Model
Qwen 7B
Alibaba · open weights
Knowledge & Reasoning
Knowledge & Reasoning| Benchmark | Score | Metric | Harness | Source | Confidence | Link |
|---|---|---|---|---|---|---|
| BBH | 45.0 | average | N/A | Self-reported | medium | arxiv.org |
| BoolQ | 76.4 | score | N/A | Self-reported | medium | arxiv.org |
| LAMBADA | 67.9 | score | N/A | Self-reported | medium | arxiv.org |
| MMLU | 56.7 | average_(%) | N/A | Independent | medium | paperswithcode.com |
| MMLU | 45.0 | exact_match | N/A | Self-reported | medium | arxiv.org |
| PIQA | 77.9 | score | N/A | Self-reported | medium | arxiv.org |
Math
MathReproduced by the community
Loading community runs…