Table 2; thinking-model video multiple-choice prompt in Appendix B.8; max 2,048 frames and 224K visual tokens 报告提示词见Appendix B;不自动套用当前README的复现采样设置。 仅取235B-A22B-Thinking目标列,其他变体不是本结果的替代。
Qwen3-VL-235B-A22B-Thinking · MVBench · Qwen3-VL技术报告v2;Table 2; thinking-model video multiple-choice prompt in Appendix B.8; max 2,048 frames and 224K visual tokens · Scores and configurations
Qwen3-VL-235B-A22B-Thinking record for MVBench · Qwen3-VL技术报告v2;Table 2; thinking-model video multiple-choice prompt in Appendix B.8; max 2,048 frames and 224K visual tokens. 1 score record for this release, including 1 exact value (may include historical records). Includes 1 source location.
Table 2; thinking-model video multiple-choice prompt in Appendix B.8; max 2,048 frames and 224K visual tokens 报告提示词见Appendix B;不自动套用当前README的复现采样设置。 仅取235B-A22B-Thinking目标列,其他变体不是本结果的替代。