Qwen3-VL-235B-A22B-Thinking · OCRBenchV2_(en/ch)(Qwen3-VL-235B-A22B-Thinking model-card image table; Text Recognition and Chart/Document Understanding; label as printed; unit and metric definition not stated) 66.8 / 63.5 · 附件证据(ev-qwen-3-vl-235b-a22b-thinking-21)
Qwen3-VL-235B-A22B-Thinking 的 OCRBenchV2_(en/ch) · Qwen3-VL-235B-A22B-Thinking model-card image table; Text Recognition and Chart/Document Understanding; label as printed; unit and metric definition not stated 官方出处。Qwen3-VL-235B-A22B-Thinking · 66.8 / 63.5。见《Qwen3-VL-235B-A22B-Thinking multimodal performance official model-card image table》Multimodal performance image table / Text Recognition and Chart/Document Understanding / OCRBenchV2_(en/ch) row / Qwen3-VL 235B-A22B Thinking column。证据 ev-qwen-3-vl-235b-a22b-thinking-21。
原文与定位
Qwen3-VL-235B-A22B-Thinking · OCRBenchV2_(en/ch)(Qwen3-VL-235B-A22B-Thinking model-card image table; Text Recognition and Chart/Document Understanding; label as printed; unit and metric definition not stated),Qwen3-VL-235B-A22B-Thinking配置,Reported score 66.8 / 63.5(具体成绩公布时间未确认)。见《Qwen3-VL-235B-A22B-Thinking multimodal performance official model-card image table》Multimodal performance image table / Text Recognition and Chart/Document Understanding / OCRBenchV2_(en/ch) row / Qwen3-VL 235B-A22B Thinking column。 查看成绩条件
Qwen3-VL / 235B-A22B / Thinking | OCRBenchV2_(en/ch) | 66.8 / 63.5 Note: The default evaluation is conducted through API calls, and * indicates scores from the report.
- 官方材料
- Qwen3-VL-235B-A22B-Thinking multimodal performance official model-card image table
- 定位
- 附件 · Multimodal performance image table / Text Recognition and Chart/Document Understanding / OCRBenchV2_(en/ch) row / Qwen3-VL 235B-A22B Thinking column
- 材料版本
- Official model-card image saved as 本地留存副本; Qwen target column transcribed and checked from the independent AI image-reading report on 2026-11-17; other model columns not transcribed.
- 版本公布
- 未确认
- 披露时间
- 未确认 · 首发/后补未确认
- 采集时间
- 历史依据
- 暂无可靠历史版本依据
引用文本
Qwen3-VL-235B-A22B-Thinking · OCRBenchV2_(en/ch)(Qwen3-VL-235B-A22B-Thinking model-card image table; Text Recognition and Chart/Document Understanding; label as printed; unit and metric definition not stated),Qwen3-VL-235B-A22B-Thinking配置,Reported score 66.8 / 63.5(具体成绩公布时间未确认)。官方出处 Qwen3-VL-235B-A22B-Thinking multimodal performance official model-card image table(附件,Official model-card image saved as 本地留存副本; Qwen target column transcribed and checked from the independent AI image-reading report on 2026-11-17; other model columns not transcribed.)Multimodal performance image table / Text Recognition and Chart/Document Understanding / OCRBenchV2_(en/ch) row / Qwen3-VL 235B-A22B Thinking column,https://qianwen-res.oss-accelerate-overseas.aliyuncs.com/Qwen3-VL/table_thinking_vl.jpg。Benchlog https://benchlog.lekshome.cc/evidence/qwen-3-vl-235b-a22b-thinking/ev-qwen-3-vl-235b-a22b-thinking-21/
关联成绩与条件
| 指标与成绩 | 配置与评测条件 | 证据关系 |
|---|---|---|
| Reported score66.8 / 63.5原文 66.8 / 63.5 · 单位 未标注 公布 未确认 原文未提供可确认的精确值。 | Qwen3-VL-235B-A22B-Thinking
| 直接支持该成绩 在排名中查看此成绩 |