Social Commonsense Question Answering on SIQA
80.04AccuracyIoT
Evaluation Results
| Method | Links | |
|---|---|---|
| IoTModel=GPT-4o mini2026.03 | 80.04 | |
| CoTModel=GPT-4o mini2026.03 | 79.52 | |
| IoTModel=Olmo-2-13B2026.03 | 73.64 | |
| SCModel=Olmo-2-13B2026.03 | 72.93 | |
| EoTModel=Olmo-2-13B2026.03 | 72.57 | |
| CoTModel=Olmo-2-13B2026.03 | 71.6 | |
| SCModel=Olmo-2-7B2026.03 | 71.36 | |
| SCModel=Llama-3.3-8B2026.03 | 71.14 | |
| IoTModel=Olmo-2-7B2026.03 | 70.88 | |
| EoTModel=Llama-3.3-8B2026.03 | 70.57 | |
| CoTModel=Olmo-2-7B2026.03 | 70.42 | |
| EoTModel=Olmo-2-7B2026.03 | 69.91 | |
| CoTModel=Llama-3.3-8B2026.03 | 69.75 | |
| IoTModel=Llama-3.3-8B2026.03 | 69.7 |