List your company

Multi-task Language Understanding on MMLU (153-question shuffled subset)

87.28AccuracySIGMA
56.527264.511172.49580.4789Jun 18, 2026

Evaluation results

MethodLinks
SIGMABase LLM=GPT-OSS-120B, Multi-agent execution=Full, Communication-topology design=Full, Skill-based composition=Full2026.0687.28
CARDBase LLM=GPT-OSS-120B, Multi-agent execution=Full, Communication-topology design=Full, Skill-based composition=No2026.0685.78
ARG-DesignerBase LLM=GPT-OSS-120B, Multi-agent execution=Full, Communication-topology design=Full, Skill-based composition=No2026.0685.63
G-DesignerBase LLM=GPT-OSS-120B, Multi-agent execution=Full, Communication-topology design=Full, Skill-based composition=No2026.0685.06
GPTSwarmBase LLM=GPT-OSS-120B, Multi-agent execution=Full, Communication-topology design=Partial, Skill-based composition=No2026.0683.59
CoTBase LLM=GPT-OSS-120B, Multi-agent execution=No, Communication-topology design=No, Skill-based composition=No2026.0683.39
LLM-DebateBase LLM=GPT-OSS-120B, Multi-agent execution=Full, Communication-topology design=No, Skill-based composition=No2026.0682.92
VanillaBase LLM=GPT-OSS-120B, Multi-agent execution=No, Communication-topology design=No, Skill-based composition=No2026.0681.58
SIGMABase LLM=GPT-4o-mini, Multi-agent execution=Full, Communication-topology design=Full, Skill-based composition=Full2026.0676.47
CARDBase LLM=GPT-4o-mini, Multi-agent execution=Full, Communication-topology design=Full, Skill-based composition=No2026.0675.07
ARG-DesignerBase LLM=GPT-4o-mini, Multi-agent execution=Full, Communication-topology design=Full, Skill-based composition=No2026.0674.23
G-DesignerBase LLM=GPT-4o-mini, Multi-agent execution=Full, Communication-topology design=Full, Skill-based composition=No2026.0673.19
GPTSwarmBase LLM=GPT-4o-mini, Multi-agent execution=Full, Communication-topology design=Partial, Skill-based composition=No2026.0671.4
LLM-DebateBase LLM=GPT-4o-mini, Multi-agent execution=Full, Communication-topology design=No, Skill-based composition=No2026.0669.66
CoTBase LLM=GPT-4o-mini, Multi-agent execution=No, Communication-topology design=No, Skill-based composition=No2026.0668.84
VanillaBase LLM=GPT-4o-mini, Multi-agent execution=No, Communication-topology design=No, Skill-based composition=No2026.0667.61
SIGMABase LLM=Qwen3-8B, Multi-agent execution=Full, Communication-topology design=Full, Skill-based composition=Full2026.0661.44
ARG-DesignerBase LLM=Qwen3-8B, Multi-agent execution=Full, Communication-topology design=Full, Skill-based composition=No2026.0660.92
CARDBase LLM=Qwen3-8B, Multi-agent execution=Full, Communication-topology design=Full, Skill-based composition=No2026.0660.13
G-DesignerBase LLM=Qwen3-8B, Multi-agent execution=Full, Communication-topology design=Full, Skill-based composition=No2026.0660.07
LLM-DebateBase LLM=Qwen3-8B, Multi-agent execution=Full, Communication-topology design=No, Skill-based composition=No2026.0659.61
GPTSwarmBase LLM=Qwen3-8B, Multi-agent execution=Full, Communication-topology design=Partial, Skill-based composition=No2026.0659.58
CoTBase LLM=Qwen3-8B, Multi-agent execution=No, Communication-topology design=No, Skill-based composition=No2026.0658.74
VanillaBase LLM=Qwen3-8B, Multi-agent execution=No, Communication-topology design=No, Skill-based composition=No2026.0657.71