Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Attribute Value Extraction on OA-Mine
Loading...
89.1
F1 Score
Qwen3-8B
67.26
72.93
78.6
84.27
Apr 29, 2026
F1 Score
Cost per 1k Predictions
Updated 1mo ago
Evaluation Results
Method
Method
Links
F1 Score
Cost per 1k Predictions
Qwen3-8B
Decoding Strategy=AR
2026.04
89.1
0.166
Qwen3-32B
Decoding Strategy=AR
2026.04
88.8
0.688
Phi4-14B
Decoding Strategy=HPD
2026.04
88.8
0.095
Phi4-14B
Decoding Strategy=AR
2026.04
88
0.355
Qwen3-32B
Decoding Strategy=HPD
2026.04
87.8
0.267
Qwen3-8B
Decoding Strategy=HPD
2026.04
87.8
0.069
Qwen3-4B
Decoding Strategy=AR
2026.04
87.8
0.147
Qwen3-4B
Decoding Strategy=HPD
2026.04
87.6
0.061
Qwen3-1.7B
Decoding Strategy=AR
2026.04
86.3
0.08
Qwen3-1.7B
Decoding Strategy=HPD
2026.04
84.9
0.034
GPT-4(.1)
Prompting Setting=10-shot
2026.04
82.2
32.15
GPT-4(.1)
Prompting Setting=0-shot
2026.04
68.1
-
Feedback
Search any
task
Search any
task