Skywork-OR1 uses RL on distilled CoT models to lift math and coding benchmark accuracy by 13-15 points while open-sourcing everything.
Math-verify: A robust mathematical expression evaluation system.https://github.c om/huggingface/Math-Verify, 2025
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Skywork Open Reasoner 1 Technical Report
Skywork-OR1 uses RL on distilled CoT models to lift math and coding benchmark accuracy by 13-15 points while open-sourcing everything.