Hate speech classification on HateCheck (test)
95.6AUCxList-Hate
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| xList-HateModel=mistral-24b2026.02 | 95.6 | 0.079 | |
| xList-HateModel=mistral-7b2026.02 | 93.5 | 0.1 | |
| xList-HateModel=gemma3-12b2026.02 | 92.9 | 0.086 | |
| xList-HateModel=gemma3-27b2026.02 | 92.5 | 0.057 | |
| xList-HateModel=llama3-3b2026.02 | 89.8 | 0.115 | |
| xList-HateModel=gemma3-4b2026.02 | 88 | 0.069 | |
| Zero-shotModel=mistral-24b2026.02 | 87.7 | — | |
| Zero-shotModel=gemma3-27b2026.02 | 86.8 | — | |
| xList-HateModel=llama3-8b2026.02 | 85.3 | 0.05 | |
| Zero-shotModel=gemma3-12b2026.02 | 84.3 | — | |
| Zero-shotModel=mistral-7b2026.02 | 83.5 | — | |
| Zero-shotModel=gemma3-4b2026.02 | 81.2 | — | |
| Zero-shotModel=llama3-8b2026.02 | 80.3 | — | |
| Zero-shotModel=llama3-3b2026.02 | 78.3 | — | |
| xList-HateModel=llama3-1b2026.02 | 74.3 | 0.024 | |
| Zero-shotModel=llama3-1b2026.02 | 71.8 | — |