Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Mathematical Reasoning on OlympiadBench (Avg@3)
Loading...
36
Avg@3
ADORA
1.056
10.128
19.2
28.272
Feb 10, 2026
Avg@3
Updated 4d ago
Evaluation Results
Method
Method
Links
Avg@3
ADORA
Backbone=Qwen2.5-7B, T...
2026.02
36
GRPO
Backbone=Qwen2.5-7B, S...
2026.02
35.1
Qwen2.5-7B
Training Method=Base,...
2026.02
26.3
ADORA
Backbone=DeepSeek-Math...
2026.02
12.9
GRPO
Backbone=DeepSeek-Math...
2026.02
12
ADORA
Backbone=Llama-3.1-8B,...
2026.02
10.5
GRPO
Backbone=Llama-3.1-8B,...
2026.02
5.3
ADORA
Backbone=Mistral-v0.1-...
2026.02
4.7
GRPO
Backbone=Mistral-v0.1-...
2026.02
4.1
Llama-3.1-8B
Training Method=Base,...
2026.02
3.1
DeepSeek-Math-7B
Training Method=Base,...
2026.02
3
Mistral-v0.1-7B
Training Method=Base,...
2026.02
2.4
Feedback
Search any
task
Search any
task