Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Question Answering with Abstention on ABSTAIN-QA
Loading...
83.4
Accuracy (A)
DeepSeek-R1
51.68
59.915
68.15
76.385
Apr 18, 2026
Accuracy (A)
FU Score (A)
Uncertainty Reference Rate (U-Ref)
Updated 1mo ago
Evaluation Results
Method
Method
Links
Accuracy (A)
FU Score (A)
Uncertainty Reference Rate (U-Ref)
DeepSeek-R1
Model=DeepSeek-R1
2026.04
83.4
0.2
9.1
DeepSeek-V3
Model=DeepSeek-V3
2026.04
77.5
4.3
31.2
Qwen2.5 32B Instruct
Model=Qwen2.5 32B Inst...
2026.04
70.7
8.5
34.7
Llama3.1 8B Instruct
Model=Llama3.1 8B Inst...
2026.04
59.8
1
10.3
Qwen2.5 7B Instruct
Model=Qwen2.5 7B Instruct
2026.04
58.9
8.8
35.5
Abstain-R1
Model=Abstain-R1
2026.04
53.3
16.8
40.1
Qwen2.5 3B Instruct
Model=Qwen2.5 3B Instruct
2026.04
52.9
15.3
30
Feedback
Search any
task
Search any
task