Reading Comprehension on Belebele French (test)
92AccuracyTrinity Large (MoE)
Evaluation Results
| Method | Links | |
|---|---|---|
| Trinity Large (MoE)Architecture=MoE, Evaluation=zero-shot2026.02 | 92 | |
| Qwen3 8BModel size=8B, Evaluation=zero-shot2026.02 | 89 | |
| Qwen3 4BModel size=4B, Evaluation=zero-shot2026.02 | 87 | |
| Llama-3.1 8BModel size=8B, Evaluation=zero-shot2026.02 | 78 | |
| Datology 8BModel size=8B, Evaluation=zero-shot2026.02 | 77 | |
| Granite-4.0 MicroEvaluation=zero-shot2026.02 | 74 | |
| Datology 3BModel size=3B, Evaluation=zero-shot2026.02 | 63 | |
| SmolLM3 3BModel size=3B, Evaluation=zero-shot2026.02 | 61 | |
| Llama-3.2 3BModel size=3B, Evaluation=zero-shot2026.02 | 58 | |
| LFM2.5 1.2BModel size=1.2B, Evaluation=zero-shot2026.02 | 48 | |
| Llama-3.2 1BModel size=1B, Evaluation=zero-shot2026.02 | 32 |