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

Code Generation on MBPP 3-shot (test)

64.1Speedup Ratio

Streaming-dLLM

-1.52415.51332.5549.587Sep 27, 2025Nov 6, 2025Dec 17, 2025Jan 27, 2026Mar 8, 2026Apr 18, 2026May 29, 2026
Updated 2d ago

Evaluation Results

MethodLinks
2026.01
64.1--40.81.1--
2025.09
48.3---4.64119.8140.2
2025.09
39.7---5.11108.3952.8
2026.01
32.7--420.9--
2026.05
11.8--29.2-68.4-
2026.01
9.3--13.87.6--
2026.01
7.7--28.23.8--
2026.05
7.2--28.2-41.8-
2026.05
7--29.3-40.6-
2026.05
5.6--29.5-32.5-
2026.05
5.1--29.2-29.6-
2026.01
3.4--29.68.6--
2026.01
3--13.423.6--
2026.01
1.7--26.217.6--
2026.01
1.6--14.643.3--
2026.05
1.4--29.2-8.1-
2026.01
1--29.429.4--
2026.01
1--14.870.5--
2026.05
1--29.4-5.8-
2025.12
-38.2-----
2025.12
-37-----
2025.12
-38.2-----
2025.12
--37.8----
2025.12
-34.8-----
2025.12
-36.6-----
2025.12
-38-----
2025.12
--36.5----
2025.12
-38-----
2025.12
-37.2-----
2025.12
-34.4-----
2025.12
--36.5----
2025.12
-47.4-----
2025.12
-44.6-----
2025.12
-44.2-----
2025.12
--45.4----
2025.12
-39.6-----
2025.12
-39.9-----
2025.12
-38.8-----
2025.12
--39.4----
2026.03
-39.6---9.53-
2026.03
-38.6---120.12-
2026.03
-38---158.81-