Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
NLG Meta-evaluation on CUS-QA orig. (uk)
Loading...
0.681
Kendall Correlation
Qwen 3 30B
0.46572
0.52161
0.5775
0.63339
Mar 10, 2026
Kendall Correlation
Updated 1mo ago
Evaluation Results
Method
Method
Links
Kendall Correlation
Qwen 3 30B
Shot=Zero
2026.03
0.681
Llama 3.3 70B
Shot=Few
2026.03
0.584
Llama 4 Scout
Shot=Zero
2026.03
0.573
Llama 4 Scout
Shot=Few
2026.03
0.533
Qwen 3 30B
Shot=Few
2026.03
0.516
Llama 3.3 70B
Shot=Zero
2026.03
0.474
Feedback
Search any
task
Search any
task