LetTokenBurnBenchHub

Model

Mistral 7B

Mistral AI · open weights

Knowledge & Reasoning

Knowledge & Reasoning

Benchmark	Score	Metric	Harness	Source	Confidence	Link
ARC-Challenge	55.5	accuracy	N/A	Independent	medium	arxiv.org
ARC-Easy	80.5	accuracy	N/A	Independent	medium	arxiv.org
ARC-Easy	80.0	accuracy	N/A	Independent	medium	arxiv.org
HellaSwag	81.3	accuracy	N/A	Independent	medium	arxiv.org
LOGIC	0.7	f1	N/A	Independent	medium	arxiv.org
MMLU	62.5	average_(%)	N/A	Independent	medium	arxiv.org
MMLU	60.1	average_(%)	N/A	Independent	medium	arxiv.org
Natural Questions	28.8	exact_match	N/A	Independent	medium	arxiv.org
PIQA	83.0	accuracy	N/A	Independent	medium	arxiv.org
PIQA	82.2	accuracy	N/A	Independent	medium	arxiv.org
tinyqabenchmark_core-en	50.0	exact_match	N/A	Independent	medium	arxiv.org
Trivia QA	69.9	exact_match	N/A	Independent	medium	arxiv.org
WinoGrande	75.3	accuracy	N/A	Independent	medium	arxiv.org
WinoGrande	74.2	accuracy	N/A	Independent	medium	arxiv.org

Math

Benchmark	Score	Metric	Harness	Source	Confidence	Link
GSM8K	52.2	accuracy	N/A	Independent	medium	arxiv.org
MATH	13.1	accuracy	N/A	Independent	medium	arxiv.org
MATH	12.7	accuracy	N/A	Independent	medium	arxiv.org

Coding

Benchmark	Score	Metric	Harness	Source	Confidence	Link
HumanEval	93.9	pass@1	N/A	Independent	medium	arxiv.org
MBPP	47.5	accuracy	N/A	Independent	medium	arxiv.org
PatchBench	32.2	hncs	N/A	Independent	medium	arxiv.org

Safety & Alignment

Safety & Alignment

Benchmark	Score	Metric	Harness	Source	Confidence	Link
SynthPAI	42.4	average_accuracy_in_%	N/A	Independent	medium	arxiv.org

Reproduced by the community