Question Answering on ARC-Challenge subsampled s (2500)
91.1AccuracyQwen 7B (Gem)
Evaluation Results
| Method | Links | |
|---|---|---|
| Qwen 7B (Gem)Tree=Qwen 7B, Model Category=Hidden Gem2026.01 | 91.1 | |
| Qwen 7B (Base)Tree=Qwen 7B, Model Category=Popular Consensus (Base)2026.01 | 90 | |
| Llama 8B (Gem)Tree=Llama 8B, Model Category=Hidden Gem2026.01 | 86 | |
| Qwen 3B (Gem)Tree=Qwen 3B, Model Category=Hidden Gem2026.01 | 84.1 | |
| Mistral 7B (Gem)Tree=Mistral 7B, Model Category=Hidden Gem2026.01 | 81.8 | |
| Llama 8B (Base)Tree=Llama 8B, Model Category=Popular Consensus (Base)2026.01 | 80.9 | |
| Qwen 3B (Base)Tree=Qwen 3B, Model Category=Popular Consensus (Base)2026.01 | 79.3 | |
| Mistral 7B (Base)Tree=Mistral 7B, Model Category=Popular Consensus (Base)2026.01 | 74.6 |