List your company

Mathematical Reasoning on GSM8K, MATH500, ASDiv, SVAMP, AMC23 (test)

81.96GSM8K AccuracyOuro-1.4B-STARS
10.283228.891647.566.1084May 26, 2026

Evaluation results

MethodLinks
Ouro-1.4B-STARSRecurrents=42026.0581.9667.484.7384.3352.574.18
Qwen3-4BRecurrents=-2026.0580.366386.598912.566.29
Ouro-1.4B-SFTRecurrents=42026.0580.0664.683.4776.6747.570.46
Ouro-1.4BRecurrents=22026.0576.8854.874.2781.673564.52
Ouro-1.4B-SFTRecurrents=22026.0576.0455.882.0882.333065.25
Ouro-1.4B-STARSRecurrents=22026.0575.8956.482.5679.674066.9
Qwen3-1.7BRecurrents=-2026.0575.8265.885.648917.566.75
Ouro-1.4BRecurrents=42026.0575.2159.676.5775.675067.41
Qwen2.5-3B-InstructRecurrents=-2026.0574.9168.276.188732.567.76
Ouro-1.4B-STARSRecurrents=82026.0574.4554.882.52813565.55
Llama-3.2-3B-InstructRecurrents=-2026.0571.1142.482.0479.671558.04
Ouro-1.4B-SFTRecurrents=82026.0560.0539.275.16822.552.97
Ouro-1.4BRecurrents=82026.0558.2340.870.0766.334055.09
Gemma3-1b-itRecurrents=-2026.0542.7641.272.4562.672548.82
Recurrent-OLMo-2-0425Recurrents=82026.0517.9711.44038.48021.57
Recurrent-OLMo-2-0425Recurrents=22026.0517.89929.3331.97017.64
Recurrent-OLMo-2-0425Recurrents=42026.0517.139.838.1338.672.521.25
Recurrent-Llama-3.2Recurrents=22026.0515.0114.630.518.67015.76
Recurrent-Llama-3.2Recurrents=42026.0514.0314.641.6518.67518.79
Recurrent-Llama-3.2Recurrents=82026.0513.041421.3342.177.519.61