Multi-domain evaluation on GRAFITE Sample Dataset (Total)
63.2Pass RateLlama-4-Maverick-17B-128E-Instruct
Evaluation Results
| Method | Links | |
|---|---|---|
| Llama-4-Maverick-17B-128E-InstructModel=LMav, Parameters=17B2026.03 | 63.2 | |
| Llama-3.3-70B-InstructModel=L3.3, Parameters=70B2026.03 | 57.9 | |
| Llama-3.1-8B-InstructModel=L3.1, Parameters=8B2026.03 | 42.1 | |
| Llama-3.2-3B-InstructModel=L3.2, Parameters=3B2026.03 | 26.3 |