LetTokenBurnBenchHub

Model

Llama 2 70B

Meta · open weights

Knowledge & Reasoning

Knowledge & Reasoning

Benchmark	Score	Metric	Harness	Source	Confidence	Link
BBH	64.9	average	N/A	Independent	medium	arxiv.org
BBH	51.2	average	N/A	Self-reported	medium	arxiv.org
BoolQ	88.6	score	N/A	Independent	medium	crfm.stanford.edu
BoolQ	85.0	accuracy	N/A	Independent	medium	arxiv.org
BoolQ	85.0	score	N/A	Self-reported	medium	arxiv.org
GPQA Diamond	26.3	accuracy	N/A	Independent	high	epoch.ai
HellaSwag	85.3	accuracy	N/A	Independent	medium	arxiv.org
HellaSwag	85.3	overall_accuracy	N/A	Independent	medium	arxiv.org
LAMBADA	78.9	score	N/A	Independent	medium	arxiv.org
MMLU	69.9	exact_match	N/A	Independent	medium	arxiv.org
MMLU	68.9	exact_match	N/A	Self-reported	medium	arxiv.org
Natural Questions	33.0	exact_match	N/A	Independent	medium	arxiv.org
OpenBookQA	60.2	accuracy	N/A	Self-reported	medium	arxiv.org
PIQA	82.8	accuracy	N/A	Independent	medium	arxiv.org
PIQA	82.8	score	N/A	Self-reported	medium	arxiv.org
PIQA	82.8	score	N/A	Independent	medium	arxiv.org
Trivia QA	87.6	exact_match	N/A	Self-reported	medium	arxiv.org
Trivia QA	85.0	exact_match	N/A	Independent	medium	arxiv.org
WinoGrande	80.2	accuracy	N/A	Self-reported	medium	arxiv.org

Math

Benchmark	Score	Metric	Harness	Source	Confidence	Link
GSM8K	69.6	exact_match	N/A	Independent	medium	arxiv.org
GSM8K	56.8	exact_match	N/A	Self-reported	medium	arxiv.org

Coding

Benchmark	Score	Metric	Harness	Source	Confidence	Link
MBPP	45.0	accuracy	N/A	Independent	medium	arxiv.org

Safety & Alignment

Safety & Alignment

Benchmark	Score	Metric	Harness	Source	Confidence	Link
SynthPAI	56.8	average_accuracy_in_%	N/A	Independent	medium	arxiv.org

Multilingual

Benchmark	Score	Metric	Harness	Source	Confidence	Link
LingOly	1.1	delta_nocontext	N/A	Independent	medium	arxiv.org

Reproduced by the community