Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Command Understanding on MiCU Dataset
Loading...
94.61
Overall Accuracy
MiCU-4B
31.69
48.025
64.36
80.695
May 31, 2026
Overall Accuracy
Updated 1d ago
Evaluation Results
Method
Method
Links
Overall Accuracy
MiCU-4B
Type=Open Source LLM
2026.05
94.61
MiCU-4B-fast
Type=Open Source LLM
2026.05
94.01
DeepSeek-V3.2
Type=Proprietary LLM
2026.05
74.6
GPT-4o
Type=Proprietary LLM
2026.05
73.57
DeepSeek-R1
Type=Proprietary LLM
2026.05
73.1
Rule-based Selection
Type=Rule-based
2026.05
66.32
Qwen3-30B
Type=Open Source LLM
2026.05
64.01
GPT-4o-mini
Type=Proprietary LLM
2026.05
63.79
Llama3.3-70B
Type=Open Source LLM
2026.05
61.61
Llama3.1-8B
Type=Open Source LLM
2026.05
54.31
Qwen3-4B
Type=Open Source LLM
2026.05
34.11
Feedback
Search any
task
Search any
task