Shivaay-4B (8-shot chain-of-thought)
Reported on 2 benchmarks across 1 task
Note: results are matched by exact model name. Different papers may use the same name for different model variants.
Reasoning2 results
- Accuracy87.41best: 97.72 (Claude 3.5 Sonnet (HPT))
- Parameters (Billion)4best: 540 (PaLM 540B (Self Improvement, Self Consistency))