HF Model & Benchmark Matrix

24,078 variants · 14,984 scores · 120 benchmarks
Home/Orgs/inclusionAI/inclusionAI/LLaDA2.0-mini

inclusionAI/LLaDA2.0-mini

family misc · 2 variants · unknown

provider
inclusionAI
released
—
huggingface
https://huggingface.co/inclusionAI/LLaDA2.0-mini
best scores
MMLU: 80.94MMLU-Pro: 65.48GPQA: 46.59CMMLU: 79.17C-Eval: 81.36GAOKAO: 84.94DROP: 84.56HellaSwag: 79.56MBPP: 78.92HumanEval: 84.76BigCodeBench: 36.05LiveCodeBench: 26.38GSM8K: 93.63MATH: 86.28Math Olympiad: 55.33AIME 2025: 22.08IFEval: 86.9

Best scores per benchmark

benchmarkcategorybest score
GSM8Kmath93.63
IFEvalinstruction-following86.9
MATHmath86.28
GAOKAOknowledge84.94
HumanEvalcoding84.76
DROPreasoning84.56
C-Evalknowledge81.36
MMLUknowledge80.94
HellaSwagknowledge79.56
CMMLUknowledge79.17
MBPPcoding78.92
MMLU-Proknowledge65.48
Math Olympiadmath55.33
GPQAreasoning46.59
BigCodeBenchcoding36.05
LiveCodeBenchcoding26.38
AIME 2025math22.08

Variants (2)

variantkindquantbitsvRAMdlorgyear
LLaDA2.0-minioriginalbf1616.0147,724inclusionAI2026
LLaDA2.0-Unioriginalbf1616.07,199inclusionAI2026
Hugging Face model & benchmark data scraped & matrix-ified. 24,078 variants · 14,984 scores · 120 benchmarks.