Argument Classification on UKP (Accuracy)
82.1Accuracygpt-oss-120b
Evaluation results
| Method | Links | |
|---|---|---|
| gpt-oss-120bPrompting/Aggregation Strategy=voting2026.02 | 82.1 | |
| GPT-5.2Prompting/Aggregation Strategy=voting2026.02 | 80.4 | |
| gpt-oss-20bPrompting/Aggregation Strategy=voting2026.02 | 79.7 | |
| Llama-4-Scout-70BPrompting/Aggregation Strategy=voting2026.02 | 78.7 | |
| ds70bPrompting/Aggregation Strategy=voting2026.02 | 78.6 | |
| GPT-5.2Prompting/Aggregation Strategy=mRaR2026.02 | 78 | |
| gpt-oss-120bPrompting/Aggregation Strategy=mRaR2026.02 | 77.2 | |
| Llama-4-Scout-70BPrompting/Aggregation Strategy=CoT2026.02 | 76.9 | |
| Llama-3.3-70BPrompting/Aggregation Strategy=CoT2026.02 | 76.8 | |
| gpt-oss-20bPrompting/Aggregation Strategy=mRaR2026.02 | 76.1 | |
| ds70bPrompting/Aggregation Strategy=mRaR2026.02 | 75.9 | |
| Llama-3.3-70BPrompting/Aggregation Strategy=voting2026.02 | 75.6 | |
| Llama-3.1-70BPrompting/Aggregation Strategy=CoT2026.02 | 75.3 | |
| Llama-3.1-70BPrompting/Aggregation Strategy=voting2026.02 | 75 | |
| Llama-4-Scout-70BPrompting/Aggregation Strategy=mRaR2026.02 | 73.1 | |
| Llama-3.3-70BPrompting/Aggregation Strategy=mRaR2026.02 | 72.5 | |
| Llama-3.1-8BPrompting/Aggregation Strategy=voting2026.02 | 71.4 | |
| Llama-3.1-70BPrompting/Aggregation Strategy=mRaR2026.02 | 70.9 | |
| Llama-3.1-8BPrompting/Aggregation Strategy=mRaR2026.02 | 65.4 | |
| Llama-3.1-8BPrompting/Aggregation Strategy=CoT2026.02 | 65.4 | |
| Llama-3.1-3BPrompting/Aggregation Strategy=voting2026.02 | 61.7 | |
| Llama-3.1-3BPrompting/Aggregation Strategy=CoT2026.02 | 55.4 | |
| Llama-3.1-3BPrompting/Aggregation Strategy=mRaR2026.02 | 53.5 | |
| Llama-3.1-1BPrompting/Aggregation Strategy=voting2026.02 | 42.2 | |
| Llama-3.1-1BPrompting/Aggregation Strategy=mRaR2026.02 | 37.3 | |
| Llama-3.1-1BPrompting/Aggregation Strategy=CoT2026.02 | 26.6 |