Text-to-Code on VisPlotMermaid
90.1Execution Success Rate
Gemini-3-Flash
Updated 3mo ago
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
2026.04 | 90.1 | 58.4 | 80.2 | |
2026.04 | 88.6 | 49.4 | 64.5 | |
2026.04 | 86.3 | 51 | 66.9 | |
2026.04 | 84 | 45.3 | 62.6 | |
2026.04 | 82.4 | 45.8 | 64.3 | |
2026.04 | 67.2 | 40.4 | 55.1 | |
2026.04 | 64.9 | 34.7 | 48.4 | |
2026.04 | 63.4 | 35.2 | 49 | |
2026.04 | 63.4 | 33.8 | 45.8 | |
2026.04 | 60.3 | 31 | 46 | |
2026.04 | 57.5 | 34.2 | 50.5 | |
2026.04 | 57.3 | 25.6 | 37.3 | |
2026.04 | 51.2 | 22.4 | 31.9 | |
2026.04 | 45 | 19.1 | 28.2 |