Text-to-Image Generation on GenExam
86.3Math ScoreNano Banana Pro
Evaluation results
| Method | Links | |||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Nano Banana Pro#Params=-2026.03 | 86.3 | 95.1 | 88.7 | 95.9 | 96.5 | 91.7 | 95.1 | 97.2 | 91 | 99.9 | 93.7 | |
| GPT-Image-1.5#Params=-2026.03 | 65.8 | 85.4 | 78.1 | 91.9 | 92.5 | 75.8 | 86.4 | 85.5 | 70.8 | 90.9 | 82.3 | |
| Seedream 4.5#Params=-2026.03 | 44.7 | 63.4 | 48.9 | 75.8 | 67.6 | 57.9 | 69.7 | 67.3 | 38 | 55 | 58.8 | |
| InternVL-U#Params=2B+1.7B, CoT=true2026.03 | 25.6 | 24.2 | 23.5 | 23.6 | 35.6 | 12 | 21.4 | 24.4 | 18.4 | 20.3 | 22.9 | |
| InternVL-U#Params=2B+1.7B2026.03 | 21.5 | 22.2 | 19.3 | 20 | 31.2 | 9.9 | 19.6 | 21.5 | 17.8 | 24.9 | 20.8 | |
| Qwen-Image#Params=20B2026.03 | 18.9 | 26.3 | 15.3 | 32.1 | 49.6 | 18.9 | 32 | 20.3 | 23.4 | 38.6 | 27.5 | |
| HunyuanImage-3.0#Params=-2026.03 | 17 | 17.2 | 18.8 | 18.7 | 30.4 | 15.5 | 16.9 | 11.7 | 23.9 | 20.4 | 19.1 | |
| BAGEL#Params=7B+7B2026.03 | 14.7 | 10.6 | 7.9 | 10.8 | 24.5 | 6.8 | 10.2 | 5.3 | 13.7 | 14.4 | 11.9 | |
| Janus-Pro#Params=7B2026.03 | 13.7 | 8.8 | 8.2 | 7.2 | 18.8 | 3.9 | 10.5 | 4.2 | 14.5 | 6.6 | 9.6 | |
| FLUX.1 [dev]#Params=12B2026.03 | 12.2 | 14.4 | 12.5 | 22.8 | 36.4 | 11 | 14 | 9.2 | 21.3 | 21.7 | 17.6 | |
| Ovis-U1#Params=2.4B+1.2B2026.03 | 12.2 | 10.8 | 6.6 | 10 | 25.4 | 6.1 | 8.8 | 5.4 | 13.2 | 15.1 | 11.4 | |
| Show-o2#Params=7B2026.03 | 10.8 | 11.9 | 4.8 | 12.8 | 33.3 | 4.7 | 11.8 | 7 | 8.8 | 14.5 | 12 | |
| BLIP-3o#Params=8B2026.03 | 6.4 | 5.5 | 4.7 | 7 | 16.7 | 3.6 | 8.4 | 2.5 | 6 | 11.2 | 7.2 |