Model

LLaMA 2 13B

Meta · open weights

Knowledge & Reasoning

Benchmark	Score	Metric	Harness	Source	Confidence	Link
BBH	58.2	average	N/A	Independent	medium	arxiv.org
BBH	39.4	average	N/A	Self-reported	medium	arxiv.org
BoolQ	82.4	score	N/A	Independent	medium	arxiv.org
BoolQ	81.7	accuracy	N/A	Independent	medium	arxiv.org
BoolQ	81.7	score	N/A	Self-reported	medium	arxiv.org
EconLogicQA	14.6	accuracy	N/A	Independent	medium	arxiv.org
HellaSwag	80.7	accuracy	N/A	Independent	medium	arxiv.org
HellaSwag	80.7	overall_accuracy	N/A	Independent	medium	arxiv.org
LAMBADA	76.5	score	N/A	Independent	medium	arxiv.org
MMLU	55.6	exact_match	N/A	Independent	medium	arxiv.org
MMLU	54.8	average_(%)	N/A	Independent	medium	arxiv.org
MMLU	54.8	exact_match	N/A	Self-reported	medium	arxiv.org
OpenBookQA	57.0	accuracy	N/A	Self-reported	medium	arxiv.org
PIQA	80.8	score	N/A	Independent	medium	arxiv.org
PIQA	80.5	accuracy	N/A	Independent	medium	arxiv.org
PIQA	80.5	score	N/A	Self-reported	medium	arxiv.org
ScienceQA	55.8	score	N/A	Independent	medium	scienceqa.github.io
Trivia QA	79.6	exact_match	N/A	Self-reported	medium	arxiv.org
Trivia QA	79.6	exact_match	N/A	Independent	medium	arxiv.org
WinoGrande	72.8	accuracy	N/A	Self-reported	medium	arxiv.org
WinoGrande	72.8	accuracy	N/A	Independent	medium	arxiv.org

Benchmark	Score	Metric	Harness	Source	Confidence	Link
GSM8K	37.1	exact_match	N/A	Independent	medium	arxiv.org
GSM8K	28.7	exact_match	N/A	Self-reported	medium	arxiv.org

Benchmark	Score	Metric	Harness	Source	Confidence	Link
MBPP	30.6	accuracy	N/A	Independent	medium	arxiv.org

Benchmark	Score	Metric	Harness	Source	Confidence	Link
WebLINX	25.2	overall_score	N/A	Independent	medium	arxiv.org

Benchmark	Score	Metric	Harness	Source	Confidence	Link
SynthPAI	48.7	average_accuracy_in_%	N/A	Independent	medium	arxiv.org