Conversation Simulation on MirrorBench
68.3Primary Metric
OSIM 8B
Updated 1mo ago
Evaluation Results
| Method | Links | |
|---|---|---|
2026.06 | 68.3 | |
2026.06 | 63.7 | |
2026.06 | 56.7 | |
2026.06 | 54 | |
2026.06 | 49.1 | |
2026.06 | 48.3 | |
2026.06 | 48 | |
2026.06 | 45.4 | |
2026.06 | 13.9 |
OSIM 8B
| Method | Links | |
|---|---|---|
2026.06 | 68.3 | |
2026.06 | 63.7 | |
2026.06 | 56.7 | |
2026.06 | 54 | |
2026.06 | 49.1 | |
2026.06 | 48.3 | |
2026.06 | 48 | |
2026.06 | 45.4 | |
2026.06 | 13.9 |