Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Mathematical Reasoning on GSM8K (Accuracy & Token Count)

98Accuracy

MARS

90.023292.094194.16596.2359Mar 13, 2024Jul 12, 2024Nov 10, 2024Mar 11, 2025Jul 10, 2025Nov 8, 2025Mar 9, 2026
Updated 24d ago

Evaluation Results

MethodLinks
2025.09
983,389----------
2025.09
97.677,440----------
2025.09
97.673,313----------
2025.09
97.33777----------
2025.09
97.331,410----------
2025.09
97.336,307----------
2025.09
97.337,659----------
2026.01
97.04--166.930.58-------
2026.01
97.04--47.732.03-------
2026.01
97.04--47.712.03-------
2026.01
97.04--35.322.75-------
2025.09
97335----------
2025.09
971,548----------
2026.01
96.89--29.363.3-------
2025.09
96.338,831----------
2025.09
96384----------
2026.02
95.8738.24----------
2026.01
95.6-----------
2026.02
95.6197.03----------
2025.12
951,450.68----------
2026.02
94.5-----------
2025.08
94.463,053.67----------
2025.08
94.463,053.67----------
2025.09
94.4-------83.26---
2025.12
94.39983.77----0.64-32.2-----
2025.08
94.392,557.47----------
2025.08
94.392,557.47----------
2026.01
94.31--41.592.27-------
2026.01
94.24--13.876.8-------
2026.01
94.24--13.47.04-------
2026.01
94.24--12.47.6-------
2026.02
94.2263.04----------
2026.01
94.09--10.439.02-------
2025.08
94.091,978.91----------
2026.03
94736----------
2026.03
94266----------
2026.03
93.7327----------
2026.03
93.6265----------
2025.12
93.561,095.1----1.52-24.5-----
2025.08
93.561,629.03----------
2026.02
93.51-----------
2026.02
93.5291.22----------
2026.02
93.33289.82----------
2026.02
93.331,710.27----------
2026.02
93.17182.8----------
2026.02
93974.57----------
2026.02
92.831,121.24----------
2026.03
92.72630----------
2026.02
92.6362.5----------
2026.02
92.5184.1----------
2026.02
92.51,475.27----------
2026.03
92.5825----------
2026.03
92.5391----------
2026.03
92.5326----------
2026.03
92.5311----------
2025.12
92.49974.08----2.64-32.9-----
2026.02
92.41,672.23----------
2025.09
92.33894----------
2025.09
92.3-------80.43---
2025.12
92.2------1.43----
2026.02
92.2360.17----------
2026.03
92.19576----------
2026.01
92.12--32.672.82-------
2026.01
92.12--12.267.52-------
2025.12
92.12-----------
2026.01
92.04--12.937.12-------
2026.01
92.04--9.459.74-------
2026.01
92.04--10.258.98-------
2025.09
92-------80.18---
2025.09
92-------80.66---
2026.03
92289----------
2024.03
91.9-----------
2026.02
91.85-----------
2026.02
91.671,082.18----------
2026.02
91.671,149.86----------
2025.12
91.65-----------
2025.12
91.6------1.46----
2025.12
91.6------1.4----
2026.02
91.46-----------
2025.12
91.4------1.43----
2026.03
91.3405----------
2025.12
91.2------1.4----
2026.02
91.171,182.04----------
2025.09
91.16-------79.73---
2026.03
91.05985----------
2026.01
90.9-----------
2026.01
90.9-----------
2026.03
90.9722----------
2026.02
90.9-----------
2026.02
90.83260.63----------
2026.02
90.8439.25----------
2026.02
90.672,094----------
2026.03
90.551,166----------
2026.02
90.5298.82----------
2026.03
90.5168----------
2026.03
90.481,448----------
2026.03
90.461,269----------
2026.02
90.45694----------
2025.09
90.43-------77.29---
2025.09
90.333,515----------
Showing 100 of 677 rows