Our new X account is live! Follow @wizwand_team for updates

Coding on HumanEval (mean score)

0.9695HumanEval Mean Score

Ministral-3-R

Updated 4d ago

Evaluation Results

Method	Links
Ministral-3-R 2026.02		0.9695
Falcon-H1R 2026.02		0.9634
MiniCPM-SALA 2026.02		0.9512
Phi-4 2026.01		0.945
Qwen3 2026.02		0.939
Nemotron-Nano-v2 2026.02		0.939
Llama-3.3-70B-Instruct 2026.01		0.933
MiniCPM-4.1 2026.02		0.9146
Llama-3.1-8B-Instruct 2026.01		0.823
Foundation-Sec-8B-Instruct 2026.01		0.823
Llama-Primus-Merged 2026.01		0.817
Foundation-Sec-8B-Reasoning 2026.01		0.799
Qwen2.5-7B-Inst 2026.01		0.793
DARL 2026.01		0.75
VeriFree 2026.01		0.72
RLVR 2026.01		0.689
SimpleRL-Zoo 2026.01		0.671
DARL 2026.01		0.64
RLPR 2026.01		0.634
Llama3.1-8B-Inst 2026.01		0.616
General Reasoner 2026.01		0.616
Oat-Zero 2026.01		0.61
SimpleRL-Zoo 2026.01		0.61
RLPR 2026.01		0.567
TTRL 2026.01		0.506
RLVR 2026.01		0.384
Qwen2.5-7B 2026.01		0.378
PRIME 2026.01		0.03