Functional Completeness on Falcon-X
0.017MAEFalcon
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| FalconEvaluation Protocol=Fine-tuned2026.06 | 0.017 | 0.09 | |
| GromaEvaluation Protocol=Fine-tuned2026.06 | 0.019 | 0.13 | |
| Sting-BeeEvaluation Protocol=Fine-tuned2026.06 | 0.031 | 0.36 | |
| LISAEvaluation Protocol=Fine-tuned2026.06 | 0.28 | 0.35 | |
| Sting-BeeEvaluation Protocol=Zero-shot2026.06 | 0.49 | 0.48 | |
| GLaMMEvaluation Protocol=Zero-shot2026.06 | 0.52 | — | |
| Kosmos-2Evaluation Protocol=Zero-shot2026.06 | 0.57 | 0.67 | |
| GromaEvaluation Protocol=Zero-shot2026.06 | 0.59 | 0.69 | |
| Sa2VaEvaluation Protocol=Zero-shot2026.06 | 0.6 | — | |
| Llava-1.5Evaluation Protocol=Zero-shot2026.06 | 0.7 | — | |
| LISAEvaluation Protocol=Zero-shot2026.06 | 0.9 | 0.9 |