Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Mathematical Reasoning on Olympiad (Pass@1 Accuracy, Length Exceeding Ratio)
Loading...
67.5
Pass@1 Accuracy
GDPO
43.164
49.482
55.8
62.118
Jan 8, 2026
Pass@1 Accuracy
Length Exceeding Ratio
Updated 3d ago
Evaluation Results
Method
Method
Links
Pass@1 Accuracy
Length Exceeding Ratio
GDPO
Model=Qwen3-4B-Instruct
2026.01
67.5
1
GRPO
Model=Qwen3-4B-Instruct
2026.01
66.8
1.6
-
Model=Qwen3-4B-Instruct
2026.01
65.7
41.3
GRPO
Model=DeepSeek-R1-7B
2026.01
60.2
1.1
GDPO
Model=DeepSeek-R1-7B
2026.01
59.7
0.4
-
Model=DeepSeek-R1-7B
2026.01
58.2
60.6
GDPO
Model=DeepSeek-R1-1.5B
2026.01
46.6
1.9
GRPO
Model=DeepSeek-R1-1.5B
2026.01
44.3
2.6
-
Model=DeepSeek-R1-1.5B
2026.01
44.1
70.1
Feedback
Search any
task
Search any
task
