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

Code Generation on BigCodeBench

83.84Accuracy

LatentMem

Updated 4d ago

Evaluation Results

Method	Links
LatentMem 2026.02		83.84
LatentMem 2026.02		83.84
LatentMem 2026.02		83.25
LatentMem 2026.02		82.75
G-Memory 2026.02		82.67
OAgent 2026.02		82.28
G-Memory 2026.02		82.28
Generative 2026.02		82.19
MetaGPT 2026.02		82.11
Generative 2026.02		82.11
OAgent 2026.02		82.11
MetaGPT 2026.02		81.93
G-Memory 2026.02		81.93
Voyager 2026.02		81.75
Voyager 2026.02		81.67
Voyager 2026.02		81.58
Voyager 2026.02		81.49
OAgent 2026.02		81.49
G-Memory 2026.02		81.46
OAgent 2026.02		81.3
MetaGPT 2026.02		81.28
MetaGPT 2026.02		81.28
Generative 2026.02		81.11
No-memory 2026.02		80.96
No-memory 2026.02		80.28
Generative 2026.02		80.28
No-memory 2026.02		80.26
No-memory 2026.02		79.28
MiMo-V2-Flash Base 2026.01		70.1
DeepSeek-V3.1 Base 2026.01		63
DeepSeek-V3.2 Exp Base 2026.01		62.9
Kimi-K2 Base 2026.01		61.7
DataFlow-Code-10K 2025.12		41.9
DataFlow-Code-1K 2025.12		41.4
DataFlow-Code-5K 2025.12		41.1
Conductor 2025.12		37.86
Gemini 2.5 Pro 2025.12		37.51
Qwen2.5-14B-Instruct 2025.12		37.5
Claude Sonnet 4 2025.12		37.16
Code Alpaca-1K 2025.12		37
Self-OSS 2025.12		36.9
DataFlow-Code-10K 2025.12		36.8
DataFlow-Code-5K 2025.12		36.2
DAJ 2026.01		35.9
DataFlow-Code-1K 2025.12		35.5
Qwen2.5-7B-Instruct 2025.12		35.3
Skywork-o1 PRM 2026.01		35.2
DeepSeek GRM 2026.01		33.8
Code Alpaca-1K 2025.12		33.3
o3-mini (medium) 2026.01		33.1
R1-Distill-Qwen-32B 2025.12		33.07
GPT 5 2025.12		32.75
o1 (high) 2026.01		32.4
o3-mini (high) 2026.01		32.4
Claude-3.7-Sonnet 2026.01		32.4
Self-OSS 2025.12		31.9
Qwen3-32B 2025.12		30.41
Qwen3-32B (thinking) 2025.12		28.38
gemma-3-27b-it 2025.12		14.86