HF Model & Benchmark Matrix

24,078 variants · 14,984 scores · 120 benchmarks
Home/Orgs/tiiuae/tiiuae/Falcon-H1-1.5B-Deep-Base

tiiuae/Falcon-H1-1.5B-Deep-Base

family falcon · 2 variants · unknown

provider
tiiuae
released
—
huggingface
https://huggingface.co/tiiuae/Falcon-H1-1.5B-Deep-Base
best scores
BBH: 54.43TruthfulQA: 50.48HellaSwag: 69.72MMLU: 67.43GSM8K: 82.34MATH-500: 77.8GPQA: 33.22GPQA Diamond: 40.57MMLU-Pro: 41.89HumanEval: 73.78MBPP: 70.9LiveCodeBench: 23.87IFEval: 83.5AlpacaEval: 27.12MT-Bench: 8.53WinoGrande: 67.09MATH: 24.77

Best scores per benchmark

benchmarkcategorybest score
IFEvalinstruction-following83.5
GSM8Kmath82.34
MATH-500math77.8
HumanEvalcoding73.78
MBPPcoding70.9
HellaSwagknowledge69.72
MMLUknowledge67.43
WinoGrandeknowledge67.09
BBHreasoning54.43
TruthfulQAsafety50.48
MMLU-Proknowledge41.89
GPQA Diamondreasoning40.57
GPQAreasoning33.22
AlpacaEvalchat27.12
MATHmath24.77
LiveCodeBenchcoding23.87
MT-Benchchat8.53

Variants (2)

variantkindquantbitsvRAMdlorgyear
Falcon-H1-1.5B-Deep-Instructoriginalbf1616.04,469tiiuae2025
Falcon-H1-1.5B-Deep-Baseoriginalbf1616.0400tiiuae2025
Hugging Face model & benchmark data scraped & matrix-ified. 24,078 variants · 14,984 scores · 120 benchmarks.