Multilingual Evaluation on MGSM
87.47MGSM ScoreN-3-Super 120B-A12B-Base
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| N-3-Super 120B-A12B-BaseShots=82026.04 | 87.47 | — | |
| Ling-flash base-2.0Shots=82026.04 | 82.73 | — | |
| GLM-4.5 Air-BaseShots=82026.04 | 80.33 | — | |
| Qwen3-1.7B# Total Params=1.7B, # Trained Tokens=36T2025.11 | 66.56 | — | |
| LFM2-1.2B# Total Params=1.2B, # Trained Tokens=11T2025.11 | 55.04 | — | |
| LFM2-700M# Total Params=0.70B, # Trained Tokens=11T2025.11 | 45.36 | — | |
| Gemma-3-1B# Total Params=1B, # Trained Tokens=2T2025.11 | 43.6 | — | |
| Qwen3-0.6B# Total Params=0.6B, # Trained Tokens=36T2025.11 | 41.28 | — | |
| LFM2-350M# Total Params=0.35B, # Trained Tokens=11T2025.11 | 29.52 | — | |
| Llama-3.2-1B# Total Params=1.2B, # Trained Tokens=9T2025.11 | 29.12 | — | |
| Gemma-3-4BTotal Parameters=4B, Active Parameters=4B, Trained Tokens=4T2025.11 | — | 87.28 | |
| Granite-4.0-HTotal Parameters=7B, Active Parameters=1B, Trained Tokens=15T2025.11 | — | 73.68 | |
| LFM2-2.6BTotal Parameters=2.6B, Active Parameters=2.6B, Trained Tokens=11T2025.11 | — | 74.32 | |
| LFM2-8B-A1BTotal Parameters=8.3B, Active Parameters=1.5B, Trained Tokens=13T2025.11 | — | 72.4 | |
| Llama-3.2-3BTotal Parameters=3.2B, Active Parameters=3.2B, Trained Tokens=9T2025.11 | — | 61.68 | |
| Qwen3-4BTotal Parameters=4B, Active Parameters=4B, Trained Tokens=36T2025.11 | — | 81.76 | |
| SmolLM3-3BTotal Parameters=3.1B, Active Parameters=3.1B, Trained Tokens=11T2025.11 | — | 68.72 |