List your company

Tool-augmented planning on MagicEval-Tool General

97.7Name AccuracyMagicAgent-30B-A3B
16.37237.48658.679.714Feb 22, 2026

Evaluation results

MethodLinks
MagicAgent-30B-A3BScale Category=MagicAgent Series2026.0297.786.3
MagicAgent-32BScale Category=MagicAgent Series2026.0297.587.3
Qwen3-MAXScale Category=Ultra-Scale2026.0292.472.3
Kimi-K2-InstructScale Category=Ultra-Scale2026.0289.966.8
Qwen3-235B-A22B-InstructScale Category=Ultra-Scale2026.0289.367.3
GLM-4.7Scale Category=Ultra-Scale2026.0289.170.6
DeepSeek-V3.1-nothinkScale Category=Ultra-Scale2026.0286.865
Llama3.3-70B-InstructScale Category=Large-Scale2026.0274.953.8
GPT-5.2Scale Category=Ultra-Scale2026.0274.655.8
ERNIE-4.5-21B-A3B-PTScale Category=Large-Scale2026.0271.643.7
Qwen3-32B-nothinkScale Category=Large-Scale2026.0269.550.7
Qwen3-30B-A3B-InstructScale Category=Large-Scale2026.0248.334.5
GLM-4.7-FlashScale Category=Large-Scale2026.0238.326.4
Olmo-3.1-32B-InstructScale Category=Large-Scale2026.0219.511.7