Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Revision-cycle prediction on FIRSTPASS n=318 (test)
Loading...
78.2
F1 Macro
FIRSTPASS
37.952
48.401
58.85
69.299
Jun 18, 2026
F1 Macro
F1 Extended
McNemar p-value
Accuracy
Updated 1mo ago
Evaluation Results
Method
Method
Links
F1 Macro
F1 Extended
McNemar p-value
Accuracy
FIRSTPASS
loss_masking=true, ada...
2026.06
78.2
71
-
80.5
Qwen2.5-7B
prompting_strategy=zer...
2026.06
73.3
63.3
0.185
77
Gemini-3.1-flash-lite-preview
prompting_strategy=zer...
2026.06
56.3
31.7
0.001
70.1
Qwen2.5-7B + LoRA
loss_masking=false, ad...
2026.06
56.2
40.4
0.001
62
Llama-3-8B
prompting_strategy=zer...
2026.06
48.3
16.4
0.001
67.9
Majority baseline
strategy=constant pred...
2026.06
39.5
0
0.001
65.4
Qwen2.5-7B
prompting_strategy=5-shot
2026.06
39.5
0
0.001
65.4
DeepSeek-R1-7B
prompting_strategy=zer...
2026.06
39.5
0
0.001
65.4
Feedback
Search any
task
Search any
task