Benchmark
GSM-8K (CoT)
Grade School Math 8K with Chain-of-Thought prompting, featuring 8.5K high-quality linguistically diverse grade school math word problems requiring…
- Modality
- text
- Categories
- math, reasoning
- Openness
- unknown
- Source
- llm_stats
- Reported scores
- 2
Reported scores
llm_stats
| Model | Organization | Reported value | Reported | Evidence |
|---|---|---|---|---|
| Llama 3.1 70B Instruct | Meta | 0.951 | 2024-07-23 | evidence |
| Llama 3.1 8B Instruct | Meta | 0.845 | 2024-07-23 | evidence |
Scores are partitioned by the source that reported them and are never merged into a single cross-source ranking, because the sources measure different things and say so.