Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Multi-Motif Counting on LLMTM Level 2 1.0 (test)
Loading...
19.69
Accuracy
Qwen2.5-32B
-0.59
4.675
9.94
15.205
Dec 24, 2025
Accuracy
Updated 3d ago
Evaluation Results
Method
Method
Links
Accuracy
Qwen2.5-32B
2025.12
19.69
DeepSeek-R1
2025.12
13.41
GPT-4o-mini
2025.12
13.07
DeepSeek-Qwen-14B
2025.12
6.08
DeepSeek-Qwen-32B
2025.12
5.4
DeepSeek-Qwen-7B
2025.12
2
o3
2025.12
1.94
QwQ-32B
2025.12
0.4
openPangu-7B
2025.12
0.19
Feedback
Search any
task
Search any
task