BenchmarkAA-Briefcase
AA-Briefcase
An adversarial model evaluation benchmark released by Artificial Analysis that uses an Elo rating mechanism to measure the relative performance of models on practical tasks.
Timeline (last 90 days)
Oct 22
The Ling-3.1-flash 1019 version raised its Elo score on AA-Briefcase from about 1400 to 1524.
Unverified50%
Oct 22
AA-Briefcase adopts the Elo rating mechanism, dynamically adjusting scores based on win-loss results from pairwise model matchups.
Unverified50%
Oct 12
Mistral Large 4 scores 59.9% on AutomationBench (657 business processes) and achieves 1393 Elo on AA-Briefcase.
Expired50%