Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Truthfulness on TruthfulQA (Accuracy, Correct out of 30, Ranking)
Loading...
83.3
Accuracy
Gemma 2 9B
-3.332
19.159
41.65
64.141
Jun 2, 2026
Jun 6, 2026
Jun 11, 2026
Jun 16, 2026
Jun 21, 2026
Jun 26, 2026
Jul 1, 2026
Accuracy
Correct Answers (out of 30)
Rank
Updated 23d ago
Evaluation Results
Method
Method
Links
Accuracy
Correct Answers (out of 30)
Rank
Gemma 2 9B
Type=Open-source, Why...
2026.06
83.3
25
1
Mistral 7B
Type=Open-source, Why...
2026.06
63.3
19
2
FP16
BIT=16, Evaluation Pro...
2026.07
52.49
-
-
VQLLM
BIT=2, Evaluation Prot...
2026.07
51.05
-
-
GSRQ
BIT=2, Evaluation Prot...
2026.07
50.12
-
-
GSRQ
BIT=1, Evaluation Prot...
2026.07
48.67
-
-
GSRQ
BIT=0.75, Evaluation P...
2026.07
47.26
-
-
VQLLM
BIT=1, Evaluation Prot...
2026.07
44.25
-
-
Llama 3 8B
Type=Open-source, Why...
2026.06
40
12
3
Claude Haiku
Type=Closed-source, Wh...
2026.06
0
0
4
Feedback
Search any
task
Search any
task