List your company

Mathematical Reasoning on MATH 500 (Accuracy by Context Length)

29.2Accuracy (128 tokens)EvoToken (10k FT)
15.6819.1922.726.21Jan 12, 2026

Evaluation results

MethodLinks
EvoToken (10k FT)NFE / Gen Len=1/22026.0129.236.437.434.33
BaselineNFE / Gen Len=12026.0128.834.639.434.27
EvoToken (10k FT)NFE / Gen Len=12026.0128.439.64136.33
FT-Base (10k FT)NFE / Gen Len=12026.0126.636.240.434.4
BaselineNFE / Gen Len=1/22026.0126.632.233.230.67
EvoToken (10k FT)NFE / Gen Len=1/42026.0123.63131.228.6
BaselineNFE / Gen Len=1/42026.0123.426.629.626.53
FT-Base (10k FT)NFE / Gen Len=1/22026.0122.631.23429.27
FT-Base (10k FT)NFE / Gen Len=1/42026.0116.219.623.219.67