General Language Performance on Aggregate Suite
78.03Average ScoreQwen3-4B
Evaluation Results
| Method | Links | |
|---|---|---|
| Qwen3-4BParams=4B2025.12 | 78.03 | |
| Qwen2.5-3BParams=3B2025.12 | 71.54 | |
| Qwen3-1.7BParams=1.7B2025.12 | 68.44 | |
| Qwen2.5-1.5BParams=1.5B2025.12 | 65.57 | |
| SmolLM3-3BParams=3B2025.12 | 64.61 | |
| llama-3.2-3BParams=3B2025.12 | 62.31 | |
| YuLan-Mini-2.4BParams=2.4B2025.12 | 61.7 | |
| Qwen2-1.5BParams=1.5B2025.12 | 61.08 | |
| PCMind-2.1-Kaiyuan-2BParams=2B2025.12 | 59.07 | |
| Qwen3-0.6BParams=0.6B2025.12 | 57.11 | |
| gemma2-2BParams=2B2025.12 | 53.26 | |
| SmolLM2-1.7BParams=1.7B2025.12 | 51.89 | |
| OLMo-2-0425-1BParams=1B2025.12 | 48.6 | |
| llama-3.2-1BParams=1B2025.12 | 47.25 |