Paraphrasing Robustness on ELI5 prompts 32-bit payload Llama3.1-8B (test)
50.9Bit Accuracy
MC2Mark
Updated 21d ago
Evaluation Results
| Method | Links | |
|---|---|---|
2026.05 | 50.9 | |
2026.05 | 50.9 | |
2026.05 | 50.7 | |
2026.05 | 50.5 | |
2026.05 | 50.4 | |
2026.05 | 50.1 | |
2026.05 | 49.8 |
MC2Mark
| Method | Links | |
|---|---|---|
2026.05 | 50.9 | |
2026.05 | 50.9 | |
2026.05 | 50.7 | |
2026.05 | 50.5 | |
2026.05 | 50.4 | |
2026.05 | 50.1 | |
2026.05 | 49.8 |