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

Function-level Code Generation on MBPP+ augmented (test)

79.6Pass@1

LLaDA2.0-flash

Updated 1mo ago

Evaluation Results

Method	Links
LLaDA2.0-flash 2026.01		79.6
Seed-Diffusion-Preview(0705) 2026.01		79.4
Mercury Coder 2026.01		77.1
Gemini Diffusion 2026.01		76
DeepSeek-Coder-V2-Instruct 2026.01		75.1
Qwen2.5-Coder-32B-Instruct 2026.01		75.1
LLaDA2.0-mini 2026.01		74.1
Stable-DiffCoder-8B-Instruct 2026.01		72.8
Qwen2.5-Coder-14B-Instruct 2026.01		72.8
Qwen2.5-Coder-7B-Instruct 2026.01		71.7
Seed-Coder-8B-Instruct 2026.01		71.2
GPT-4-Turbo 2024.10		70.7
DeepSeek-Coder-V2-Lite-Instruct 2026.01		70.4
DeepSeek-Coder-33B-Instruct 2026.01		70.1
Yi-Coder-9B-Chat 2026.01		69
OpenCoder-8B-Instruct 2026.01		69
OpenCodeInterpreter-DS-33B 2024.10		67.7
CodeQwen1.5-7B-Chat 2024.10		67.2
CodeQwen1.5-7B-Chat 2026.01		67.2
Qwen3-8B 2026.01		67.2
WizardCoder-33B-v1.1 2024.10		66.9
DeepSeekCoder-33B-Instruct 2024.10		66.7
Llama3-70B-Instruct 2024.10		66.4
DeepSeek-Coder-6.7B-Instruct 2026.01		65.6
Magicoder-S-DS-6.7B 2024.10		65.4
SelfCodeAlign-CQ-7B 2024.10		65.2
StarCoder2-15B-Instruct 2026.01		65.1
CodeLlama-70B-Instruct 2026.01		64.6
Snowflake Arctic (480B) 2024.10		64.3
CodeQwen1.5-7B-OctoPack 2024.10		63.2
Mixtral-8x22B-Instruct-v0.1 2024.10		62.9
Codestral-22B 2026.01		62.2
DiffuCoder-7B-Instruct 2026.01		61.9
CodeLlama-70B-Instruct 2024.10		61.7
RMI 50% (G) 2026.03		60.58
CodeQwen1.5-7B-Base 2024.10		60.2
Full Data 2026.03		59.52
Llama-3.1-8B-Instruct 2026.01		59
RDS+ 2026.03		58.99
Command-R+ (104B) 2024.10		58.6
RMI QW 50% 2026.03		58.47
RMI 50-75% 2026.03		58.47
RMI Top 50% 2026.03		58.2
Gemini Pro 2024.10		57.9
Random 2026.03		57.67
SCAR 2026.03		57.67
RMI Top-25% 2026.03		57.14
SDLM-32B 2026.01		57.1
Mistral Large 2024.10		56.6
RMI Bot-25% 2026.03		54.76
IFD 2026.03		54.76
StarCoder2-15B 2024.10		53.1
Mixtral-8x7B-Instruct-v0.1 2024.10		49.7
OctoCoder-16B 2024.10		49.1
CodeLlama-7B-Instruct 2026.01		44.4
Fast-dLLMv2 2026.01		41.3