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

Mathematical Reasoning on GSM8K (Accuracy, Time, and Speed Up)

13.4Speed Up (x)

ES-dLLM

2.3765.2388.110.962May 30, 2024Sep 15, 2024Jan 1, 2025Apr 19, 2025Aug 5, 2025Nov 21, 2025Mar 10, 2026
Updated 29d ago

Evaluation Results

MethodLinks
2026.03
13.4-------282.67------73.92
2026.03
12.19-68.39------153.21------
2024.05
10.727.8128.5814.1813,440.71-----------
2026.03
10.2-------211.67------73.16
2024.05
10.13-23.659.2514,215.12-----------
2026.03
9.6-78.09------120.62------
2026.03
8.89-79.3------111.79------
2024.05
8.867.8135.4111.7616,250.34-----------
2026.03
7.6-79.08------87.21------
2026.03
6.99-78.01------80.15------
2026.03
6.56-78.24------75.24------
2025.12
6.08--------99.919-0.375----
2026.02
5.71-34-------------
2026.01
5.7-76.1------29.9------
2026.02
5.59-34.11-------------
2026.02
5.54----------78.8----
2026.02
5.03-80-------7.48-----
2026.03
4.98---------8.53-----
2026.02
4.86-81.25-------7.07-----
2026.02
4.68-78.75-------6.71-----
2026.02
4.65-78.75-------6.71-----
2026.03
4.59---------7.38-----
2026.02
4.52-73.16-----32.99-------
2026.02
4.51-73.24-----32.94-------
2026.01
4.5-74.4------24.1------
2026.02
4.48-80.82-----43.24-------
2026.03
4.45-77.18------51.05------
2026.01
4.43----------7.46----
2026.02
4.41-80.14-----42.6-------
2026.01
4.41------------10.86--
2026.02
4.33-77.94-----44.72-------
2026.02
4.32-78.75-------6.09-----
2026.02
4.28-77.33-----44.19-------
2026.01
4.24----------7.4----
2026.01
4.21------------6.02--
2026.02
4.21-----------78.8---
2026.01
4.2-74.7------22.5------
2026.02
4.19-78.75-------5.82-----
2026.03
4.14---------7.64-----
2026.03
4.02---------7.95-----
2026.01
3.99----------6.8----
2026.03
3.97---------6.89-----
2026.02
3.95-75.2-----28.81-------
2026.01
3.91-----------5.6---
2026.01
3.89-----------9.58---
2026.01
3.87----------6.74----
2026.01
3.83------------10.86--
2024.05
3.824.6210.315.913,275.9-----------
2026.01
3.81----------6.24----
2026.03
3.81---------6.39-----
2026.03
3.79---------6.73-----
2026.02
3.75----------73.4----
2026.03
3.75---------6.38-----
2025.12
3.71---------------
2026.03
3.68---------5.64-----
2026.03
3.67---------5.74-----
2026.03
3.67-72.4------46.19------
2026.01
3.65----------6.77----
2026.03
3.64---------5.63-----
2026.01
3.63----------6.42----
2026.03
3.58---------5.46-----
2026.01
3.52------------8.57--
2026.03
3.45-74.45------43.32------
2026.03
3.43---------5.24-----
2025.12
3.41-75------30.3------
2026.03
3.41---------5.63-----
2024.05
3.44.627.735.384,186.22-----------
2026.02
3.37-80.74-----32.49-------
2026.03
3.36---------5.5-----
2026.03
3.35---------4.09-----
2026.03
3.35---------5.09-----
2026.03
3.33---------4.74-----
2026.03
3.32---------5.26-----
2026.01
3.31-----------8.06---
2026.03
3.28---------4.27-----
2026.03
3.28---------5.24-----
2026.03
3.26---------5.08-----
2026.03
3.26---------5.78-----
2026.02
3.24-78.39-----33.44-------
2026.03
3.21---------4.92-----
2026.03
3.21-77.18------36.77------
2026.02
3.14-32.65-------------
2025.12
3.1---------------
2026.02
3.09--------56.315.99-----
2025.12
3.07-83.1------16.32------
2026.02
3.07-----------73.4---
2026.03
3.06---------4.79-----
2025.12
3.04---------------
2026.03
3.02---------3.9-----
2026.02
2.89--------52.664.43-----
2026.03
2.89---------4.4-----
2026.01
2.88------------5.95--
2026.03
2.88---------4.37-----
2026.03
2.84---------4.32-----
2026.01
2.83------------7.86--
2026.03
2.83---------3.76-----
2026.01
2.82------------7.83--
2025.12
2.82---------------
2026.03
2.82---------3.92-----
2026.01
2.8-74.1------14.8------
Showing 100 of 359 rows