Visual Tool Reasoning on VisualToolBench (test)
12.85Average@4
Agent-KB
Updated 1mo ago
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
2026.03 | 12.85 | 20.09 | 3.88 | |
2026.03 | 11.8 | 19.62 | 3.82 | |
2026.03 | 11.52 | 20.56 | 5.12 | |
2026.03 | 11.09 | 18.69 | 2.65 | |
2026.03 | 10.86 | 19.16 | 4.09 | |
2026.03 | 10.51 | 17.76 | - | |
2026.03 | 10.28 | 16.82 | 2.88 | |
2026.03 | 10.28 | 19.43 | 4.19 | |
2026.03 | 10.05 | 17.76 | 2.73 | |
2026.03 | 10.04 | 18.22 | 3.71 | |
2026.03 | 9.11 | 15.89 | 2.54 | |
2026.03 | 7.94 | 12.62 | - |