Text-to-Code on M3²Bench
91.4Execution Rate (%)
Gemini-3-Flash
Updated 3mo ago
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
2026.04 | 91.4 | 72.4 | 87.7 | |
2026.04 | 90.3 | 70.8 | 85 | |
2026.04 | 89.2 | 71.8 | 84.2 | |
2026.04 | 88.7 | 70.6 | 83.5 | |
2026.04 | 87.3 | 65.1 | 81.6 | |
2026.04 | 86.5 | 64 | 81 | |
2026.04 | 68.7 | 46.9 | 61.1 | |
2026.04 | 68.5 | 49.1 | 64.5 | |
2026.04 | 46.6 | 29 | 40.2 | |
2026.04 | 46.1 | 28.1 | 35.1 | |
2026.04 | 44.2 | 25.6 | 36.8 | |
2026.04 | 43.4 | 27.4 | 37.2 | |
2026.04 | 42.6 | 24.4 | 34.8 | |
2026.04 | 32.6 | 17.9 | 22.8 |