List your company

Math Reasoning on AMC23 (mean@12)

92.7Mean Score @12RLCSD
72.10877.45482.888.146Jun 10, 2026

Evaluation results

MethodLinks
RLCSDModel=Olmo-3-7B2026.0692.7
RLSDModel=Olmo-3-7B2026.0692.6
GRPOModel=Olmo-3-7B2026.0692.4
OPSDModel=Olmo-3-7B2026.0692.2
SRPOModel=Olmo-3-7B2026.0692.1
SDPOModel=Olmo-3-7B2026.0691.6
BaseModel=Olmo-3-7B2026.0691.2
RLCSDModel=Qwen3-8B2026.0690.8
OPSDModel=Qwen3-8B2026.0690.4
RLCSDModel=Qwen3-4B2026.0690.1
GRPOModel=Qwen3-8B2026.0690.1
OPSDModel=Qwen3-4B2026.0689.4
GRPOModel=Qwen3-4B2026.0689.1
BaseModel=Qwen3-8B2026.0688.8
SDPOModel=Qwen3-8B2026.0688.8
RLSDModel=Qwen3-8B2026.0688.7
BaseModel=Qwen3-4B2026.0688.6
SDPOModel=Qwen3-4B2026.0688.3
SRPOModel=Qwen3-8B2026.0688.3
SRPOModel=Qwen3-4B2026.0687.9
RLSDModel=Qwen3-4B2026.0686.9
RLCSDModel=Qwen3-1.7B2026.0677.2
GRPOModel=Qwen3-1.7B2026.0676.6
OPSDModel=Qwen3-1.7B2026.0676.3
BaseModel=Qwen3-1.7B2026.0674.1
RLSDModel=Qwen3-1.7B2026.0673.9
SRPOModel=Qwen3-1.7B2026.0673.2
SDPOModel=Qwen3-1.7B2026.0672.9