scoring entries in total (18 dirty and 19 clean), testing 13 models with 74 prompts per model.
The benchmark is built on the Kaggle Benchmarks platform; each model is required to answer 287 scored questions spanning five dimensions: numbers, verbs, translation, cloze, and error correction.
All Facts (2)
This benchmark uses 10 original short documents of 200 to 250 words each, with 18 planted anomalies, 37 scoring entries in total (18 dirty and 19 clean), testing 13 models with 74 prompts per model.
50%UnverifiedThe benchmark is built on the Kaggle Benchmarks platform; each model is required to answer 287 scored questions spanning five dimensions: numbers, verbs, translation, cloze, and error correction.
50%