List your company

Code Reasoning on LCB

62.46pass@1SCF-RKL
18.717630.073841.4352.7862Feb 12, 2026Feb 28, 2026Mar 16, 2026Apr 2, 2026Apr 18, 2026May 4, 2026May 21, 2026

Evaluation results

MethodLinks
SCF-RKLModels=Fuse2026.0262.46
w/o MergingModels=Math2026.0255.91
w/o MergingModels=Code2026.0255.2
SCEModels=Fuse2026.0244.35
Ties MergingModels=Fuse2026.0244.18
Dare Ties MergingModels=Fuse2026.0240.05
Task ArithmeticModels=Fuse2026.0238.53
Dare Task ArithmeticModels=Fuse2026.0238.53
Teacher-OPPOBase Model=Qwen3-4B-Instruct-2507, Optimization Framework=DAPO2026.0536.2
Teacher-OPPOBase Model=Qwen3-4B-Instruct-2507, Optimization Framework=GRPO2026.0535.4
Self-OPPOBase Model=Qwen3-4B-Instruct-2507, Optimization Framework=DAPO2026.0534.6
Self-OPPOBase Model=Qwen3-4B-Instruct-2507, Optimization Framework=GRPO2026.0534.2
DAPOBase Model=Qwen3-4B-Instruct-25072026.0532.8
SDPOBase Model=Qwen3-4B-Instruct-25072026.0532.4
GRPOBase Model=Qwen3-4B-Instruct-25072026.0531.5
Dr.GRPOBase Model=Qwen3-4B-Instruct-25072026.0531.4
SFTBase Model=Qwen3-4B-Instruct-25072026.0528.6
Teacher-OPPOBase Model=Phi-4-mini-instruct, Optimization Framework=DAPO2026.0528
Teacher-OPPOBase Model=Phi-4-mini-instruct, Optimization Framework=GRPO2026.0527.2
Self-OPPOBase Model=Phi-4-mini-instruct, Optimization Framework=DAPO2026.0526.5
Self-OPPOBase Model=Phi-4-mini-instruct, Optimization Framework=GRPO2026.0525.8
DAPOBase Model=Phi-4-mini-instruct2026.0524.2
SDPOBase Model=Phi-4-mini-instruct2026.0523.8
GRPOBase Model=Phi-4-mini-instruct2026.0523
Dr.GRPOBase Model=Phi-4-mini-instruct2026.0522.8
SFTBase Model=Phi-4-mini-instruct2026.0520.4