Image Captioning on ICBench Long Caption
76.57Human ScoreChatGPT-5
Evaluation Results
| Method | Links | ||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| ChatGPT-52026.04 | 76.57 | — | — | — | — | — | — | — | — | 50.44 | 63.53 | 52.74 | — | — | |
| ChatGPT-52026.04 | 74.62 | — | — | — | — | — | — | — | — | 50.73 | 51.72 | 64.54 | — | — | |
| Gemini-3.0-Flash2026.04 | 73 | — | — | — | — | — | — | — | — | 49.37 | 62.27 | 45.15 | — | — | |
| Gemini-3.0-Flash2026.04 | 70.4 | — | — | — | — | — | — | — | — | 48.96 | 58.36 | 51.86 | — | — | |
| Gemini-3.0-Flash2026.04 | 68.53 | — | — | — | — | — | — | — | — | 48.44 | 52.97 | 61.07 | — | — | |
| Qwen3-VL2026.04 | 66.9 | — | — | — | — | — | — | — | — | 46.12 | 59.1 | 43.68 | — | — | |
| InternVL3.52026.04 | 66.31 | — | — | — | — | — | — | — | — | 47.47 | 60.13 | 53.46 | — | — | |
| InternVL3.52026.04 | 64.45 | — | — | — | — | — | — | — | — | 47.92 | 55.66 | 59 | — | — | |
| Qwen3-VL2026.04 | 62.9 | — | — | — | — | — | — | — | — | 46.44 | 56.73 | 44.5 | — | — | |
| ChatGPT-52026.04 | 62.83 | — | — | — | — | — | — | — | — | 47.88 | 56.31 | 47.69 | — | — | |
| DeepSeekVL22026.04 | 61.16 | — | — | — | — | — | — | — | — | 45.7 | 50.75 | 51.05 | — | — | |
| DeepSeekVL22026.04 | 59.98 | — | — | — | — | — | — | — | — | 43.03 | 51.05 | 49.66 | — | — | |
| MiniCPM-V2.62026.04 | 59.58 | — | — | — | — | — | — | — | — | 45.18 | 50.53 | 46.6 | — | — | |
| Qwen3-VL2026.04 | 58.21 | — | — | — | — | — | — | — | — | 46.83 | 49.56 | 56.79 | — | — | |
| MiniCPM-V2.62026.04 | 57.2 | — | — | — | — | — | — | — | — | 44.17 | 52.99 | 43.45 | — | — | |
| InternVL3.52026.04 | 56.64 | — | — | — | — | — | — | — | — | 44.38 | 52.55 | 45.36 | — | — | |
| MiniCPM-V2.62026.04 | 55.35 | — | — | — | — | — | — | — | — | 44.6 | 45.56 | 53.04 | — | — | |
| Ovis2.52026.04 | 54.36 | — | — | — | — | — | — | — | — | 45.37 | 54.76 | 52.75 | — | — | |
| DeepSeekVL22026.04 | 53.91 | — | — | — | — | — | — | — | — | 42.57 | 54.7 | 44.02 | — | — | |
| Ovis2.52026.04 | 52.55 | — | — | — | — | — | — | — | — | 43.32 | 46.76 | 55.21 | — | — | |
| LLama3.2-V2026.04 | 51.22 | — | — | — | — | — | — | — | — | 42.23 | 48.85 | 46.09 | — | — | |
| Ovis2.52026.04 | 51.06 | — | — | — | — | — | — | — | — | 41.85 | 48.81 | 42.66 | — | — | |
| LLama3.2-V2026.04 | 49.5 | — | — | — | — | — | — | — | — | 42.78 | 48.44 | 45.98 | — | — | |
| LLama3.2-V2026.04 | 48.14 | — | — | — | — | — | — | — | — | 39.47 | 46.26 | 41.2 | — | — | |
| mPLUG-Owl32026.04 | 47.84 | — | — | — | — | — | — | — | — | 40.85 | 46.59 | 47.35 | — | — | |
| mPLUG-Owl32026.04 | 45.84 | — | — | — | — | — | — | — | — | 40.89 | 43.61 | 48.73 | — | — | |
| mPLUG-Owl32026.04 | 44.73 | — | — | — | — | — | — | — | — | 40.19 | 44.18 | 43.9 | — | — | |
| LLaVA-1.52026.04 | 42.6 | — | — | — | — | — | — | — | — | 38.77 | 42.6 | 41.92 | — | — | |
| LLaVA-1.52026.04 | 40.01 | — | — | — | — | — | — | — | — | 38.01 | 40.4 | 40.82 | — | — | |
| LLaVA-1.52026.04 | 39.54 | — | — | — | — | — | — | — | — | 36.98 | 39.55 | 36.63 | — | — | |
| LLaVA-1.52026.04 | 10 | — | — | — | — | — | — | — | — | — | — | — | — | 10 | |
| mPLUG-Owl32026.04 | 9 | — | — | — | — | — | — | — | — | — | — | — | — | 9 | |
| LLama3.2-V2026.04 | 8 | — | — | — | — | — | — | — | — | — | — | — | — | 8 | |
| Ovis2.52026.04 | 7 | — | — | — | — | — | — | — | — | — | — | — | — | 7 | |
| MiniCPM-V2.62026.04 | 6 | — | — | — | — | — | — | — | — | — | — | — | — | 6 | |
| DeepSeekVL22026.04 | 5 | — | — | — | — | — | — | — | — | — | — | — | — | 5 | |
| Qwen3-VL2026.04 | 4 | — | — | — | — | — | — | — | — | — | — | — | — | 3 | |
| InternVL3.52026.04 | 3 | — | — | — | — | — | — | — | — | — | — | — | — | 4 | |
| Gemini-3.0-Flash2026.04 | 2 | — | — | — | — | — | — | — | — | — | — | — | — | 2 | |
| ChatGPT-52026.04 | 1 | — | — | — | — | — | — | — | — | — | — | — | — | 1 | |
| ChatGPT-5Method Category=Advanced MLLM2026.04 | — | 49.81 | 49.17 | 45.36 | 45.11 | 45.76 | 45 | 47.09 | 46.52 | — | — | — | — | — | |
| CLIP-SMethod Category=Reference-free2026.04 | — | 30.61 | 29.53 | 10.02 | 9.91 | 9.79 | 8.72 | 18.93 | 18.17 | — | — | — | — | — | |
| DeepSeekVL2 (small)Method Category=Advanced MLLM2026.04 | — | 38.74 | 38.44 | 32.17 | 32.25 | 36.71 | 36.42 | 35.59 | 35.43 | — | — | — | — | — | |
| FLEURMethod Category=Reference-free2026.04 | — | 31.53 | 30.42 | 11.83 | 10.72 | 8.12 | 7.01 | 19.41 | 18.42 | — | — | — | — | — | |
| FLEUR [20]2026.04 | — | — | — | — | — | — | — | — | — | — | — | — | 0.867 | — | |
| FLEUR [20]2026.04 | — | — | — | — | — | — | — | — | — | — | — | — | 0.533 | — | |
| FLEUR [20]2026.04 | — | — | — | — | — | — | — | — | — | — | — | — | 0.667 | — | |
| Gemini-3.0-FlashMethod Category=Advanced MLLM2026.04 | — | 51.02 | 50.2 | 43.21 | 42.77 | 46.52 | 46.07 | 46.11 | 45.57 | — | — | — | — | — | |
| GPT-5 [32]2026.04 | — | — | — | — | — | — | — | — | — | — | — | — | 0.917 | — | |
| GPT-5 [32]2026.04 | — | — | — | — | — | — | — | — | — | — | — | — | 0.917 | — | |
| GPT-5 [32]2026.04 | — | — | — | — | — | — | — | — | — | — | — | — | 0.933 | — | |
| InternVL3Model Parameters=8B, Method Category=Advanced MLLM2026.04 | — | 41.56 | 41.04 | 29.86 | 29.73 | 38.83 | 38.56 | 34.69 | 34.48 | — | — | — | — | — | |
| InternVL3.5Model Parameters=8B, Method Category=Advanced MLLM2026.04 | — | 46.73 | 46.18 | 40.49 | 40.35 | 43.24 | 42.86 | 43.4 | 42.98 | — | — | — | — | — | |
| ITIScoreBase Model=DeepSeekVL2 (small), Method Category=Instruction-tuned MLLM2026.04 | — | 64.45 | 64.45 | 56.02 | 56.02 | 58.48 | 58.48 | 60.06 | 60.06 | — | — | — | — | — | |
| ITIScoreBase Model=Qwen3-VL (8B), Method Category=Instruction-tuned MLLM2026.04 | — | 63.84 | 63.85 | 57.24 | 57.24 | 59.08 | 59.08 | 60.66 | 60.66 | — | — | — | — | — | |
| ITIScoreBase Model=InternVL3.5 (8B), Method Category=Instruction-tuned MLLM2026.04 | — | 65.39 | 65.39 | 60.65 | 60.65 | 61.71 | 61.72 | 62.92 | 62.93 | — | — | — | — | — | |
| ITIScore2026.04 | — | — | — | — | — | — | — | — | — | — | — | — | 0.983 | — | |
| ITIScore2026.04 | — | — | — | — | — | — | — | — | — | — | — | — | 0.933 | — | |
| ITIScore2026.04 | — | — | — | — | — | — | — | — | — | — | — | — | 0.983 | — | |
| ITIScore2026.04 | — | — | — | — | — | — | — | — | — | — | — | — | 0.983 | — | |
| LLama3.2-VModel Parameters=11B, Method Category=Advanced MLLM2026.04 | — | 38.48 | 38.31 | 34.57 | 34.47 | 37.88 | 37.57 | 37.85 | 37.65 | — | — | — | — | — | |
| LLaVA-1.5Model Parameters=7B, Method Category=Advanced MLLM2026.04 | — | 23.92 | 23.95 | 21.77 | 22.02 | 24.75 | 24.85 | 23.12 | 23.31 | — | — | — | — | — | |
| MiniCPM-V2.6Model Parameters=8B, Method Category=Advanced MLLM2026.04 | — | 27.11 | 25.83 | 22.99 | 21.94 | 25.43 | 24.17 | 25.52 | 24.27 | — | — | — | — | — | |
| mPLUG-Owl3Model Parameters=7B, Method Category=Advanced MLLM2026.04 | — | 29.46 | 29.25 | 27.82 | 27.86 | 28.46 | 28.25 | 29.47 | 29.35 | — | — | — | — | — | |
| Ovis2.5Model Parameters=8B, Method Category=Advanced MLLM2026.04 | — | 25.16 | 24.07 | 16.64 | 16.14 | 23.81 | 22.8 | 21.28 | 20.46 | — | — | — | — | — | |
| PAC-SMethod Category=Reference-free2026.04 | — | 32.79 | 31.63 | 13.47 | 12.31 | 10.87 | 9.76 | 21.54 | 20.09 | — | — | — | — | — | |
| Qwen2.5-VLModel Parameters=8B, Method Category=Advanced MLLM2026.04 | — | 43.79 | 43.28 | 31.05 | 31.03 | 43.52 | 43.02 | 37.73 | 37.46 | — | — | — | — | — | |
| Qwen3-VLModel Parameters=8B, Method Category=Advanced MLLM2026.04 | — | 49.54 | 48.91 | 44.6 | 44.34 | 44.44 | 43.89 | 44.37 | 43.92 | — | — | — | — | — | |
| UMICMethod Category=Reference-free2026.04 | — | 29.76 | 28.62 | 7.12 | 6.97 | 8.83 | 7.69 | 17.2 | 16.35 | — | — | — | — | — |