Multitask Language Understanding on MMLU Arabic translated (test)
72MMLUTrinity Large (MoE)
Evaluation results
| Method | Links | |
|---|---|---|
| Trinity Large (MoE)Zero-shot=true2026.02 | 72 | |
| Qwen3 8BZero-shot=true2026.02 | 63 | |
| Qwen3 4BZero-shot=true2026.02 | 56 | |
| Datology 8BZero-shot=true2026.02 | 49 | |
| SmolLM3 3BZero-shot=true2026.02 | 47 | |
| LFM2.5 1.2BZero-shot=true2026.02 | 45 | |
| Granite-4.0 MicroZero-shot=true2026.02 | 44 | |
| Llama-3.1 8BZero-shot=true2026.02 | 43 | |
| Datology 3BZero-shot=true2026.02 | 42 | |
| Llama-3.2 3BZero-shot=true2026.02 | 38 | |
| Llama-3.2 1BZero-shot=true2026.02 | 27 |