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

Code Generation on LiveCodeBench v6

100Accuracy

AutoGen

Updated 4d ago

Evaluation Results

Method	Links
AutoGen 2026.04		100
Agent Q-Mix 2026.04		100
MaAS 2026.04		100
Lobster 2026.04		100
LangGraph 2026.04		100
AutoGen 2026.04		100
Agent Framework 2026.04		100
Agent Q-Mix 2026.04		100
GPTSwarm 2026.04		99
G-Designer 2026.04		98.75
Agent Framework 2026.04		98.25
TopoDIM 2026.04		98.25
LLM-Debate 2026.04		98
GTD 2026.04		97.75
Base (direct) 2026.04		96.5
AgentDropout 2026.04		96.25
Lobster 2026.04		96
GPTSwarm 2026.04		95.75
MaAS 2026.04		94.5
TopoDIM 2026.04		94
GTD 2026.04		93.75
LangGraph 2026.04		93.5
G-Designer 2026.04		92.25
LLM-Debate 2026.04		92
AgentDropout 2026.04		90
Base (direct) 2026.04		88.75
Conductor 2025.12		83.93
GPT 5 2025.12		82.9
Agentic Proposing 2026.02		71.2
PromptCoT 2.0 2026.02		71
OpenCodeReasoning 2026.02		67.4
Gemini 2.5 Pro 2025.12		67.24
OpenThoughts-S3 2026.02		67.2
Qwen3-30B-A3B-Thinking-2507 2026.02		66
OpenR1 2026.02		63.7
OpenMathReasoning 2026.02		58.4
Qwen3 2026.04		58.3
I-DLM 2026.04		57.1
BF16 Baseline 2026.01		54.3
NVFP4 QAD 2026.01		53.3
NVFP4 PTQ 2026.01		52
Qwen3 2026.04		50.3
Claude Sonnet 4 2025.12		46.54
NVFP4 QAT 2026.01		45.9
I-DLM 2026.04		45.7
LLaDA-2.1-flash 2026.04		45.4
LLaDA-2.0-flash 2026.04		42.5
MiMo-V2-Flash Base 2026.01		30.8
LLaDA-2.1-mini 2026.04		30.4
R1-Distill-Qwen-32B 2025.12		26.86
Kimi-K2 Base 2026.01		26.3
Qwen3-32B (thinking) 2025.12		25.86
DeepSeek-V3.2 Exp Base 2026.01		24.9
DeepSeek-V3.1 Base 2026.01		24.8
SDAR 2026.04		21.7
Qwen3-32B 2025.12		21.21
SDAR 2026.04		16.6
gemma-3-27b-it 2025.12		13.14