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

Code Generation on MBPP+

75.9Accuracy

Planning

Updated 4d ago

Evaluation Results

Method	Links
Planning 2026.02		75.9
Primitives-based MAS 2026.02		75.9
LatentMAS 2026.02		75.7
Primitives-based MAS 2026.02		75.7
LatentMAS 2026.02		74.6
TextMAS 2026.02		74.6
Voting 2026.02		74.6
Voting 2026.02		74.3
Planning 2026.02		74.3
Single 2026.02		73.8
Review 2026.02		73.8
ExPO 2026.02		72
ExOPD 2026.02		70.7
ExOPD 2026.02		70.6
Review 2026.02		70.6
Primitives-based MAS 2026.02		70.6
Teacher 2026.02		70.2
ExPO 2026.02		70.2
OPD 2026.02		69.9
SFT 2026.02		69.6
OPD 2026.02		69.5
TextMAS 2026.02		69.5
TextMAS 2026.02		68.8
Voting 2026.02		68.8
Review 2026.02		67.2
Planning 2026.02		66.7
Single 2026.02		66.4
PASC-GRPO 2026.01		65.24
qwen3-8B 2026.01		65.1
Single 2026.02		64.8
GRP-SFT 2026.01		64.71
Student 2026.02		64.7
HSA-UL 2025.11		62.17
qwen3-8B-Base 2026.01		61.73
HSA-UL 2025.11		55.82
LatentMAS 2026.02		55.6
TRM-MoE 2025.11		50.26
RCO 2025.06		40.34
DPCO 2025.06		39.63
LLaMA-3-70B-Instruct 2025.06		39.26
RCO 2025.06		38.42
Qwen3 2025.11		38.36
RCO 2025.06		37.74
LLaMA-3-8B-Instruct 2025.06		37.73
RCO 2025.06		37.69
RCO 2025.06		37.23
LLAMA-2-70B-Chat 2025.06		36.72
Self-refinement 2025.06		36.5
DPCO 2025.06		35.82
DPCO 2025.06		35.27
DPCO 2025.06		35.12
LLaMA-2-13B-Chat 2025.06		35.05
LLaMA-2-7B-Chat 2025.06		34.74
UltraCM-13B 2025.06		34.46
DPCO 2025.06		34.01
Auto-J-13B 2025.06		32.86
Initial Answer 2025.06		32.85
Qwen2.5 2025.11		32.8
Aligner 2025.06		30.54
P2 2025.12		23.7
HSA-UL 2025.11		20.63
Entropy 2025.12		7.5
Confidence 2025.12		5.9
E-SMC 2025.12		4
Margin 2025.12		3.9
E-BON 2025.12		3.8
E-SMC 2025.12		2.6
E-BON 2025.12		2.4
E-BON 2025.12		2.3
E-SMC 2025.12		2
Uniform 2025.12		1.6
E-BON 2025.12		1.5
E-SMC 2025.12		1.3
E-SMC 2025.12		0.3
E-BON 2025.12		0.2