Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Grade School Math Reasoning on GSM8K No CoT augmented (test)
Loading...
0.2482
Accuracy
TurboConn
0.064952
0.112526
0.1601
0.207674
Feb 20, 2026
Accuracy
Updated 1mo ago
Evaluation Results
Method
Method
Links
Accuracy
TurboConn
Model=Llama 3.1 8B
2026.02
0.2482
Baseline
Model=Llama 3.1 8B
2026.02
0.2392
TurboConn
Model=Qwen 3 1.7B
2026.02
0.2031
Baseline
Model=Qwen 3 1.7B
2026.02
0.159
TurboConn
Model=Llama 3.2 1B
2026.02
0.0832
Baseline
Model=Llama 3.2 1B
2026.02
0.072
Feedback
Search any
task
Search any
task