GSM8K Benchmark

Explore score history ↗

GSM8K is an AI benchmark in the Benchmark Radar catalog.

Released: 2021-10-28
Openness: unknown
Importer: Benchmark Saturation

Source provenance

Original evidence

GSM8K results and reported scores

Reported benchmark scores · Benchmark Saturation

Reported scores: 5

Model	Organization	Reported value	Reported	Evidence
Claude 3.5 Sonnet	—	96.4	—	evidence
GPT-4.5	—	97.0	—	evidence
Kimi K2 Instruct	—	97.3	—	evidence
Llama 3.1 405B Instruct	—	96.8	—	evidence
o1	—	97.1	—	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?

GSM8K