Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Multi-task Performance Evaluation on Aggregated Benchmarks
Loading...
1.3
Average Rank
RG-OPD (ours)
1.224
1.737
2.25
2.763
Jul 4, 2026
Average Rank
Updated 18d ago
Evaluation Results
Method
Method
Links
Average Rank
RG-OPD (ours)
Generation Length=1024
2026.07
1.3
RG-OPD (ours)
Generation Length=8096
2026.07
1.3
Qwen2.5(1.5B)S
Generation Length=1024
2026.07
2.7
Reverse KL [1]
Generation Length=8096
2026.07
2.7
Qwen2.5(1.5B)S
Generation Length=8096
2026.07
2.8
Reverse KL [1]
Generation Length=1024
2026.07
3
TSD-KD [10]
Generation Length=1024
2026.07
3
TSD-KD [10]
Generation Length=8096
2026.07
3.2
Feedback
Search any
task
Search any
task