Mathematical Reasoning on GSM8K MC
95.68AccuracySC
Evaluation Results
| Method | Links | |
|---|---|---|
| SCModel=Olmo-2-13B2026.03 | 95.68 | |
| IoTModel=GPT-4o mini2026.03 | 95 | |
| CoTModel=GPT-4o mini2026.03 | 94.74 | |
| IoTModel=Olmo-2-13B2026.03 | 93.1 | |
| SCModel=Llama-3.3-8B2026.03 | 91.89 | |
| IoTModel=Olmo-2-7B2026.03 | 91.66 | |
| CoTModel=Olmo-2-13B2026.03 | 91.36 | |
| IoTModel=Llama-3.3-8B2026.03 | 90.67 | |
| EoTModel=Olmo-2-13B2026.03 | 90.14 | |
| SCModel=Olmo-2-7B2026.03 | 89.39 | |
| CoTModel=Olmo-2-7B2026.03 | 89.08 | |
| CoTModel=Llama-3.3-8B2026.03 | 87.41 | |
| EoTModel=Olmo-2-7B2026.03 | 87.06 | |
| EoTModel=Llama-3.3-8B2026.03 | 84.31 |