kth8/Qwen3.5-4B-Claude-Opus-Reasoning-Distill-MMLU-Pro-benchmark

--- license: apache-2.0 language: - en base_model: TeichAI/Qwen3.5-4B-Claude-Opus-Reasoning-Distill datasets: - TIGER-Lab/MMLU-Pro --- Benchmark of [TeichAI/Qwen3.5-4B-Claude-Opus-Reasoning-Distill](https://huggingface.co/TeichAI/Qwen3.5-4B-Claude-Opus-Reasoning-Distill) against [TIGER-Lab/MMLU-Pro](https://huggingface.co/datasets/TIGER-Lab/MMLU-Pro) dataset. Accuracy: 72.89999999999999% with Python tool. | Metric | Value | |----------------------|---------------| | **Correct** | 729 | | **Incorrect** | 268 | | **Errors** | 3 | | **Total samples** | 1000 | | **Python tool calls**| 1078 | | **Total completion tokens** | 2,449,614 | Raw stats: ```json { "accuracy": 0.729, "correct": 729, "incorrect": 268, "error": 3, "total": 1000, "python_tool_calls": 1078, "completion_tokens": 2449614 } ```