List your company

Tool-augmented planning on MagicEval-Tool Condition

95.4Name AccuracyMagicAgent-32B
7.31230.18153.0575.919Feb 22, 2026

Evaluation results

MethodLinks
MagicAgent-32BScale Category=MagicAgent Series2026.0295.488.7
MagicAgent-30B-A3BScale Category=MagicAgent Series2026.0294.287.2
Kimi-K2-InstructScale Category=Ultra-Scale2026.0288.771
Qwen3-MAXScale Category=Ultra-Scale2026.0288.169.5
Qwen3-235B-A22B-InstructScale Category=Ultra-Scale2026.0287.569.2
DeepSeek-V3.1-nothinkScale Category=Ultra-Scale2026.0286.666.5
GLM-4.7Scale Category=Ultra-Scale2026.0282.665.6
Llama3.3-70B-InstructScale Category=Large-Scale2026.0276.853.1
GPT-5.2Scale Category=Ultra-Scale2026.0273.558.2
ERNIE-4.5-21B-A3B-PTScale Category=Large-Scale2026.0261.340.2
Qwen3-32B-nothinkScale Category=Large-Scale2026.0257.644.2
Qwen3-30B-A3B-InstructScale Category=Large-Scale2026.0240.229.7
GLM-4.7-FlashScale Category=Large-Scale2026.0227.420.1
Olmo-3.1-32B-InstructScale Category=Large-Scale2026.0210.75.2