Multi-task Language Understanding on MMLU (153-question shuffled subset)
87.28AccuracySIGMA
Evaluation Results
| Method | Links | |
|---|---|---|
| SIGMABase LLM=GPT-OSS-120B, Multi-agent execution=Full, Communication-topology design=Full, Skill-based composition=Full2026.06 | 87.28 | |
| CARDBase LLM=GPT-OSS-120B, Multi-agent execution=Full, Communication-topology design=Full, Skill-based composition=No2026.06 | 85.78 | |
| ARG-DesignerBase LLM=GPT-OSS-120B, Multi-agent execution=Full, Communication-topology design=Full, Skill-based composition=No2026.06 | 85.63 | |
| G-DesignerBase LLM=GPT-OSS-120B, Multi-agent execution=Full, Communication-topology design=Full, Skill-based composition=No2026.06 | 85.06 | |
| GPTSwarmBase LLM=GPT-OSS-120B, Multi-agent execution=Full, Communication-topology design=Partial, Skill-based composition=No2026.06 | 83.59 | |
| CoTBase LLM=GPT-OSS-120B, Multi-agent execution=No, Communication-topology design=No, Skill-based composition=No2026.06 | 83.39 | |
| LLM-DebateBase LLM=GPT-OSS-120B, Multi-agent execution=Full, Communication-topology design=No, Skill-based composition=No2026.06 | 82.92 | |
| VanillaBase LLM=GPT-OSS-120B, Multi-agent execution=No, Communication-topology design=No, Skill-based composition=No2026.06 | 81.58 | |
| SIGMABase LLM=GPT-4o-mini, Multi-agent execution=Full, Communication-topology design=Full, Skill-based composition=Full2026.06 | 76.47 | |
| CARDBase LLM=GPT-4o-mini, Multi-agent execution=Full, Communication-topology design=Full, Skill-based composition=No2026.06 | 75.07 | |
| ARG-DesignerBase LLM=GPT-4o-mini, Multi-agent execution=Full, Communication-topology design=Full, Skill-based composition=No2026.06 | 74.23 | |
| G-DesignerBase LLM=GPT-4o-mini, Multi-agent execution=Full, Communication-topology design=Full, Skill-based composition=No2026.06 | 73.19 | |
| GPTSwarmBase LLM=GPT-4o-mini, Multi-agent execution=Full, Communication-topology design=Partial, Skill-based composition=No2026.06 | 71.4 | |
| LLM-DebateBase LLM=GPT-4o-mini, Multi-agent execution=Full, Communication-topology design=No, Skill-based composition=No2026.06 | 69.66 | |
| CoTBase LLM=GPT-4o-mini, Multi-agent execution=No, Communication-topology design=No, Skill-based composition=No2026.06 | 68.84 | |
| VanillaBase LLM=GPT-4o-mini, Multi-agent execution=No, Communication-topology design=No, Skill-based composition=No2026.06 | 67.61 | |
| SIGMABase LLM=Qwen3-8B, Multi-agent execution=Full, Communication-topology design=Full, Skill-based composition=Full2026.06 | 61.44 | |
| ARG-DesignerBase LLM=Qwen3-8B, Multi-agent execution=Full, Communication-topology design=Full, Skill-based composition=No2026.06 | 60.92 | |
| CARDBase LLM=Qwen3-8B, Multi-agent execution=Full, Communication-topology design=Full, Skill-based composition=No2026.06 | 60.13 | |
| G-DesignerBase LLM=Qwen3-8B, Multi-agent execution=Full, Communication-topology design=Full, Skill-based composition=No2026.06 | 60.07 | |
| LLM-DebateBase LLM=Qwen3-8B, Multi-agent execution=Full, Communication-topology design=No, Skill-based composition=No2026.06 | 59.61 | |
| GPTSwarmBase LLM=Qwen3-8B, Multi-agent execution=Full, Communication-topology design=Partial, Skill-based composition=No2026.06 | 59.58 | |
| CoTBase LLM=Qwen3-8B, Multi-agent execution=No, Communication-topology design=No, Skill-based composition=No2026.06 | 58.74 | |
| VanillaBase LLM=Qwen3-8B, Multi-agent execution=No, Communication-topology design=No, Skill-based composition=No2026.06 | 57.71 |