Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Long-context graph reasoning on GraphWalks (F1)
Loading...
82.3
F1 Score
Gemma 4 31B
0.972
22.086
43.2
64.314
Jul 2, 2026
F1 Score
Updated 19d ago
Evaluation Results
Method
Method
Links
F1 Score
Gemma 4 31B
Model Size/Architectur...
2026.07
82.3
Gemma 4 26B-A4B
Model Size/Architectur...
2026.07
72.6
Gemma 4 12B
Model Size/Architectur...
2026.07
71
Gemma 4 E4B
Model Size/Architectur...
2026.07
50.9
Gemma 3 27B
Model Size/Architectur...
2026.07
32.8
Gemma 4 E2B
Model Size/Architectur...
2026.07
4.1
Feedback
Search any
task
Search any
task