Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Multi-domain evaluation on GRAFITE Sample Dataset (Total)
Loading...
63.2
Pass Rate
Llama-4-Maverick-17B-128E-Instruct
24.824
34.787
44.75
54.713
Mar 18, 2026
Pass Rate
Updated 1mo ago
Evaluation Results
Method
Method
Links
Pass Rate
Llama-4-Maverick-17B-128E-Instruct
Model=LMav, Parameters...
2026.03
63.2
Llama-3.3-70B-Instruct
Model=L3.3, Parameters...
2026.03
57.9
Llama-3.1-8B-Instruct
Model=L3.1, Parameters=8B
2026.03
42.1
Llama-3.2-3B-Instruct
Model=L3.2, Parameters=3B
2026.03
26.3
Feedback
Search any
task
Search any
task