Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Competition Mathematics on OlympiadBench (Accuracy (avg@4))
Loading...
61.1
Accuracy (avg@4)
PAPO
20.852
31.301
41.75
52.199
Mar 27, 2026
Accuracy (avg@4)
Updated 20d ago
Evaluation Results
Method
Method
Links
Accuracy (avg@4)
PAPO
Model=Qwen3-4B-Base
2026.03
61.1
PAPO
Model=Qwen2.5-14B
2026.03
59.8
ORM(DAPO)
Model=Qwen3-4B-Base
2026.03
55
ORM(GRPO)
Model=Qwen2.5-14B
2026.03
54.3
PAPO
Model=Qwen2.5-7B
2026.03
51.3
ORM(GRPO)
Model=Qwen2.5-7B
2026.03
46.3
PAPO
Model=Qwen2.5-3B
2026.03
38.6
Base
Model=Qwen3-4B-Base
2026.03
36.8
Base
Model=Qwen2.5-14B
2026.03
35.5
ORM(GRPO)
Model=Qwen2.5-3B
2026.03
35.3
Base
Model=Qwen2.5-7B
2026.03
32.8
Base
Model=Qwen2.5-3B
2026.03
22.4
Feedback
Search any
task
Search any
task