Question Answering on MMLU-X
69.3AccuracyGemma 2
Evaluation Results
| Method | Links | |
|---|---|---|
| Gemma 2shot_count=5-shot2026.03 | 69.3 | |
| ALIAshot_count=5-shot2026.03 | 60.7 | |
| TildeOpen LLMshot_count=5-shot2026.03 | 59.9 | |
| EuroLLMshot_count=5-shot2026.03 | 59.3 | |
| SmolLM2-1.7bprompting=Zero-shot, data_tokens=11T, gpu_hours=not reported2025.12 | 32 | |
| Gemma-3-1b-ittuning=Instruction-tuned, prompt_language=English2025.12 | 31.1 | |
| SmolLM2-1.7b-Instructtuning=Instruction-tuned, prompt_language=English2025.12 | 27.1 | |
| EuroLLM-1.7bprompting=Zero-shot, data_tokens=4T, gpu_hours=500K2025.12 | 25 | |
| MiniLingua-1b-Instructtuning=Instruction-tuned, prompt_language=English2025.12 | 24.5 | |
| MiniLingua-1bprompting=Zero-shot, data_tokens=1.5T, gpu_hours=75K2025.12 | 24 | |
| EuroLLM-1.7b-Instructtuning=Instruction-tuned, prompt_language=English2025.12 | 20.5 | |
| Gemma-3-1b-ptprompting=Zero-shot, data_tokens=2T, gpu_hours=∼300K2025.12 | 20 |