Benchmark
Frontier-CS
A benchmark for evaluating AI agent performance on frontier computer science algorithmic programming tasks.
Timeline (last 90 days)
Oct 1
AREX-2 scored 81.8 on MLE-bench Lite and 70.7 on Frontier-CS
Unverified50%
A benchmark for evaluating AI agent performance on frontier computer science algorithmic programming tasks.
AREX-2 scored 81.8 on MLE-bench Lite and 70.7 on Frontier-CS