Benchmark
GSM8K Benchmark
What is GSM8K?
Saturated. A legacy baseline for small open models. Benchmark Radar tracks 1 reported scores for GSM8K, cited by 7 source documents, with links to its code.
- Released
- 2021-10-27
- Evaluates
- math
- Openness
- unknown
- Importer
- Model reports
- Reported scores
- 1
Source provenance
- Original evidence https://github.com/openai/grade-school-math
GSM8K code
GSM8K results and reported scores
Model reports
| Model | Organization | Reported value | Reported | Evidence |
|---|---|---|---|---|
| Gemini 1.5 Pro | 90.8 | 2024-03-08 | 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.
Which sources cite GSM8K?
- DeepSeek-V4-Pro DeepSeek, 2026-04-22
- Olmo 3 (7B and 32B) Ai2, 2025-11-20
- DeepSeek-V3 DeepSeek, 2024-12-27
- Qwen2.5-Coder Qwen, 2024-09-18
- Mistral Large 2 Mistral, 2024-07-24
- Llama 3.1 405B Meta, 2024-07-23
- Gemini 1.5 Google, 2024-03-08