Scientific Image Synthesis on Science-T2I (test)
53.19Physics ScoreFLUX.2[dev]
Evaluation Results
| Method | Links | ||||
|---|---|---|---|---|---|
| FLUX.2[dev]Prompt Type=implicit, Evaluator=Qwen3.5-27B2025.04 | 53.19 | 53.55 | 32.5 | 47.8 | |
| Qwen-ImagePrompt Type=implicit, Evaluator=Qwen3.5-27B2025.04 | 34.58 | 46.45 | 23.06 | 33.99 | |
| FLUX.2[klein-9B-Base]Prompt Type=implicit, Evaluator=Qwen3.5-27B2025.04 | 30.28 | 45.75 | 23.06 | 31.57 | |
| FLUX.2[klein-9B]Prompt Type=implicit, Evaluator=Qwen3.5-27B2025.04 | 29.44 | 57.45 | 19.44 | 32.6 | |
| FLUX.2[klein-4B]Prompt Type=implicit, Evaluator=Qwen3.5-27B2025.04 | 28.75 | 50.36 | 19.72 | 30.84 | |
| SD 3.5 LargePrompt Type=implicit, Evaluator=Qwen3.5-27B2025.04 | 27.64 | 44.68 | 18.33 | 28.71 | |
| FLUX.2[klein-4B-Base]Prompt Type=implicit, Evaluator=Qwen3.5-27B2025.04 | 27.22 | 43.97 | 21.11 | 29.08 | |
| Z-Image-TurboPrompt Type=implicit, Evaluator=Qwen3.5-27B2025.04 | 26.81 | 36.53 | 28.33 | 29.22 | |
| Z-ImagePrompt Type=implicit, Evaluator=Qwen3.5-27B2025.04 | 26.53 | 32.98 | 22.22 | 26.73 | |
| BagelPrompt Type=implicit, Evaluator=Qwen3.5-27B2025.04 | 25.28 | 45.75 | 23.33 | 29 | |
| SANAPrompt Type=implicit, Evaluator=Qwen3.5-27B2025.04 | 23.89 | 46.45 | 14.72 | 26.14 | |
| FLUX.1[schnell]Prompt Type=implicit, Evaluator=Qwen3.5-27B2025.04 | 23.19 | 38.3 | 13.33 | 23.72 | |
| SD 3.5 MediumPrompt Type=implicit, Evaluator=Qwen3.5-27B2025.04 | 23.06 | 39.01 | 24.44 | 26.73 | |
| FLUX.1[dev]Prompt Type=implicit, Evaluator=Qwen3.5-27B2025.04 | 22.64 | 50 | 17.22 | 26.87 | |
| GLM-ImagePrompt Type=implicit, Evaluator=Qwen3.5-27B2025.04 | 22.22 | 41.84 | 14.44 | 24.23 | |
| LongCat-ImagePrompt Type=implicit, Evaluator=Qwen3.5-27B2025.04 | 21.94 | 39.01 | 15.83 | 23.86 | |
| Lumina-Image-2Prompt Type=implicit, Evaluator=Qwen3.5-27B2025.04 | 20.28 | 47.87 | 22.22 | 26.51 | |
| SDXLPrompt Type=implicit, Evaluator=Qwen3.5-27B2025.04 | 16.11 | 20.92 | 25.56 | 19.6 |