Mathematical Reasoning on MGSM Thai
87.6Score†DAGGER
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| †DAGGERModel=GPT-4.1, Reasoning Strategy=†DAGGER2026.01 | 87.6 | 98.4 | |
| CoTModel=GPT-4.1, Reasoning Strategy=Chain-of-Thought2026.01 | 78.4 | — | |
| Transport and Mergeadaptation=true2026.02 | 72 | — | |
| Transport and Mergeadaptation=false2026.02 | 64 | — | |
| base model2026.02 | 50 | — |