Sleeping K2 V3 Error Analysis Scorecard 🧭 Explore model benchmarks and error analysis with interactive charts
Sleeping K2 V3 Error Analysis Scorecard 🧭 Explore model benchmarks and error analysis with interactive charts
CEPO: RLVR Self-Distillation using Contrastive Evidence Policy Optimization Paper • 2605.19436 • Published May 19 • 14