mindlab-research/Macaron-V1-Coding-Venti

1model: Macaron-V1-Coding-Venti2source:3  name: Model Card4  url: https://huggingface.co/mindlab-research/Macaron-V1-Coding-Venti5notes:6  higher_is_better: true7  missing_values_are_null: false8  checkpoint_type: merged GLM-5.2 BF16 checkpoint with Macaron-V1 L2 Coding LoRA update merged into the base weights9baselines:10  - Macaron V111  - GLM 5.212  - GPT 5.513  - Claude Opus 4.814  - Gemini 3.1 Pro15  - Qwen 3.7 Max16  - Minimax M317results:18  - benchmark: SWE Verified19    scores: {Macaron V1: 85.6, GLM 5.2: 80.4, GPT 5.5: 82.9, Claude Opus 4.8: 88.6, Gemini 3.1 Pro: 80.6, Qwen 3.7 Max: 80.4, Minimax M3: 80.5}20  - benchmark: TerminalBench 2.121    scores: {Macaron V1: 87.6, GLM 5.2: 82.7, GPT 5.5: 83.4, Claude Opus 4.8: 78.9, Gemini 3.1 Pro: 70.7, Qwen 3.7 Max: 73.5, Minimax M3: 66.0}22  - benchmark: DeepSWE23    scores: {Macaron V1: 58.4, GLM 5.2: 54.9, GPT 5.5: 70.0, Claude Opus 4.8: 58.0, Gemini 3.1 Pro: 10.0, Qwen 3.7 Max: 18.0, Minimax M3: 20.0}24  - benchmark: SWE Atlas QnA25    scores: {Macaron V1: 49.5, GLM 5.2: 48.9, GPT 5.5: 45.4, Claude Opus 4.8: 57.3, Gemini 3.1 Pro: 13.5, Qwen 3.7 Max: 22.6, Minimax M3: 37.9}26