List your company

Tool-augmented planning on MagicEval-Tool Dependency

98.5Name AccMagicAgent-30B-A3B
18.21239.05659.980.744Feb 22, 2026

Evaluation results

MethodLinks
MagicAgent-30B-A3BScale Category=MagicAgent Series2026.0298.578.5
MagicAgent-32BScale Category=MagicAgent Series2026.0297.580
Kimi-K2-InstructScale Category=Ultra-Scale2026.029158.3
Qwen3-MAXScale Category=Ultra-Scale2026.029058.3
Qwen3-235B-A22B-InstructScale Category=Ultra-Scale2026.0289.555.3
DeepSeek-V3.1-nothinkScale Category=Ultra-Scale2026.0286.854.8
GLM-4.7Scale Category=Ultra-Scale2026.0285.356.5
Llama3.3-70B-InstructScale Category=Large-Scale2026.027141.8
Qwen3-32B-nothinkScale Category=Large-Scale2026.0269.843.8
GPT-5.2Scale Category=Ultra-Scale2026.0267.846.5
ERNIE-4.5-21B-A3B-PTScale Category=Large-Scale2026.0261.532.8
Qwen3-30B-A3B-InstructScale Category=Large-Scale2026.0249.330
GLM-4.7-FlashScale Category=Large-Scale2026.0224.813
Olmo-3.1-32B-InstructScale Category=Large-Scale2026.0221.39.5