Mathematical Reasoning on MMLU High School
88.1AccuracyComb-E
Evaluation Results
| Method | Links | |
|---|---|---|
| Comb-EBackbone=GPT-4o-mini, Workflow Type=Combined-E2026.05 | 88.1 | |
| IC-QBackbone=GPT-4o-mini, Workflow Type=Learned2026.05 | 88.1 | |
| CoTBackbone=GPT-4o-mini, Workflow Type=Chain-of-Thought2026.05 | 86.3 | |
| Reflect.Backbone=GPT-4o-mini, Workflow Type=Reflection2026.05 | 85.9 | |
| Comb-TBackbone=GPT-4o-mini, Workflow Type=Combined-T2026.05 | 85.2 | |
| Direct AnsBackbone=GPT-4o-mini, Workflow Type=Direct2026.05 | 41.5 |