Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Attribute Value Extraction on AE-110K
Loading...
87.5
F1 Score
GPT-4(.1)
61.084
67.942
74.8
81.658
Apr 29, 2026
F1 Score
Cost per 1k Predictions
Updated 1mo ago
Evaluation Results
Method
Method
Links
F1 Score
Cost per 1k Predictions
GPT-4(.1)
Prompting Setting=10-shot
2026.04
87.5
17.85
Qwen3-32B
Decoding Strategy=HPD
2026.04
85.4
0.27
Qwen3-8B
Decoding Strategy=HPD
2026.04
85.3
0.07
Qwen3-4B
Decoding Strategy=HPD
2026.04
83.9
0.063
Qwen3-1.7B
Decoding Strategy=HPD
2026.04
81.4
0.035
Phi4-14B
Decoding Strategy=AR
2026.04
79.7
0.35
Qwen3-4B
Decoding Strategy=AR
2026.04
79.5
0.156
Qwen3-32B
Decoding Strategy=AR
2026.04
79.4
0.727
Qwen3-8B
Decoding Strategy=AR
2026.04
78.7
0.163
Phi4-14B
Decoding Strategy=HPD
2026.04
78.2
0.109
Qwen3-1.7B
Decoding Strategy=AR
2026.04
78
0.076
GPT-4(.1)
Prompting Setting=0-shot
2026.04
62.1
-
Feedback
Search any
task
Search any
task