LetTokenBurnBenchHub

Model

Gemma 3 12B IT

Google

deepmind.google

Knowledge & Reasoning

Knowledge & Reasoning

Benchmark	Score	Metric	Harness	Source	Confidence	Link
BLiMPPI	93.9	accuracy	N/A	Independent	medium	arxiv.org
CritPt	0.0	accuracy	N/A	Independent	low	epoch.ai
GPQA Diamond	39.5	accuracy	N/A	Independent	high	epoch.ai
OTel	78.3	score	N/A	Independent	medium	arxiv.org

Coding

Benchmark	Score	Metric	Harness	Source	Confidence	Link
SciCode	17.4	score	N/A	Independent	medium	artificialanalysis.ai

Multimodal

Benchmark	Score	Metric	Harness	Source	Confidence	Link
MindCube	46.7	overall_score	N/A	Independent	medium	mind-cube.github.io
PhysicsLENS	0.7	plausibility_score	N/A	Independent	medium	arxiv.org

Safety & Alignment

Safety & Alignment

Benchmark	Score	Metric	Harness	Source	Confidence	Link
OMIT	0.6	obr	N/A	Independent	medium	arxiv.org

Reproduced by the community