Long-document Visual Question Answering on MMLongBench 128K context
83.33MMLB-DGPT-5.5
Evaluation results
| Method | Links | ||||
|---|---|---|---|---|---|
| GPT-5.5Model Category=Closed-source LVLMs2026.05 | 83.33 | 89.12 | — | 86.22 | |
| Gemini-3.1-ProModel Category=Closed-source LVLMs2026.05 | 77.75 | 80.57 | 93 | 83.77 | |
| Gemini-3.1-FlashModel Category=Closed-source LVLMs2026.05 | 69.63 | 76.38 | 90 | 78.67 | |
| Gemini-2.5-ProModel Category=Closed-source LVLMs2026.05 | 65.04 | 67.6 | 91 | 74.55 | |
| GPT-5.4Model Category=Closed-source LVLMs2026.05 | 52.96 | 73.06 | — | 63.01 | |
| Gemma4-31BModel Category=Large open-source LVLMs (≥ 15B), Parameter Scale=31B2026.05 | 51.87 | 62 | 86 | 66.62 | |
| Qwen2.5-VL-72BModel Category=Large open-source LVLMs (≥ 15B), Parameter Scale=72B2026.05 | 40.19 | 62.45 | 73.9 | 58.85 | |
| Gemma4-26B-A4BModel Category=Large open-source LVLMs (≥ 15B), Parameter Scale=26B-A4B2026.05 | 35.68 | 43.25 | 60 | 46.31 | |
| MMProLongModel Category=Small open-source LVLMs (< 15B)2026.05 | 34.19 | 56.33 | 77 | 55.84 | |
| Qwen2.5-VL-32BModel Category=Large open-source LVLMs (≥ 15B), Parameter Scale=32B2026.05 | 32.08 | 60.15 | 76 | 56.08 | |
| Gemma3-12BModel Category=Small open-source LVLMs (< 15B), Parameter Scale=12B2026.05 | 30.56 | 51.91 | 60 | 47.49 | |
| InternVL3-38BModel Category=Large open-source LVLMs (≥ 15B), Parameter Scale=38B2026.05 | 29.65 | 50.33 | 54 | 44.66 | |
| InternVL3-14BModel Category=Small open-source LVLMs (< 15B), Parameter Scale=14B2026.05 | 29.61 | 50.21 | 53 | 44.27 | |
| Gemma4-E4BModel Category=Small open-source LVLMs (< 15B), Parameter Scale=E4B2026.05 | 28.5 | 37.78 | 45 | 37.09 | |
| Gemma3-27BModel Category=Large open-source LVLMs (≥ 15B), Parameter Scale=27B2026.05 | 27.94 | 61.13 | 68 | 52.35 | |
| Qwen2.5-VL-7BModel Category=Small open-source LVLMs (< 15B), Parameter Scale=7B2026.05 | 26.96 | 51.85 | 68 | 48.94 | |
| Gemma3-4BModel Category=Small open-source LVLMs (< 15B), Parameter Scale=4B2026.05 | 26.44 | 33.38 | 53 | 37.61 | |
| InternVL3-8BModel Category=Small open-source LVLMs (< 15B), Parameter Scale=8B2026.05 | 25.89 | 48.44 | 58 | 44.11 | |
| InternVL3.5-38BModel Category=Large open-source LVLMs (≥ 15B), Parameter Scale=38B2026.05 | 22.24 | 40.09 | 1.01 | 21.11 | |
| Gemma4-E2BModel Category=Small open-source LVLMs (< 15B), Parameter Scale=E2B2026.05 | 20.83 | 27.73 | 51 | 33.19 | |
| InternVL3.5-8BModel Category=Small open-source LVLMs (< 15B), Parameter Scale=8B2026.05 | 18.28 | 31.89 | 0 | 16.72 | |
| InternVL3.5-14BModel Category=Small open-source LVLMs (< 15B), Parameter Scale=14B2026.05 | 16.91 | 33.86 | 0 | 16.92 |