Mathematical Reasoning on GSM8K s (subsampled 2500) (Accuracy)
96AccuracyLlama 8B (Gem)
Evaluation Results
| Method | Links | |
|---|---|---|
| Llama 8B (Gem)Tree=Llama 8B, Model Category=Hidden Gem2026.01 | 96 | |
| Qwen 7B (Gem)Tree=Qwen 7B, Model Category=Hidden Gem2026.01 | 92.1 | |
| Qwen 7B (Base)Tree=Qwen 7B, Model Category=Popular Consensus (Base)2026.01 | 89.7 | |
| Qwen 3B (Gem)Tree=Qwen 3B, Model Category=Hidden Gem2026.01 | 89 | |
| Qwen 3B (Base)Tree=Qwen 3B, Model Category=Popular Consensus (Base)2026.01 | 83.5 | |
| Llama 8B (Base)Tree=Llama 8B, Model Category=Popular Consensus (Base)2026.01 | 83.2 | |
| Mistral 7B (Gem)Tree=Mistral 7B, Model Category=Hidden Gem2026.01 | 80.7 | |
| Mistral 7B (Base)Tree=Mistral 7B, Model Category=Popular Consensus (Base)2026.01 | 40.6 |