Accuracy on MMLU Question Answering
75.5MMLU AccuracyBaseline with CoT
Evaluation Results
| Method | Links | |
|---|---|---|
| Baseline with CoTBackbone=Llama 3 70B2026.07 | 75.5 | |
| MALLM (Simple Voting)Backbone=Llama 3 70B, Discussion Paradigm=Memory, Decision Protocol=Simple Voting2026.07 | 75.5 | |
| MALLM (Majority Consensus)Backbone=Llama 3 70B, Discussion Paradigm=Memory, Decision Protocol=Majority Consensus2026.07 | 74 | |
| MALLM (Average Voting)Backbone=Llama 3 70B, Discussion Paradigm=Memory, Note=Excludes Approval Voting2026.07 | 73.8 | |
| MALLM (Ranked Voting)Backbone=Llama 3 70B, Discussion Paradigm=Memory, Decision Protocol=Ranked Voting2026.07 | 73.3 | |
| BaselineBackbone=Llama 3 70B2026.07 | 72.7 | |
| MALLM (Average Consensus)Backbone=Llama 3 70B, Discussion Paradigm=Memory2026.07 | 72.7 | |
| MALLM (Cumulative Voting)Backbone=Llama 3 70B, Discussion Paradigm=Memory, Decision Protocol=Cumulative Voting2026.07 | 72.5 | |
| MALLM (Judge)Backbone=Llama 3 70B, Discussion Paradigm=Memory, Decision Protocol=Judge2026.07 | 72.2 | |
| MALLM (Unanimity Consensus)Backbone=Llama 3 70B, Discussion Paradigm=Memory, Decision Protocol=Unanimity Consensus2026.07 | 72.2 | |
| MALLM (Supermajority Consensus)Backbone=Llama 3 70B, Discussion Paradigm=Memory, Decision Protocol=Supermajority Consensus2026.07 | 71.9 | |
| MALLM (Approval Voting)Backbone=Llama 3 70B, Discussion Paradigm=Memory, Decision Protocol=Approval Voting2026.07 | 50.2 |