LetTokenBurnBenchHub

Model

GPT-4

OpenAI · closed weights

Knowledge & Reasoning

Knowledge & Reasoning

Benchmark	Score	Metric	Harness	Source	Confidence	Link
ARC-Challenge	96.4	accuracy	N/A	Independent	medium	arxiv.org
BLURB	80.6	accuracy	N/A	Independent	medium	medrxiv.org
CloudEval-YAML	0.6	accuracy	N/A	Independent	medium	arxiv.org
EconLogicQA	56.9	accuracy	N/A	Independent	medium	arxiv.org
GPQA Diamond	46.6	accuracy	N/A	Independent	high	epoch.ai
HellaSwag	95.3	accuracy	N/A	Independent	medium	arxiv.org
LegalBench	82.9	balanced_accuracy	N/A	Independent	medium	paperswithcode.com
medqa	90.2	accuracy	N/A	Independent	medium	arxiv.org
MedSecId	96.9	1_shot_micro-f1	N/A	Independent	medium	arxiv.org
MMLU	83.9	exact_match	N/A	Independent	medium	arxiv.org
OCW	75.8	wasserstein_distance_(wd)	N/A	Independent	medium	arxiv.org
OCW	73.7	wasserstein_distance_(wd)	N/A	Independent	medium	arxiv.org
OCW	73.6	wasserstein_distance_(wd)	N/A	Independent	medium	arxiv.org
OCW	73.4	wasserstein_distance_(wd)	N/A	Independent	medium	arxiv.org
OCW	72.9	wasserstein_distance_(wd)	N/A	Independent	medium	arxiv.org
TimeQuestions	30.6	p@1	N/A	Independent	medium	arxiv.org
TIQ	28.6	p@1	N/A	Independent	medium	arxiv.org
WinoGrande	87.5	accuracy	N/A	Independent	medium	arxiv.org

Math

Benchmark	Score	Metric	Harness	Source	Confidence	Link
ConvFinQA	76.5	execution_accuracy	N/A	Independent	medium	arxiv.org
Fin QA	68.8	execution_accuracy	N/A	Independent	medium	arxiv.org
gsm_plus	85.6	1:1_accuracy	N/A	Independent	medium	arxiv.org
GSM8K	92.0	exact_match	N/A	Independent	medium	arxiv.org
GSM8K	87.1	accuracy	N/A	Independent	medium	arxiv.org
MATH	42.5	accuracy	N/A	Independent	medium	arxiv.org
TheoremQA	43.8	accuracy	N/A	Independent	medium	arxiv.org

Coding

Benchmark	Score	Metric	Harness	Source	Confidence	Link
MBPP	80.0	accuracy	N/A	Independent	medium	arxiv.org
MMSQL	67.0	tdex	N/A	Independent	medium	arxiv.org
TACO-BAAI	31.5	easy_pass@1	N/A	Independent	medium	arxiv.org
Turbulence	84.8	corrsc	N/A	Independent	medium	arxiv.org

Multimodal

Benchmark	Score	Metric	Harness	Source	Confidence	Link
AlgoPuzzleVQA	30.3	accuracy	N/A	Independent	medium	arxiv.org

Instruction Following

Instruction Following

Benchmark	Score	Metric	Harness	Source	Confidence	Link
IFEval	85.4	inst-level_loose-accuracy	N/A	Independent	medium	arxiv.org

Safety & Alignment

Safety & Alignment

Benchmark	Score	Metric	Harness	Source	Confidence	Link
HarmfulQA	65.1	asr	N/A	Independent	medium	arxiv.org
rt-inod-jailbreaking	91.0	best-of	N/A	Independent	medium	arxiv.org
SynthPAI	77.9	average_accuracy_in_%	N/A	Independent	medium	arxiv.org

Multilingual

Benchmark	Score	Metric	Harness	Source	Confidence	Link
CATT benchmark	9.5	der(%)	N/A	Independent	medium	arxiv.org
LingOly	21.5	delta_nocontext	N/A	Independent	medium	arxiv.org

Reproduced by the community