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

Code Generation on LiveCode Bench V6

86.19LiveCode BenchV6

GLM-5

Updated 14d ago

Evaluation Results

Method	Links
GLM-5 2026.05		86.19
Step-3.5-Flash 2026.05		83.9
GLM-4-7 2026.05		83.81
GPT-5-2025-08-07 2026.05		83.24
Gemini-3-Pro-Preview 2026.05		82.86
DeepSeek-V3.2-Speciale 2026.05		80.86
GPT-5-mini-2025-08-07 2026.05		80.76
Kimi-K2.5 2026.05		80.57
gpt-oss-120b 2026.05		78.38
GLM-4.6 2026.05		78.19
Kimi-K2 2026.05		77.14
o3-mini-2025-04-16 2026.05		76
DeepSeek-V3.2 2026.05		75.43
MiniMax-M2 2026.05		74
GPT-5-nano-2025-08-07 2026.05		74
MiniMax-M2.5 2026.05		73.62
o3-2025-04-16 2026.05		72.67
Mimo-V2-Flash 2026.05		71.81
TeleChat 2026.05		71.71
Gemini-2.5-Pro 2026.05		71.33
o4-mini-2025-04-16 2026.05		71.05
Qwen3 2026.05		70.57
gpt-oss-20b 2026.05		68.38
Seed-OSS-36B 2026.05		67.33
Qwen3-Next 2026.05		66.29
GLM-4.5 2026.05		65.05
JT 2026.05		64.86
doubao-seed-1.6 2026.05		61.81
DeepSeek-R1-0528 2026.05		60.95
Qwen3 2026.05		60
Qwen3 2026.05		59.43
GLM-4.5-Air 2026.05		58.38
Finix-P1-32B 2026.05		54.86
Qwen3-Next 2026.05		54.76
MiniCPM-Sala 2026.05		54.67
QwQ-32B 2026.05		52.76
Qwen3-4B 2026.05		51.62
GLM-Z1-32B-0414 2026.05		50.19
LongCat-Flash-Chat 2026.05		48.19
Claude Sonnet 4 2026.05		47.52
ERNIE-4.5 2026.05		47.05
Kimi-K2 2026.05		46.76
DeepSeek-Chat-V3-0324 2026.05		46
Hunyuan-A13B 2026.05		43.9
Qwen3 2026.05		42.95
ERNIE-4.5 2026.05		41.05
Qwen3 2026.05		38.67
GPT-4.1-20250414 2026.05		37.24
Qwen3-4B 2026.05		33.52
Llama4-Maverick 2026.05		33.24
GLM-4-32B-0414 2026.05		32.57
Gemma-3-27B-it 2026.05		30.76