Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Mathematical Reasoning on GSM8K (Acc., Final Gap)
Loading...
81.2
Accuracy
Pioneer Agent
11.832
29.841
47.85
65.859
Apr 10, 2026
Accuracy
Final Gap
Updated 5d ago
Evaluation Results
Method
Method
Links
Accuracy
Final Gap
Pioneer Agent
Model=Qwen3-8B, System...
2026.04
81.2
16.5
Pioneer Agent
Model=Qwen3-8B, System...
2026.04
75.9
16.5
Naive Baseline
Model=Qwen3-8B, System...
2026.04
71.6
16.5
Naive Baseline
Model=Qwen3-8B, System...
2026.04
64.7
16.5
Pioneer Agent
Model=Llama 3.2-3B, Sy...
2026.04
34.8
20.3
Pioneer Agent
Model=Llama 3.2-3B, Sy...
2026.04
27.8
20.3
Naive Baseline
Model=Llama 3.2-3B, Sy...
2026.04
19.8
20.3
Naive Baseline
Model=Llama 3.2-3B, Sy...
2026.04
14.5
20.3
Feedback
Search any
task
Search any
task