Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Reasoning / Reward on RR
Loading...
73.2
RR Average
Qwen2.5-Coder-14B-Ins
27.544
39.397
51.25
63.103
Jun 4, 2026
RR Average
Updated 1mo ago
Evaluation Results
Method
Method
Links
RR Average
Qwen2.5-Coder-14B-Ins
Model Family=AZR Serie...
2026.06
73.2
ANCHOR-8B
Model Family=R-Zero Se...
2026.06
73.2
ANCHOR-Coder-14B
Model Family=AZR Serie...
2026.06
70.7
AZR-Coder-14B
Model Family=AZR Serie...
2026.06
65.9
ANCHOR-Coder-7B
Model Family=AZR Serie...
2026.06
61
Qwen3-8B-Base
Model Family=R-Zero Se...
2026.06
61
AZR-Coder-3B
Model Family=AZR Serie...
2026.06
58.5
ANCHOR-Coder-3B
Model Family=AZR Serie...
2026.06
58.5
Qwen2.5-Coder-7B-Ins
Model Family=AZR Serie...
2026.06
58.5
Qwen2.5-7B-Ins
Model Family=AZR Serie...
2026.06
56.1
Qwen3-4B-Base
Model Family=R-Zero Se...
2026.06
56.1
Qwen2.5-Coder-3B-Ins
Model Family=AZR Serie...
2026.06
53.7
AZR-Coder-7B
Model Family=AZR Serie...
2026.06
53.7
ANCHOR-4B
Model Family=R-Zero Se...
2026.06
53.7
ANCHOR-7B
Model Family=AZR Serie...
2026.06
46.3
AZR-7B
Model Family=AZR Serie...
2026.06
36.6
R-Zero-8B
Model Family=R-Zero Se...
2026.06
34.1
R-Zero-4B
Model Family=R-Zero Se...
2026.06
29.3
Feedback
Search any
task
Search any
task