Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Alignment on TruthfulQA MC2
Loading...
77.72
Score
Qwen3-14B
12.2936
29.2793
46.265
63.2507
May 16, 2026
Score
Updated 15d ago
Evaluation Results
Method
Method
Links
Score
Qwen3-14B
Model Scale=14B, NGM C...
2026.05
77.72
Qwen3-14B + NGM
Model Scale=14B, NGM C...
2026.05
77.6
Qwen3-8B + NGM
Model Scale=8B, NGM Co...
2026.05
76.38
Qwen3-8B
Model Scale=8B, NGM Co...
2026.05
76.13
Qwen3-1.7B + NGM
Model Scale=1.7B, NGM...
2026.05
52.51
Qwen3-1.7B
Model Scale=1.7B, NGM...
2026.05
52.39
Qwen3-4B + NGM
Model Scale=4B, NGM Co...
2026.05
35.37
Qwen3-4B
Model Scale=4B, NGM Co...
2026.05
35.25
Qwen3-0.6B + NGM
Model Scale=0.6B, NGM...
2026.05
18.48
Qwen3-0.6B
Model Scale=0.6B, NGM...
2026.05
14.81
Feedback
Search any
task
Search any
task