LetTokenBurnBenchHub

Model

Llama-3.1-8B-Instruct

Meta · open weights

Knowledge & Reasoning

Knowledge & Reasoning

Benchmark	Score	Metric	Harness	Source	Confidence	Link
Balrog	15.1	average_progress	N/A	Independent	medium	balrogai.com
BLiMPPI	92.7	accuracy	N/A	Independent	medium	arxiv.org
BoolQ	82.8	score	N/A	Independent	medium	arxiv.org
CritPt	0.0	accuracy	N/A	Independent	low	epoch.ai
DCBench-440	14.0	accuracy	openrouter	Independent	medium	arxiv.org
GeopoliticalQA	2.3	overall	N/A	Independent	medium	arxiv.org
GPQA Diamond	27.0	accuracy	N/A	Independent	high	epoch.ai
LOGIC	0.8	f1	N/A	Independent	medium	arxiv.org
MMLU	73.0	average_(%)	N/A	Independent	medium	arxiv.org
MMLU	56.1	exact_match	N/A	Independent	medium	crfm.stanford.edu
MS-Exam-Gen	73.1	accuracy	N/A	Independent	medium	arxiv.org
PIQA	81.2	score	N/A	Independent	medium	arxiv.org
ViLegalExpert	72.1	score	N/A	Independent	medium	arxiv.org

Math

Benchmark	Score	Metric	Harness	Source	Confidence	Link
GSM8K	82.4	exact_match	N/A	Independent	medium	arxiv.org
NLData2Opt	0.3	accuracy	N/A	Independent	medium	arxiv.org

Coding

Benchmark	Score	Metric	Harness	Source	Confidence	Link
AlgoREval	31.4	accuracy	N/A	Independent	medium	arxiv.org
PatchBench	31.2	hncs	N/A	Independent	medium	arxiv.org
SciCode	13.2	score	N/A	Independent	medium	artificialanalysis.ai

Agentic / Tool Use

Agentic / Tool Use

Benchmark	Score	Metric	Harness	Source	Confidence	Link
MASBench	26.1	score	N/A	Independent	medium	arxiv.org
NAQD-Env	0.6	withdrawal_recall	naqd-env	Independent	medium	arxiv.org
SmartSalesBench	24.2	cr	N/A	Independent	medium	arxiv.org
TALK-Dem	66.7	success_rate	N/A	Independent	medium	arxiv.org

Multimodal

Benchmark	Score	Metric	Harness	Source	Confidence	Link
FLARE	0.1	mean_regret	N/A	Independent	medium	arxiv.org
VisualNoiseQA	36.4	accuracy	react	Independent	medium	arxiv.org

Instruction Following

Instruction Following

Benchmark	Score	Metric	Harness	Source	Confidence	Link
CreativePreferences	0.7	auc	N/A	Independent	medium	arxiv.org
Intent-Eval	91.7	accuracy	N/A	Independent	medium	arxiv.org

Safety & Alignment

Safety & Alignment

Benchmark	Score	Metric	Harness	Source	Confidence	Link
DIB-Bench	99.9	clean_acceptance	N/A	Independent	medium	arxiv.org
INFUSE	22.0	asr-l	N/A	Independent	medium	arxiv.org
ObligationBench	0.6	recall	N/A	Independent	medium	arxiv.org
OMIT	0.5	obr	N/A	Independent	medium	arxiv.org
PFaithBench	48.7	overans	N/A	Independent	medium	arxiv.org
Scaling Multilingual Safety and Reasoning Evaluation	44.0	math-500_accuracy	N/A	Independent	medium	arxiv.org
Trapped in Your Story	83.0	reversal_any_(%)	N/A	Independent	medium	arxiv.org

Reproduced by the community