Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Next-token reasoning on OMNI-MATH Easy (val)
Loading...
76.89
Accuracy
LoopRPT
8.0524
25.9237
43.795
61.6663
Mar 20, 2026
Accuracy
Average Steps
Updated 26d ago
Evaluation Results
Method
Method
Links
Accuracy
Average Steps
LoopRPT
Model=Ouro-2.6B, Reaso...
2026.03
76.89
4
LoopRPT
Model=Ouro-2.6B, Reaso...
2026.03
76.07
2.05
LoopRPT
Model=Ouro-1.4B, Reaso...
2026.03
75.38
4
LoopRPT
Model=Ouro-1.4B, Reaso...
2026.03
75
2.5
Peak
Model=Ouro-1.4B
2026.03
74.62
4
Adap.
Model=Ouro-2.6B
2026.03
74.51
3.24
Adap.
Model=Ouro-1.4B
2026.03
74.4
3.34
Peak
Model=Ouro-2.6B
2026.03
74.33
4
Vanilla
Model=Qwen3-1.7B
2026.03
47.49
-
+CoT
Model=Qwen3-1.7B
2026.03
10.7
-
Feedback
Search any
task
Search any
task
