Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Mathematical Reasoning on OlympiadBench (Accuracy, Pass@1)
Loading...
64
Pass@1
Qwen3-4B-Instruct-2507
37.792
44.596
51.4
58.204
Dec 8, 2025
Dec 17, 2025
Dec 26, 2025
Jan 4, 2026
Jan 13, 2026
Jan 22, 2026
Jan 31, 2026
Pass@1
Accuracy
Updated 3d ago
Evaluation Results
Method
Method
Links
Pass@1
Accuracy
Qwen3-4B-Instruct-2507
Data=N/A, Train=N/A, B...
2025.12
64
-
NPR
Data=orz-8k, Train=Par...
2025.12
63.7
-
SR
Data=orz-8k, Train=Seq...
2025.12
62.2
-
NPR (Variant)
Data=orz-8k, Train=Par...
2025.12
61.9
-
NPR-BETA
Data=orz-8k, Train=Par...
2025.12
60.1
-
NPR-BETA (Variant)
Data=orz-8k, Train=Par...
2025.12
57.8
-
SR-BETA
Data=orz-8k, Train=Seq...
2025.12
56.3
-
Qwen3-4B (Non-Thinking)
Data=N/A, Train=N/A, B...
2025.12
48.6
-
Multiverse-32B
Data=s1.1-8k, Train=S→...
2025.12
48
-
Qwen2.5-32B-Instruct
Data=N/A, Train=N/A, B...
2025.12
46.4
-
Segment Selective SFT
Model Backbone=Qwen2.5...
2026.01
41.9
-
Multiverse-4B
Data=s1.1-8k, Train=S→...
2025.12
38.8
-
Feedback
Search any
task
Search any
task