Non-Agentic Performance Evaluation on HarmBench (test)
73.92Mean Score
LLama 4 Maverick
Updated 1mo ago
Evaluation Results
| Method | Links | ||||
|---|---|---|---|---|---|
2026.03 | 73.92 | 16.33 | 38 | 93.33 | |
2026.03 | 62.33 | 14.88 | 40 | 80 | |
2026.03 | 62.33 | 17.17 | 40 | 85.33 | |
2026.03 | 60.5 | 11.13 | 40 | 73.33 |
LLama 4 Maverick
| Method | Links | ||||
|---|---|---|---|---|---|
2026.03 | 73.92 | 16.33 | 38 | 93.33 | |
2026.03 | 62.33 | 14.88 | 40 | 80 | |
2026.03 | 62.33 | 17.17 | 40 | 85.33 | |
2026.03 | 60.5 | 11.13 | 40 | 73.33 |