Argument Classification on Args.me
91.9F1 ScoreGPT-5.2
Evaluation Results
| Method | Links | |
|---|---|---|
| GPT-5.2Evaluation Protocol=voting2026.02 | 91.9 | |
| gpt-oss-120bEvaluation Protocol=voting2026.02 | 88.8 | |
| gpt-oss-20bEvaluation Protocol=voting2026.02 | 87.2 | |
| ds70bEvaluation Protocol=voting2026.02 | 86.1 | |
| Llama-3.3-70BEvaluation Protocol=voting2026.02 | 85.3 | |
| Llama-3.1-70BEvaluation Protocol=voting2026.02 | 84.6 | |
| Llama-4-Scout-70BEvaluation Protocol=voting2026.02 | 83.9 | |
| Llama-3.3-70BEvaluation Protocol=CoT2026.02 | 76.4 | |
| Llama-3.1-8BEvaluation Protocol=voting2026.02 | 71.7 | |
| GPT-5.2Evaluation Protocol=mRaR2026.02 | 61 | |
| Llama-3.1-3BEvaluation Protocol=voting2026.02 | 59.1 | |
| gpt-oss-120bEvaluation Protocol=mRaR2026.02 | 58.3 | |
| gpt-oss-20bEvaluation Protocol=mRaR2026.02 | 57 | |
| ds70bEvaluation Protocol=mRaR2026.02 | 55.8 | |
| Llama-3.3-70BEvaluation Protocol=mRaR2026.02 | 53.5 | |
| Llama-3.1-70BEvaluation Protocol=mRaR2026.02 | 52.9 | |
| Llama-4-Scout-70BEvaluation Protocol=mRaR2026.02 | 52.6 | |
| Llama-3.1-70BEvaluation Protocol=CoT2026.02 | 50.4 | |
| Llama-4-Scout-70BEvaluation Protocol=CoT2026.02 | 49.4 | |
| Llama-3.1-8BEvaluation Protocol=mRaR2026.02 | 45.4 | |
| Llama-3.1-8BEvaluation Protocol=CoT2026.02 | 44 | |
| Llama-3.1-3BEvaluation Protocol=CoT2026.02 | 38.1 | |
| Llama-3.1-3BEvaluation Protocol=mRaR2026.02 | 37.9 | |
| Llama-3.1-1BEvaluation Protocol=voting2026.02 | 35.7 | |
| Llama-3.1-1BEvaluation Protocol=CoT2026.02 | 30.9 | |
| Llama-3.1-1BEvaluation Protocol=mRaR2026.02 | 27.8 |