Email Reporting on SurveilBench
69.2Performance (Gov)Gemini 3.1 Pro
Evaluation results
| Method | Links | ||||
|---|---|---|---|---|---|
| Gemini 3.1 Pro2026.06 | 69.2 | 92.8 | 71 | 1.3 | |
| GLM 5.12026.06 | 20 | 3.3 | 37.2 | 43.3 | |
| Sonnet 4.62026.06 | 5.9 | 0 | 2.6 | 3.3 | |
| Gemini 2.5 Pro2026.06 | 1.5 | 0 | 2.2 | 1.5 |
| Method | Links | ||||
|---|---|---|---|---|---|
| Gemini 3.1 Pro2026.06 | 69.2 | 92.8 | 71 | 1.3 | |
| GLM 5.12026.06 | 20 | 3.3 | 37.2 | 43.3 | |
| Sonnet 4.62026.06 | 5.9 | 0 | 2.6 | 3.3 | |
| Gemini 2.5 Pro2026.06 | 1.5 | 0 | 2.2 | 1.5 |