MoTCoder-32B-V1.5

Reported on 3 benchmarks across 1 task · 1 paper · 2 SOTA

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Natural Language Processing3 results

Code GenerationonAPPS
Interview Pass@1· 2023-12-26
44.49
best: 65.2 (LPW (GPT-4o))
SOTA
MoTCoder: Elevating Large Language Models with Modular of Thought for Challenging Programming Tasks arXiv:2312.15960
Code GenerationonAPPS
Introductory Pass@1· 2023-12-26
68.44
best: 87.2 (LPW (GPT-4o))
SOTA
MoTCoder: Elevating Large Language Models with Modular of Thought for Challenging Programming Tasks arXiv:2312.15960
Code GenerationonAPPS
Competition Pass@1· 2023-12-26
27.84
best: 34.8 (LPW (GPT-4o))
MoTCoder: Elevating Large Language Models with Modular of Thought for Challenging Programming Tasks arXiv:2312.15960