Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Knowledge-intensive Question Answering on TriviaQA
Loading...
71.7
Pass@1 Accuracy
Baseline
17.1
31.275
45.45
59.625
Jun 5, 2026
Pass@1 Accuracy
Token Count
Updated 1mo ago
Evaluation Results
Method
Method
Links
Pass@1 Accuracy
Token Count
Baseline
backbone=QwQ-32B
2026.06
71.7
630
DyCon
backbone=QwQ-32B
2026.06
71.7
592
DyCon
backbone=Qwen3-14B
2026.06
66.8
440
Baseline
backbone=Qwen3-14B
2026.06
66.4
508
DyCon
backbone=Qwen3-4B-Thin...
2026.06
34.1
729
Baseline
backbone=Qwen3-4B-Thin...
2026.06
33.5
1,041
DyCon
backbone=DeepSeek-R1-D...
2026.06
19.6
619
Baseline
backbone=DeepSeek-R1-D...
2026.06
19.2
1,295
Feedback
Search any
task
Search any
task