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

Coding on MBPP

94.16Score

Ministral-3-R

Updated 12d ago

Evaluation Results

Method	Links
Ministral-3-R 2026.02		94.16
Nemotron-Nano-v2 2026.02		93.39
MiniCPM-4.1 2026.02		91.05
Falcon-H1R 2026.02		91.05
MiniCPM-SALA 2026.02		89.11
Qwen3 2026.02		81.32
SkillWeave 2026.05		49.7
Twin-merging 2026.05		49.4
Llama3.2-1B-Instruct 2026.05		49
PEFT 2026.05		48.2
FuseChat3.0 2026.05		45.5
self-rewarding 2026.05		44.6
Hybrid-KSA 2026.04		36.4
KSA 2026.04		35.8
Hybrid-GDN 2026.04		34.8
Hybrid-SCA 2026.04		31.6
Full 2026.04		30.6
Hybrid-SWA 2026.04		30
Llama-3-70B-Instruct 2024.07		0.823
Qwen2-72B-Instruct 2024.07		0.802
Qwen1.5-110B-Chat 2024.07		0.764
Mixtral-8x22B-Instruct 2024.07		0.759
Qwen1.5-72B-Chat 2024.07		0.719