[KongchangAI]
BenchmarkRLMEval子集

RLMEval

An evaluation benchmark containing a theoretical computer science-focused subset, used to measure models' pass@1 performance on mathematical reasoning tasks.

Timeline (last 90 days)

Nov 17

Turing Agent achieved an overall pass@1 score of 83% on the TCS-focused RLMEval subset.

Unverified50%

All Facts (1)

Source Articles