Skip to content

Benchmark

GSM8K Chat

Math benchmarks measure how well models solve maths problems. Scores are percentages. Higher is better.

Models measured
1
Scores recorded
1
Sources
1
IQ weight
No weight published

Score distribution

81.9%
Mean
81.9%
Median
0%
Std dev
81.9%
10th percentile
81.9%
90th percentile
81.9%
Min

Leaderboard

#ModelScore
1Llama 3.1 Nemotron 70B Instruct· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim81.9%

Data credits: Data by LLM Stats