| code-generation-on-multipl-e | Qwen3-Coder-Next | #1 | Accuracy: 88.23 |
| code-generation-on-aider-polyglot | Qwen3-Coder-Next | #2 | Accuracy: 66.2 |
| code-generation-on-terminal-bench-2-0-terminus-2 | Qwen3-Coder-Next (Terminus2-json) | #8 | Accuracy: 36.2 |
| multi-task-language-understanding-on-mmlu-redux | Qwen3-Coder-Next | #13 | Accuracy: 91.18 |
| multiple-choice-question-answering-mcqa-on-supergpqa | Qwen3-Coder-Next | #13 | Accuracy: 57.45 |
| mathematical-reasoning-on-aime24 | Qwen3-Coder-Next | #14 | Acc: 89.01 |
| code-generation-on-swe-bench-multilingual | Qwen3-Coder-Next (OpenHands) | #27 | Accuracy: 64.3 |
| mathematical-reasoning-on-aime-2025 | Qwen3-Coder-Next | #36 | Accuracy: 83.07 |
| code-generation-on-swe-bench-verified | Qwen3-Coder-Next (OpenHands) | #37 | Accuracy: 71.3 |
| multi-task-language-understanding-on-mmlu-pro | Qwen3-Coder-Next | #41 | Accuracy: 80.52 |
| code-generation-on-livecodebench-v6 | Qwen3-Coder-Next | #43 | Pass@1: 58.93 |