| agents-on-claw-eval | ThinkingCap-Qwen3.6-27B | #1 | Accuracy: 84.4 |
| multi-task-language-understanding-on-mmlu-redux | ThinkingCap-Qwen3.6-27B | #3 | Accuracy: 93.9 |
| multiple-choice-question-answering-mcqa-on-supergpqa | ThinkingCap-Qwen3.6-27B | #8 | Accuracy: 64.0 |
| arithmetic-reasoning-on-gsm8k | ThinkingCap-Qwen3.6-27B | #9 | Accuracy: 96.5 |
| multi-task-language-understanding-on-c-eval | ThinkingCap-Qwen3.6-27B | #10 | Accuracy: 90.3 |
| visual-question-answering-vqa-on-realworldqa | ThinkingCap-Qwen3.6-27B | #10 | Accuracy: 81.9 |
| code-generation-on-livecodebench-v6 | ThinkingCap-Qwen3.6-27B | #12 | Pass@1: 84.3 |
| multi-task-language-understanding-on-mmlu-pro | ThinkingCap-Qwen3.6-27B | #12 | Accuracy: 85.4 |
| multiple-choice-question-answering-mcqa-on-gpqa-diamond | ThinkingCap-Qwen3.6-27B | #43 | Accuracy: 83.8 |