List your company

Algorithm Synthesis on Novel Hard Benchmark 15 problems version 2

7Correct Count (out of 15)Reflexion
2.843.9256.08Jun 29, 2026

Evaluation results

MethodLinks
ReflexionSource=version 22026.06786
AlgoSkill-MCTSSource=version 22026.067100
MapCoderSource=prior-only2026.06650
CoTSource=version 22026.064100
Self-RefineSource=version 22026.064—
AlgoSkill-GreedySource=version 22026.064100
Direct LLMSource=version 22026.063100