| agents-on-bfclv4 | Qwen3.5-397B-A17B | #1 | Accuracy: 72.9 |
| agents-on-bfclv4 | Qwen3.5-9B | #5 | Accuracy: 66.1 |
| multi-task-language-understanding-on-c-eval | Qwen3.5-397B-A17B | #1 | Accuracy: 93.0 |
| multi-task-language-understanding-on-c-eval | Qwen3.5-122B-A10B | #4 | Accuracy: 91.9 |
| multi-task-language-understanding-on-c-eval | Qwen3.5-27B | #7 | Accuracy: 90.5 |
| multi-task-language-understanding-on-c-eval | Qwen3.5-35B-A3B | #11 | Accuracy: 90.2 |
| multi-task-language-understanding-on-c-eval | Qwen3.5-9B | #16 | Accuracy: 88.2 |
| multi-task-language-understanding-on-mmlu-redux | Qwen3.5-397B-A17B | #1 | Accuracy: 94.9 |
| multi-task-language-understanding-on-mmlu-redux | Qwen3.5-122B-A10B | #2 | Accuracy: 94.0 |
| multi-task-language-understanding-on-mmlu-redux | Qwen3.5-35B-A3B | #6 | Accuracy: 93.3 |
| multi-task-language-understanding-on-mmlu-redux | Qwen3.5-27B | #8 | Accuracy: 93.2 |
| multi-task-language-understanding-on-mmlu-redux | Qwen3.5-9B | #14 | Accuracy: 91.1 |
| multi-task-language-understanding-on-mmmlu | Qwen3.5-397B-A17B | #1 | Accuracy: 88.5 |
| multi-task-language-understanding-on-mmmlu | Qwen3.5-122B-A10B | #4 | Accuracy: 86.7 |
| multi-task-language-understanding-on-mmmlu | Qwen3.5-27B | #5 | Accuracy: 85.9 |
| multi-task-language-understanding-on-mmmlu | Qwen3.5-35B-A3B | #6 | Accuracy: 85.2 |
| multi-task-language-understanding-on-mmmlu | Qwen3.5-9B | #11 | Accuracy: 81.2 |
| multimodal-reasoning-on-mathvision | Qwen3.5-397B-A17B | #1 | Accuracy: 88.6 |
| multimodal-reasoning-on-mathvision | Qwen3.5-122B-A10B | #4 | Accuracy: 86.2 |
| multimodal-reasoning-on-mathvision | Qwen3.5-27B | #5 | Accuracy: 86.0 |
| multimodal-reasoning-on-mathvision | Qwen3.5-35B-A3B | #8 | Accuracy: 83.9 |
| multimodal-reasoning-on-mathvision | Qwen3.5-9B | #12 | Accuracy: 78.9 |
| multimodal-reasoning-on-mathvista | Qwen3.5-397B-A17B | #1 | Accuracy: 90.3 |
| multimodal-reasoning-on-mathvista | Qwen3.5-27B | #3 | Accuracy: 87.8 |
| multimodal-reasoning-on-mathvista | Qwen3.5-122B-A10B | #4 | Accuracy: 87.4 |
| multimodal-reasoning-on-mathvista | Qwen3.5-35B-A3B | #8 | Accuracy: 86.2 |
| multimodal-reasoning-on-mathvista | Qwen3.5-9B | #12 | Accuracy: 85.7 |
| multimodal-reasoning-on-mmmu | Qwen3.5-397B-A17B | #1 | Accuracy: 85.0 |
| multimodal-reasoning-on-mmmu | Qwen3.5-122B-A10B | #3 | Accuracy: 83.9 |
| multimodal-reasoning-on-mmmu | Qwen3.5-27B | #6 | Accuracy: 82.3 |
| multimodal-reasoning-on-mmmu | Qwen3.5-35B-A3B | #8 | Accuracy: 81.4 |
| multimodal-reasoning-on-mmmu | Qwen3.5-9B | #13 | Accuracy: 78.4 |
| multimodal-reasoning-on-zerobench | Qwen3.5-397B-A17B | #1 | Accuracy: 12 |
| multimodal-reasoning-on-zerobench | Qwen3.5-27B | #2 | Accuracy: 10 |
| multimodal-reasoning-on-zerobench | Qwen3.5-122B-A10B | #4 | Accuracy: 9 |
| multimodal-reasoning-on-zerobench | Qwen3.5-35B-A3B | #5 | Accuracy: 8 |
| multimodal-reasoning-on-zerobench | Qwen3.5-9B | #7 | Accuracy: 3.0 |
| optical-character-recognition-ocr-on-ocrbench | Qwen3.5-397B-A17B | #1 | Score: 931 |
| video-question-answering-on-mlvu | Qwen3.5-122B-A10B | #1 | Accuracy: 87.3 |
| video-question-answering-on-mlvu | Qwen3.5-397B-A17B | #2 | Accuracy: 86.7 |
| video-question-answering-on-mlvu | Qwen3.5-27B | #5 | Accuracy: 85.9 |
| video-question-answering-on-mlvu | Qwen3.5-35B-A3B | #7 | Accuracy: 85.6 |
| video-question-answering-on-mlvu | Qwen3.5-9B | #8 | Accuracy: 84.4 |
| vision-language-understanding-on-mmbench-v1-1 | Qwen3.5-397B-A17B | #1 | Accuracy: 93.7 |
| vision-language-understanding-on-mmbench-v1-1 | Qwen3.5-122B-A10B | #2 | Accuracy: 92.8 |
| vision-language-understanding-on-mmbench-v1-1 | Qwen3.5-27B | #4 | Accuracy: 92.6 |
| vision-language-understanding-on-mmbench-v1-1 | Qwen3.5-35B-A3B | #6 | Accuracy: 91.5 |
| vision-language-understanding-on-mmbench-v1-1 | Qwen3.5-9B | #7 | Accuracy: 90.1 |
| visual-question-answering-vqa-on-hallusionbench-average-accuracy | Qwen3.5-397B-A17B | #1 | Accuracy: 71.4 |
| visual-question-answering-vqa-on-hallusionbench-average-accuracy | Qwen3.5-27B | #2 | Accuracy: 70.0 |
| visual-question-answering-vqa-on-hallusionbench-average-accuracy | Qwen3.5-9B | #3 | Accuracy: 69.3 |
| visual-question-answering-vqa-on-hallusionbench-average-accuracy | Qwen3.5-35B-A3B | #4 | Accuracy: 67.9 |
| visual-question-answering-vqa-on-hallusionbench-average-accuracy | Qwen3.5-122B-A10B | #5 | Accuracy: 67.6 |
| zero-shot-video-question-answer-on-video-mme-w-o-subs | Qwen3.5-122B-A10B | #1 | Accuracy (%): 83.9 |
| zero-shot-video-question-answer-on-video-mme-w-o-subs | Qwen3.5-397B-A17B | #2 | Accuracy (%): 83.7 |
| zero-shot-video-question-answer-on-video-mme-w-o-subs | Qwen3.5-27B | #3 | Accuracy (%): 82.8 |
| zero-shot-video-question-answer-on-video-mme-w-o-subs | Qwen3.5-35B-A3B | #4 | Accuracy (%): 82.5 |
| zero-shot-video-question-answer-on-video-mme-w-o-subs | Qwen3.5-9B | #7 | Accuracy (%): 78.4 |
| instruction-following-on-multichallenge | Qwen3.5-397B-A17B | #2 | Accuracy: 67.6 |
| instruction-following-on-multichallenge | Qwen3.5-122B-A10B | #4 | Accuracy: 61.5 |
| instruction-following-on-multichallenge | Qwen3.5-27B | #6 | Accuracy: 60.8 |
| instruction-following-on-multichallenge | Qwen3.5-35B-A3B | #7 | Accuracy: 60.0 |
| instruction-following-on-multichallenge | Qwen3.5-9B | #10 | Accuracy: 54.5 |
| long-context-understanding-on-longbench-v2 | Qwen3.5-397B-A17B | #2 | Accuracy: 63.2 |
| long-context-understanding-on-longbench-v2 | Qwen3.5-27B | #6 | Accuracy: 60.6 |
| long-context-understanding-on-longbench-v2 | Qwen3.5-122B-A10B | #7 | Accuracy: 60.2 |
| long-context-understanding-on-longbench-v2 | Qwen3.5-35B-A3B | #9 | Accuracy: 59.0 |
| long-context-understanding-on-longbench-v2 | Qwen3.5-9B | #12 | Accuracy: 55.2 |
| multi-task-language-understanding-on-include | Qwen3.5-397B-A17B | #2 | Accuracy: 85.6 |
| multi-task-language-understanding-on-include | Qwen3.5-122B-A10B | #3 | Accuracy: 82.8 |
| multi-task-language-understanding-on-include | Qwen3.5-27B | #4 | Accuracy: 81.6 |
| multi-task-language-understanding-on-include | Qwen3.5-35B-A3B | #6 | Accuracy: 79.7 |
| multi-task-language-understanding-on-include | Qwen3.5-9B | #9 | Accuracy: 75.6 |
| multimodal-reasoning-on-babyvision | Qwen3.5-397B-A17B | #2 | Accuracy: 52.3 |
| multimodal-reasoning-on-babyvision | Qwen3.5-27B | #4 | Accuracy: 44.6 |
| multimodal-reasoning-on-babyvision | Qwen3.5-122B-A10B | #5 | Accuracy: 40.2 |
| multimodal-reasoning-on-babyvision | Qwen3.5-35B-A3B | #7 | Accuracy: 38.4 |
| multiple-choice-question-answering-mcqa-on-supergpqa | Qwen3.5-397B-A17B | #2 | Accuracy: 70.4 |
| multiple-choice-question-answering-mcqa-on-supergpqa | Qwen3.5-122B-A10B | #3 | Accuracy: 67.1 |
| multiple-choice-question-answering-mcqa-on-supergpqa | Qwen3.5-27B | #5 | Accuracy: 65.6 |
| multiple-choice-question-answering-mcqa-on-supergpqa | Qwen3.5-35B-A3B | #9 | Accuracy: 63.4 |
| multiple-choice-question-answering-mcqa-on-supergpqa | Qwen3.5-9B | #12 | Accuracy: 58.2 |
| object-counting-on-countbench | Qwen3.5-27B | #2 | Accuracy: 97.8 |
| object-counting-on-countbench | Qwen3.5-35B-A3B | #3 | Accuracy: 97.8 |
| object-counting-on-countbench | Qwen3.5-397B-A17B | #5 | Accuracy: 97.2 |
| object-counting-on-countbench | Qwen3.5-9B | #6 | Accuracy: 97.2 |
| object-counting-on-countbench | Qwen3.5-122B-A10B | #7 | Accuracy: 97.0 |
| visual-grounding-on-refcoco-refcoco-refcocog-overall | Qwen3.5-397B-A17B | #2 | Accuracy: 92.3 |
| visual-grounding-on-refcoco-refcoco-refcocog-overall | Qwen3.5-122B-A10B | #7 | Accuracy: 91.3 |
| visual-grounding-on-refcoco-refcoco-refcocog-overall | Qwen3.5-27B | #9 | Accuracy: 90.9 |
| visual-grounding-on-refcoco-refcoco-refcocog-overall | Qwen3.5-9B | #11 | Accuracy: 89.7 |
| visual-grounding-on-refcoco-refcoco-refcocog-overall | Qwen3.5-35B-A3B | #13 | Accuracy: 89.2 |
| agents-on-bench | Qwen3.5-397B-A17B | #3 | Accuracy: 86.7 |
| agents-on-bench | Qwen3.5-35B-A3B | #6 | Accuracy: 81.2 |
| agents-on-bench | Qwen3.5-122B-A10B | #11 | Accuracy: 79.5 |
| agents-on-bench | Qwen3.5-9B | #12 | Accuracy: 79.1 |
| agents-on-bench | Qwen3.5-27B | #13 | Accuracy: 79.0 |
| multi-task-language-understanding-on-mmlu-pro | Qwen3.5-397B-A17B | #3 | Accuracy: 87.8 |
| multi-task-language-understanding-on-mmlu-pro | Qwen3.5-122B-A10B | #7 | Accuracy: 86.7 |
| multi-task-language-understanding-on-mmlu-pro | Qwen3.5-27B | #11 | Accuracy: 86.1 |
| multi-task-language-understanding-on-mmlu-pro | Qwen3.5-35B-A3B | #13 | Accuracy: 85.3 |
| multi-task-language-understanding-on-mmlu-pro | Qwen3.5-9B | #32 | Accuracy: 82.5 |
| video-question-answering-on-mvbench | Qwen3.5-397B-A17B | #3 | Avg.: 77.6 |
| video-question-answering-on-mvbench | Qwen3.5-122B-A10B | #5 | Avg.: 76.6 |
| video-question-answering-on-mvbench | Qwen3.5-35B-A3B | #12 | Avg.: 74.8 |
| video-question-answering-on-mvbench | Qwen3.5-27B | #13 | Avg.: 74.6 |
| video-question-answering-on-mvbench | Qwen3.5-9B | #16 | Avg.: 74.4 |
| vision-language-understanding-on-mmstar | Qwen3.5-397B-A17B | #3 | Accuracy: 83.8 |
| vision-language-understanding-on-mmstar | Qwen3.5-122B-A10B | #4 | Accuracy: 82.9 |
| vision-language-understanding-on-mmstar | Qwen3.5-35B-A3B | #5 | Accuracy: 81.9 |
| vision-language-understanding-on-mmstar | Qwen3.5-27B | #7 | Accuracy: 81.0 |
| vision-language-understanding-on-mmstar | Qwen3.5-9B | #11 | Accuracy: 79.7 |
| chart-question-answering-on-charxiv-rq | Qwen3.5-27B | #4 | Accuracy: 79.5 |
| chart-question-answering-on-charxiv-rq | Qwen3.5-35B-A3B | #10 | Accuracy: 77.5 |
| chart-question-answering-on-charxiv-rq | Qwen3.5-122B-A10B | #11 | Accuracy: 77.2 |
| chart-question-answering-on-charxiv-rq | Qwen3.5-9B | #12 | Accuracy: 73.0 |
| code-generation-on-terminal-bench-2-0-terminus-2 | Qwen3.5-397B-A17B (Terminus-2) | #4 | Accuracy: 52.5 |
| multimodal-reasoning-on-mmmu-pro | Qwen3.5-397B-A17B | #4 | Accuracy: 79.0 |
| multimodal-reasoning-on-mmmu-pro | Qwen3.5-122B-A10B | #7 | Accuracy: 76.9 |
| multimodal-reasoning-on-mmmu-pro | Qwen3.5-35B-A3B | #11 | Accuracy: 75.1 |
| multimodal-reasoning-on-mmmu-pro | Qwen3.5-27B | #12 | Accuracy: 75.0 |
| multimodal-reasoning-on-mmmu-pro | Qwen3.5-9B | #19 | Accuracy: 70.1 |
| video-question-answering-on-video-mme-with-subtitles | Qwen3.5-397B-A17B (w/ subtitles) | #4 | Accuracy: 87.5 |
| video-question-answering-on-video-mme-with-subtitles | Qwen3.5-122B-A10B (w/ subtitles) | #6 | Accuracy: 87.3 |
| video-question-answering-on-video-mme-with-subtitles | Qwen3.5-27B (w/ subtitles) | #7 | Accuracy: 87.0 |
| video-question-answering-on-video-mme-with-subtitles | Qwen3.5-35B-A3B (w/ subtitles) | #8 | Accuracy: 86.6 |
| video-question-answering-on-video-mme-with-subtitles | Qwen3.5-9B (w/ subtitles) | #11 | Accuracy: 84.5 |
| video-question-answering-on-video-mmmu | Qwen3.5-397B-A17B | #4 | Accuracy: 84.7 |
| video-question-answering-on-video-mmmu | Qwen3.5-27B | #8 | Accuracy: 82.3 |
| video-question-answering-on-video-mmmu | Qwen3.5-122B-A10B | #9 | Accuracy: 82.0 |
| video-question-answering-on-video-mmmu | Qwen3.5-35B-A3B | #10 | Accuracy: 80.4 |
| video-question-answering-on-video-mmmu | Qwen3.5-9B | #13 | Accuracy: 78.9 |
| visual-question-answering-vqa-on-realworldqa | Qwen3.5-122B-A10B | #5 | Accuracy: 85.1 |
| visual-question-answering-vqa-on-realworldqa | Qwen3.5-35B-A3B | #6 | Accuracy: 84.1 |
| visual-question-answering-vqa-on-realworldqa | Qwen3.5-397B-A17B | #8 | Accuracy: 83.9 |
| visual-question-answering-vqa-on-realworldqa | Qwen3.5-27B | #9 | Accuracy: 83.7 |
| visual-question-answering-vqa-on-realworldqa | Qwen3.5-9B | #13 | Accuracy: 80.3 |
| visual-question-answering-vqa-on-simplevqa | Qwen3.5-122B-A10B | #5 | Accuracy: 61.7 |
| visual-question-answering-vqa-on-simplevqa | Qwen3.5-35B-A3B | #6 | Accuracy: 58.3 |
| visual-question-answering-vqa-on-simplevqa | Qwen3.5-27B | #7 | Accuracy: 56.0 |
| visual-question-answering-vqa-on-simplevqa | Qwen3.5-9B | #9 | Accuracy: 51.2 |
| zero-shot-object-detection-on-odinw13 | Qwen3.5-397B-A17B (zero-shot) | #5 | mAP: 47.0 |
| video-question-answering-on-lvbench | Qwen3.5-397B-A17B | #6 | Accuracy: 75.5 |
| video-question-answering-on-lvbench | Qwen3.5-122B-A10B | #7 | Accuracy: 74.4 |
| video-question-answering-on-lvbench | Qwen3.5-27B | #8 | Accuracy: 73.6 |
| video-question-answering-on-lvbench | Qwen3.5-35B-A3B | #11 | Accuracy: 71.4 |
| video-question-answering-on-lvbench | Qwen3.5-9B | #12 | Accuracy: 70.0 |
| video-question-answering-on-mmvu | Qwen3.5-397B-A17B | #7 | Accuracy: 75.4 |
| video-question-answering-on-mmvu | Qwen3.5-122B-A10B | #8 | Accuracy: 74.7 |
| video-question-answering-on-mmvu | Qwen3.5-27B | #9 | Accuracy: 73.3 |
| video-question-answering-on-mmvu | Qwen3.5-35B-A3B | #10 | Accuracy: 72.3 |
| video-question-answering-on-mmvu | Qwen3.5-9B | #19 | Accuracy: 67.8 |
| instruction-following-on-ifbench | Qwen3.5-27B | #9 | Accuracy: 76.5 |
| instruction-following-on-ifbench | Qwen3.5-397B-A17B | #10 | Accuracy: 76.5 |
| instruction-following-on-ifbench | Qwen3.5-122B-A10B | #11 | Accuracy: 76.1 |
| instruction-following-on-ifbench | Qwen3.5-35B-A3B | #18 | Accuracy: 70.2 |
| instruction-following-on-ifbench | Qwen3.5-9B | #26 | Accuracy: 64.5 |
| optical-character-recognition-ocr-on-omnidocbench-v1-5 | Qwen3.5-397B-A17B | #12 | Accuracy: 90.8 |
| optical-character-recognition-ocr-on-omnidocbench-v1-5 | Qwen3.5-122B-A10B | #14 | Accuracy: 89.8 |
| optical-character-recognition-ocr-on-omnidocbench-v1-5 | Qwen3.5-35B-A3B | #15 | Accuracy: 89.3 |
| optical-character-recognition-ocr-on-omnidocbench-v1-5 | Qwen3.5-27B | #17 | Accuracy: 88.9 |
| optical-character-recognition-ocr-on-omnidocbench-v1-5 | Qwen3.5-9B | #18 | Accuracy: 87.7 |
| code-generation-on-livecodebench-v6 | Qwen3.5-397B-A17B | #14 | Pass@1: 83.6 |
| code-generation-on-livecodebench-v6 | Qwen3.5-27B | #17 | Pass@1: 80.7 |
| code-generation-on-livecodebench-v6 | Qwen3.5-122B-A10B | #21 | Pass@1: 78.9 |
| code-generation-on-livecodebench-v6 | Qwen3.5-35B-A3B | #25 | Pass@1: 74.6 |
| code-generation-on-livecodebench-v6 | Qwen3.5-9B | #38 | Pass@1: 65.6 |
| computer-use-agents-on-androidworld | Qwen3.5-35B-A3B | #14 | Success Rate: 71.1 |
| question-answering-on-humanity-s-last-exam-hle | Qwen3.5-397B-A17B | #14 | Accuracy: 28.7 |
| question-answering-on-humanity-s-last-exam-hle | Qwen3.5-122B-A10B (w/ CoT) | #18 | Accuracy: 25.3 |
| question-answering-on-humanity-s-last-exam-hle | Qwen3.5-27B (w/ CoT) | #20 | Accuracy: 24.3 |
| question-answering-on-humanity-s-last-exam-hle | Qwen3.5-35B-A3B (w/ CoT) | #24 | Accuracy: 22.4 |
| multiple-choice-question-answering-mcqa-on-gpqa-diamond | Qwen3.5-397B-A17B | #17 | Accuracy: 88.4 |
| multiple-choice-question-answering-mcqa-on-gpqa-diamond | Qwen3.5-122B-A10B | #27 | Accuracy: 86.6 |
| multiple-choice-question-answering-mcqa-on-gpqa-diamond | Qwen3.5-27B | #35 | Accuracy: 85.5 |
| multiple-choice-question-answering-mcqa-on-gpqa-diamond | Qwen3.5-35B-A3B | #42 | Accuracy: 84.2 |
| multiple-choice-question-answering-mcqa-on-gpqa-diamond | Qwen3.5-9B | #51 | Accuracy: 81.7 |
| code-generation-on-swe-bench-verified | Qwen3.5-397B-A17B (Internal agent scaffold) | #20 | Accuracy: 76.4 |
| code-generation-on-swe-bench-verified | Qwen3.5-27B | #32 | Accuracy: 72.4 |
| code-generation-on-swe-bench-verified | Qwen3.5-122B-A10B | #35 | Accuracy: 72.0 |
| code-generation-on-swe-bench-verified | Qwen3.5-35B-A3B | #47 | Accuracy: 69.2 |
| code-generation-on-swe-bench-multilingual | Qwen3.5-397B-A17B (Internal agent scaffold) | #22 | Accuracy: 69.3 |
| deep-research-agents-on-browsecomp | Qwen3.5-397B-A17B | #30 | Accuracy: 69.0 |
| deep-research-agents-on-browsecomp | Qwen3.5-122B-A10B | #36 | Accuracy: 63.8 |
| deep-research-agents-on-browsecomp | Qwen3.5-27B | #37 | Accuracy: 61.0 |