unsloth/Qwen2.5-VL-72B-Instruct-bnb-4bit
| benchmark | category | score | context | conf | evidence |
|---|---|---|---|---|---|
| DocVQA | multimodal | 91.1 | DocVQA_VAL | medium | | DocVQA_VAL | 91.1 | 95.2 | 92.1 | 96.5 | 96.1 | 96.4 | |
| ChartQA | multimodal | 86.7 | ChartQA_TEST | medium | | ChartQA_TEST | 86.7 | 90.8 | 85.2 | 88.3 | 88.3 | 89.5 | |
| MMBench | multimodal | 82.1 | MMBench_DEV_EN_V11 | medium | | MMBench_DEV_EN_V11 | 82.1 | 83.4 | 83.0 | 88.5 | 86.6 | 88 | |
| MMMU | multimodal | 70.3 | MMMU<sub>val</sub> | medium | | MMMU<sub>val</sub> | 70.3 | 70.4 | 70.7 | 70.1 | 64.5 | 70.2 | |
| MathVista | multimodal | 63.8 | MathVista_MINI | medium | | MathVista_MINI | 63.8 | 65.4 | 73.1 | 76.6 | 70.5 | 74.8 | |
| OSWorld | agentic | 14.9 | OSWorld | medium | | OSWorld | | | 14.90 | 10.26 | | 8.83 | |
| MMBench | multimodal | 1.63 | MMBench-Video | medium | | MMBench-Video | 1.63 | 1.30 | 1.97 | 1.70 | 2.02 | |
none scraped.