Qwen1.5 72B (5-shot)
Reported on 2 benchmarks across 2 tasks
Note: results are matched by exact model name. Different papers may use the same name for different model variants.
Methodology2 results
- Average (%)77.5best: 87 (GPT-4 o1(300b))
- Average (%)77.5best: 87 (GPT-4 o1(300b))