Language Understanding on MMLU-Pro (150 samples per category stratified sampling)
54.78AccuracyGoA_Max
Evaluation Results
| Method | Links | |
|---|---|---|
| GoA_MaxAgent Configuration=Multi-Agent, Number of Agents=3, Zero-shot CoT=true2026.04 | 54.78 | |
| RefineAgent Configuration=Multi-Agent, Number of Agents=6, Zero-shot CoT=true2026.04 | 54.71 | |
| GoA_MeanAgent Configuration=Multi-Agent, Number of Agents=3, Zero-shot CoT=true2026.04 | 54.27 | |
| Self-MoAAgent Configuration=Multi-Agent, Number of Agents=6, Zero-shot CoT=true2026.04 | 54.19 | |
| SCAgent Configuration=Multi-Agent, Number of Agents=6, Zero-shot CoT=true2026.04 | 54.12 | |
| Qwen2.5-7B-InstructAgent Configuration=Single-Agent, Number of Agents=1, Zero-shot CoT=true, Agent Role/Strategy=General2026.04 | 53.9 | |
| MoAAgent Configuration=Multi-Agent, Number of Agents=6, Zero-shot CoT=true2026.04 | 53.33 | |
| DebateAgent Configuration=Multi-Agent, Number of Agents=6, Zero-shot CoT=true2026.04 | 47.05 | |
| ReConcileAgent Configuration=Multi-Agent, Number of Agents=6, Zero-shot CoT=true2026.04 | 44.19 | |
| Qwen2.5-Coder-7B-InstructAgent Configuration=Single-Agent, Number of Agents=1, Zero-shot CoT=true, Agent Role/Strategy=Code2026.04 | 42.33 | |
| Mathstral-7B-v0.1Agent Configuration=Single-Agent, Number of Agents=1, Zero-shot CoT=true, Agent Role/Strategy=Math2026.04 | 37.19 | |
| Bio-Medical-Llama-3-8BAgent Configuration=Single-Agent, Number of Agents=1, Zero-shot CoT=true, Agent Role/Strategy=Biomedical2026.04 | 27.9 | |
| Saul-7B-Instruct v1Agent Configuration=Single-Agent, Number of Agents=1, Zero-shot CoT=true, Agent Role/Strategy=Legal2026.04 | 27.57 | |
| finance-Llama3-8BAgent Configuration=Single-Agent, Number of Agents=1, Zero-shot CoT=true, Agent Role/Strategy=Finance2026.04 | 25.52 |