Language Understanding on MMLU French (test)
71AccuracyTrinity Large (MoE)
Evaluation results
| Method | Links | |
|---|---|---|
| Trinity Large (MoE)Architecture=MoE, Evaluation=zero-shot2026.02 | 71 | |
| Qwen3 8BModel size=8B, Evaluation=zero-shot2026.02 | 69 | |
| Qwen3 4BModel size=4B, Evaluation=zero-shot2026.02 | 66 | |
| Datology 8BModel size=8B, Evaluation=zero-shot2026.02 | 55 | |
| Llama-3.1 8BModel size=8B, Evaluation=zero-shot2026.02 | 54 | |
| Granite-4.0 MicroEvaluation=zero-shot2026.02 | 53 | |
| SmolLM3 3BModel size=3B, Evaluation=zero-shot2026.02 | 52 | |
| LFM2.5 1.2BModel size=1.2B, Evaluation=zero-shot2026.02 | 50 | |
| Llama-3.2 3BModel size=3B, Evaluation=zero-shot2026.02 | 46 | |
| Datology 3BModel size=3B, Evaluation=zero-shot2026.02 | 43 | |
| Llama-3.2 1BModel size=1B, Evaluation=zero-shot2026.02 | 29 | |
| GenKnowSubBase Model=Phi-2, Evaluation Setting=Zero-shot, Setting=En2025.05 | 26.11 | |
| ArrowBase Model=Phi-2, Evaluation Setting=Zero-shot2025.05 | 25.68 | |
| GenKnowSubBase Model=Phi-2, Evaluation Setting=Zero-shot, Setting=Avg2025.05 | 25 | |
| Phi-2Base Model=Phi-2, Evaluation Setting=Zero-shot2025.05 | 24.77 |