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

Code Generation on HumanEval

7,927Pass@1

MATRIX-Gen-SFT

-222.441,893.284,0096,124.72Dec 20, 2023May 7, 2024Sep 24, 2024Feb 10, 2025Jun 30, 2025Nov 16, 2025Apr 5, 2026
Updated 11d ago

Evaluation Results

MethodLinks
2024.10
7,927---------------------
2024.10
7,866---------------------
2024.10
7,439---------------------
2024.10
7,439---------------------
2024.10
7,378---------------------
2024.10
7,195---------------------
2024.10
7,134---------------------
2024.10
6,951---------------------
2024.10
4,930---------------------
2024.10
4,817---------------------
2024.10
4,329---------------------
2024.10
4,207---------------------
2024.10
3,659---------------------
2024.10
3,659---------------------
2024.10
3,354---------------------
2026.02
98.73---------------------
2025.12
98.37---------------------
2024.12
98.2---------------------
2024.12
98.2---------------------
2026.03
98.2---------------------
2025.12
98.17---------------------
2026.03
98.17---------------------
2026.02
97.78---------------------
2026.02
97.78---------------------
2025.12
97.56---------------------
2026.03
97.56---------------------
2025.12
97.15---------------------
2026.02
97.15---------------------
2024.12
97---------------------
2024.12
97---------------------
2024.12
97---------------------
2026.03
97---------------------
2025.12
96.95---------------------
2025.12
96.95---------------------
2026.03
96.95---------------------
2026.02
96.84---------------------
96.84---------------------
2025.12
96.54---------------------
2026.03
96.34---------------------
2023.12
96.3-42.5-------------------
2024.12
96.3---------------------
2026.03
96.3---------------------
2026.03
96.3---------------------
2026.02
96.2---------------------
2026.01
95.83---------------------
2025.11
95.73------------------2.24--
2026.03
95.73---------------------
2026.02
95.57---------------------
2026.03
95.12---------------------
2026.02
94.94---------------------
2026.01
94.86---------------------
2025.11
94.71------------------1.22--
2025.09
94.65----------------83.26----
2026.03
94.51---------------------
2026.03
94.5---------------------
2026.02
94.36---------------------
2026.01
94.21---------------------
2024.05
93.9---------------------
2024.12
93.9---------------------
2024.12
93.9---------------------
2026.03
93.89---------------------
2025.12
93.7---------------------
2026.01
93.54---------------------
2025.11
93.49---------------------
2026.01
93.47---------------------
2024.12
93.3---------------------
2026.01
93.15---------------------
2026.02
92.96---------------------
2026.01
92.88---------------------
2025.09
92.85----------------80.43----
2026.03
92.85---------------------
2025.12
92.7---------------------
2026.04
92.7---------------------
2026.04
92.7---------------------
2025.12
92.68---------------------
2026.04
92.68--92.6893.9-----------------
2026.04
92.68--93.2993.29-----------------
2026.01
92.56---------------------
2024.12
92.5---------------------
2025.11
92.48---------------------
2026.01
92.32---------------------
2026.01
92.3---------------------
2025.12
92.27---------------------
2024.12
92.1---------------------
2025.12
92.1---------------------
2025.12
92.1---------------------
92---------------------
2024.07
92---------------------
2026.01
91.6---------------------
2024.12
91.5---------------------
2026.02
91.5---------------------
2026.04
91.46--92.6893.29-----------------
2026.01
91.43---------------------
2026.02
91.22---------------------
2025.12
91.1---------------------
2025.12
91.1---------------------
2024.05
91---------------------
2023.12
91-34.6-------------------
2026.02
91---------------------
2026.03
91---------------------
Showing 100 of 1766 rows
...