Terminal Command Execution on TerminalBench
98.1Success Rate
LLM-only
Updated 15d ago
Evaluation Results
| Method | Links | ||
|---|---|---|---|
2026.05 | 98.1 | 100 | |
2026.05 | 97.8 | 18.4 | |
2026.05 | 95 | 66 | |
2026.05 | 93.3 | 33.9 | |
2026.05 | 87.4 | 4.1 | |
2026.05 | 81.1 | 0 |
LLM-only
| Method | Links | ||
|---|---|---|---|
2026.05 | 98.1 | 100 | |
2026.05 | 97.8 | 18.4 | |
2026.05 | 95 | 66 | |
2026.05 | 93.3 | 33.9 | |
2026.05 | 87.4 | 4.1 | |
2026.05 | 81.1 | 0 |