Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Math Reasoning on OlympiadBench (Pass@1 accuracy)
Loading...
48.2
Pass@1 Accuracy
s1.1-7B
22.2
28.95
35.7
42.45
Dec 16, 2025
Dec 20, 2025
Dec 25, 2025
Dec 30, 2025
Jan 3, 2026
Jan 8, 2026
Jan 13, 2026
Pass@1 Accuracy
Updated 4d ago
Evaluation Results
Method
Method
Links
Pass@1 Accuracy
s1.1-7B
Backbone=Qwen2.5-7B, P...
2025.12
48.2
Multiplex Thinking
Backbone=DeepSeek-R1-D...
2026.01
41.7
Stochastic Soft Thinking
Backbone=DeepSeek-R1-D...
2026.01
40.6
Qwen Instruct
Backbone=Qwen2.5-7B, P...
2025.12
38.7
Discrete RL
Backbone=DeepSeek-R1-D...
2026.01
38
Qwen Instruct
Backbone=Qwen2.5-Math-...
2025.12
37.9
Discrete CoT
Backbone=DeepSeek-R1-D...
2026.01
35.6
Ladder
Backbone=Qwen2.5-7B, P...
2025.12
34.3
QLoRA
Backbone=Qwen2.5-Math-...
2025.12
33.7
Ladder
Backbone=Qwen2.5-Math-...
2025.12
32.7
QLoRA
Backbone=Qwen2.5-7B, P...
2025.12
32
Multiplex Thinking
Backbone=DeepSeek-R1-D...
2026.01
31.3
Discrete RL
Backbone=DeepSeek-R1-D...
2026.01
31.2
Stochastic Soft Thinking
Backbone=DeepSeek-R1-D...
2026.01
30.6
Discrete CoT
Backbone=DeepSeek-R1-D...
2026.01
30.5
Qwen Base
Backbone=Qwen2.5-7B, P...
2025.12
30.2
Full SFT
Backbone=Qwen2.5-7B, P...
2025.12
27.6
Qwen Base
Backbone=Qwen2.5-Math-...
2025.12
23.8
Full SFT
Backbone=Qwen2.5-Math-...
2025.12
23.2
Feedback
Search any
task
Search any
task