List your company

Mathematical Reasoning on GSM8K (Pass@3 accuracy)

91.2Pass@3 AccuracyTRACERL
77.721681.220884.7288.2192Jan 16, 2026

Evaluation results

MethodLinks
TRACERLBase model=SDAR-4B-Chat-b4, Block size=b42026.0191.2
T*Base model=SDAR-4B-Chat-b8, Block size=b82026.0191
SDAR-4B-Chat-b4Method=Original Checkpoint, Block size=b42026.0190.5
T*Base model=SDAR-4B-Chat-b16, Block size=b162026.0189.4
TRACERLBase model=SDAR-4B-Chat-b8, Block size=b82026.0186.3
SDAR-4B-Chat-b8Method=Original Checkpoint, Block size=b82026.0185.87
T*Base model=SDAR-1.7B-Chat-b8, Block size=b82026.0182.4
TRACERLBase model=SDAR-1.7B-Chat-b4, Block size=b42026.0182.23
T*Base model=SDAR-1.7B-Chat-b16, Block size=b162026.0182.2
T*Base model=SDAR-1.7B-Chat-b32, Block size=b322026.0182
TRACERLBase model=SDAR-1.7B-Chat-b8, Block size=b82026.0181.5
SDAR-1.7B-Chat-b8Method=Original Checkpoint, Block size=b82026.0181
SDAR-1.7B-Chat-b4Method=Original Checkpoint, Block size=b42026.0180.54
TRACERLBase model=SDAR-1.7B-Chat-b16, Block size=b162026.0180
TRACERLBase model=SDAR-1.7B-Chat-b32, Block size=b322026.0179.8
TRACERLBase model=SDAR-4B-Chat-b16, Block size=b162026.0179.6
SDAR-1.7B-Chat-b16Method=Original Checkpoint, Block size=b162026.0179.4
SDAR-1.7B-Chat-b32Method=Original Checkpoint, Block size=b322026.0178.31
SDAR-4B-Chat-b16Method=Original Checkpoint, Block size=b162026.0178.24