model: Macaron-V1-Venti
source:
  name: Model Card
  url: https://huggingface.co/mindlab-research/Macaron-V1-Venti
notes:
  higher_is_better: true
  missing_values_are_null: false
baselines:
  - Macaron V1
  - GLM 5.2
  - GPT 5.5
  - Claude Opus 4.8
  - Gemini 3.1 Pro
  - Qwen 3.7 Max
  - Minimax M3
results:
  - benchmark: ChatBench
    scores: {Macaron V1: 58.3, GLM 5.2: 54.5, GPT 5.5: 55.5, Claude Opus 4.8: 52.8, Gemini 3.1 Pro: 52.0, Qwen 3.7 Max: 52.5, Minimax M3: 49.1}
  - benchmark: LivingBench
    scores: {Macaron V1: 64.0, GLM 5.2: 60.5, GPT 5.5: 61.9, Claude Opus 4.8: 63.8, Gemini 3.1 Pro: 52.1, Qwen 3.7 Max: 56.1, Minimax M3: 57.1}
  - benchmark: VitaBench
    scores: {Macaron V1: 60.0, GLM 5.2: 55.8, GPT 5.5: 55.8, Claude Opus 4.8: 56.5, Gemini 3.1 Pro: 55.2, Qwen 3.7 Max: 61.2, Minimax M3: 56.8}
  - benchmark: PinchBench
    scores: {Macaron V1: 94.0, GLM 5.2: 88.1, GPT 5.5: 89.0, Claude Opus 4.8: 91.8, Gemini 3.1 Pro: 82.9, Qwen 3.7 Max: 93.4, Minimax M3: 86.1}
  - benchmark: ClawGym
    scores: {Macaron V1: 77.7, GLM 5.2: 74.6, GPT 5.5: 82.5, Claude Opus 4.8: 80.5, Gemini 3.1 Pro: 77.5, Qwen 3.7 Max: 75.7, Minimax M3: 76.2}
  - benchmark: SWE Verified
    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}
  - benchmark: TerminalBench 2.1
    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}
  - benchmark: DeepSWE
    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}
  - benchmark: SWE Atlas QnA
    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}
  - benchmark: UI4ABench
    scores: {Macaron V1: 87.8, GLM 5.2: 67.1, GPT 5.5: 72.1, Claude Opus 4.8: 75.9, Gemini 3.1 Pro: 60.3, Qwen 3.7 Max: 62.5, Minimax M3: 63.0}