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

Qwen3-VL-235B-A22B-Thinking · OCRBenchV2_(en/ch) 成绩与配置
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
设置
官方 235B-A22B Thinking 视觉语言 MoE 开放权重。 本轮补读README的Evaluation Reproduction列出vLLM、VLMEvalKit/lmms-eval,Thinking复现参数:seed=1234,top_p=0.95,top_k=20,temperature=0.6,presence_penalty=0,out_seq_length=40960。评测图另注明默认通过API calls;保留两种说明的适用边界,不假定API等同本地权重服务配置。
未知项
图表未注明成绩单位,不能推定为百分比;默认 API 调用的终端、版本、量化和服务配置未说明。、多模态与纯文本图表只核对 Qwen 目标列;其他比较模型列未转录。
工具
工具条件未记录
推理预算
未记录
框架
未记录
协议
Default evaluation by API calls, per table note
条件
The image table does not state a score unit or metric definition. The table note says default evaluation is through API calls; exact serving endpoint/configuration is not given.

直接支持该成绩

在排名中查看此成绩