List your company

Mathematical Problem Solving on AIME 2024 (Accuracy (avg@k))

80.21Accuracy (avg@k)TRACE (FKL on Ky)
13.691630.960848.2365.4992May 11, 2026

Evaluation results

MethodLinks
TRACE (FKL on Ky)Backbone=Qwen3-8B, Symmetric Think evaluation=true2026.0580.21
TRACE (RKL on Ey)Backbone=Qwen3-8B, Symmetric Think evaluation=true2026.0578.54
GRPOBackbone=Qwen3-8B, Symmetric Think evaluation=true2026.0577.08
BaseBackbone=Qwen3-8B, Symmetric Think evaluation=true2026.0576.25
RLSDBackbone=Qwen3-8B, Symmetric Think evaluation=true2026.0575.42
SRPOBackbone=Qwen3-8B, Symmetric Think evaluation=true2026.0569.17
SDPOBackbone=Qwen3-8B, Symmetric Think evaluation=true2026.0552.5
RLSDBackbone=Qwen3-1.7B, Symmetric Think evaluation=true2026.0545.42
TRACE (RKL on Ey)Backbone=Qwen3-1.7B, Symmetric Think evaluation=true2026.0544.92
TRACE (FKL on Ky)Backbone=Qwen3-1.7B, Symmetric Think evaluation=true2026.0544.83
GRPOBackbone=Qwen3-1.7B, Symmetric Think evaluation=true2026.0544.58
BaseBackbone=Qwen3-1.7B, Symmetric Think evaluation=true2026.0543.75
SRPOBackbone=Qwen3-1.7B, Symmetric Think evaluation=true2026.0524.17
SDPOBackbone=Qwen3-1.7B, Symmetric Think evaluation=true2026.0516.25