Binary classification of sense ID on Fool me if you can (Set 2)
99.3F1 ScoreMixtral 7bx8
Evaluation Results
| Method | Links | |
|---|---|---|
| Mixtral 7bx8# Parameters=7B2026.03 | 99.3 | |
| T5-xl# Parameters=3B2026.03 | 99.2 | |
| Llama3 8B# Parameters=8B2026.03 | 99 | |
| T5-large# Parameters=770M2026.03 | 98.7 | |
| Bert-large# Parameters=340M2026.03 | 97.8 | |
| Qwen 3 (Reasoning)*# Parameters=4B, fine-tuned=false2026.03 | 97.2 | |
| Roberta-base# Parameters=125M2026.03 | 96.9 | |
| Gemma 3 (Reasoning)*# Parameters=4B, fine-tuned=false2026.03 | 96.9 | |
| FLAN-T5-xl# Parameters=3B2026.03 | 95.8 | |
| FLAN-T5-large# Parameters=780M2026.03 | 95.3 |