AI-generated content evaluation on AGIN
33F1 ScoreBLPO
Evaluation results
| Method | Links | ||
|---|---|---|---|
| BLPOJudge Model=Llama-4-Maverick-17B-128E-instruct2026.02 | 33 | 38 | |
| APO-imageJudge Model=Llama-4-Maverick-17B-128E-instruct2026.02 | 32 | 37 | |
| TextGradJudge Model=Llama-4-Maverick-17B-128E-instruct2026.02 | 30 | 38 | |
| No Optim.Judge Model=Llama-4-Maverick-17B-128E-instruct2026.02 | 26 | 30 | |
| OPROJudge Model=Llama-4-Maverick-17B-128E-instruct2026.02 | 26 | 30 | |
| BLPOJudge Model=Llama-4-Scout-17B-16E-instruct2026.02 | 23 | 28 | |
| TextGradJudge Model=Llama-4-Scout-17B-16E-instruct2026.02 | 21 | 25 | |
| OPROJudge Model=Llama-4-Scout-17B-16E-instruct2026.02 | 19 | 26 | |
| TextGradJudge Model=Qwen2.5-VL-32B-instruct2026.02 | 17 | 22 | |
| BLPOJudge Model=Qwen2.5-VL-32B-instruct2026.02 | 17 | 14 | |
| No Optim.Judge Model=Llama-4-Scout-17B-16E-instruct2026.02 | 16 | 21 | |
| OPROJudge Model=Qwen2.5-VL-32B-instruct2026.02 | 11 | 9 | |
| No Optim.Judge Model=Qwen2.5-VL-32B-instruct2026.02 | 9 | 8 | |
| APO-imageJudge Model=Qwen2.5-VL-32B-instruct2026.02 | 9 | 6 | |
| APO-imageJudge Model=Llama-4-Scout-17B-16E-instruct2026.02 | 6 | 8 |