Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Comparative Relationship Prediction on PANDABENCH Easy
Loading...
58
Accuracy
PANDA
18.48
28.74
39
49.26
Apr 13, 2026
Accuracy
Precision
Recall
F1 Score
Updated 5d ago
Evaluation Results
Method
Method
Links
Accuracy
Precision
Recall
F1 Score
PANDA
Model Type=Open-source
2026.04
58
61
54
56
DepictQA
Model Type=Open-source...
2026.04
49
48
38
42
Attentive Probe
Model Type=Baseline
2026.04
47
47
42
43
Linear Probe
Model Type=Baseline
2026.04
37
35
22
15
GPT-5 Nano
Model Type=Closed-source
2026.04
34
26
28
26
GPT-5 Mini
Model Type=Closed-source
2026.04
31
32
31
26
GPT-4o
Model Type=Closed-source
2026.04
26
29
26
23
Gemini 2.5 Pro
Model Type=Closed-source
2026.04
22
29
25
18
Random
Model Type=Baseline
2026.04
20
20
20
19
Feedback
Search any
task
Search any
task