Physical Commonsense Reasoning on PIQA (Character-level Accuracy)
75.52Character-level AccuracyMobileLLM-Flash 1.4B
Evaluation results
| Method | Links | |
|---|---|---|
| MobileLLM-Flash 1.4BParameter Count=1.4B, Evaluation Protocol=0-shot2026.03 | 75.52 | |
| Nemotron-Flash 1BParameter Count=1B, Evaluation Protocol=0-shot2026.03 | 75.41 | |
| Llama3.2 1BParameter Count=1B, Evaluation Protocol=0-shot2026.03 | 75.14 | |
| LFM2 1.2BParameter Count=1.2B, Evaluation Protocol=0-shot2026.03 | 74.27 | |
| Gemma3 1BParameter Count=1B, Evaluation Protocol=0-shot2026.03 | 73.8 | |
| MobileLLM-Flash 650MParameter Count=650M, Evaluation Protocol=0-shot2026.03 | 71.82 | |
| LFM2 700MParameter Count=700M, Evaluation Protocol=0-shot2026.03 | 71.11 | |
| MobileLLM-Flash 350MParameter Count=350M, Evaluation Protocol=0-shot2026.03 | 70.08 | |
| Qwen3 0.6BParameter Count=0.6B, Evaluation Protocol=0-shot2026.03 | 69.86 | |
| LFM2 350MParameter Count=350M, Evaluation Protocol=0-shot2026.03 | 69.48 | |
| Gemma3 270MParameter Count=270M, Evaluation Protocol=0-shot2026.03 | 68.34 |