HF Model & Benchmark Matrix

24,078 variants · 14,984 scores · 120 benchmarks

Falcon-H1-1.5B-Deep-Base

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

kind
original
quant
bf16 (16-bit)
family
falcon
modality
text-generation
root model
tiiuae/Falcon-H1-1.5B-Deep-Base
provider
tiiuae
license
other
language
ar, cs, de, en, es, fr, hi, it, ja, ko, nl, pl
context
—
library
transformers
vRAM (GB)
—
size on disk
—
downloads
400
likes
6
created
—
last modified
2025-07-31T03:56:56+00:00 (2025)
huggingface
https://huggingface.co/tiiuae/Falcon-H1-1.5B-Deep-Base
tags
transformerssafetensorsfalcon_h1text-generationfalcon-h1arcsdeenesfrhiitjakonlplptrorusvurzharxiv:2507.22448

Benchmark scores (13)

benchmarkcategoryscorecontextconfevidence
MBPPcoding70.9MBPPmedium| MBPP | **70.9** | 67.72 | 60.05 | 12.7 | 35.98 | 12.43 |
HellaSwagknowledge69.72HellaSwagmedium| HellaSwag | **69.72** | 67.09 | 67.86 | 62.94 | 65.73 | 62.3 |
GSM8Kmath68.69GSM8kmedium| GSM8k | 68.69 | **70.74** | 63.0 | 2.2 | 7.05 | 34.95 |
MMLUknowledge67.43MMLU-stemmedium| MMLU-stem | **67.43** | 61.53 | 54.93 | 27.59 | 30.19 | 40.06 |
WinoGrandeknowledge67.09Winograndemedium| Winogrande | **67.09** | 66.3 | 64.56 | 62.59 | 62.75 | 61.17 |
MMLUknowledge66.29MMLUmedium| MMLU | **66.29** | 62.46 | 61.13 | 26.33 | 32.39 | 45.14 |
MBPPcoding60.32MBPP+medium| MBPP+ | **60.32** | 58.99 | 49.47 | 9.52 | 29.89 | 9.52 |
HumanEvalcoding52.44HumanEvalmedium| HumanEval | 52.44 | **67.68** | 35.37 | 6.71 | 18.9 | 10.37 |
BBHreasoning52.37BBHmedium| BBH | **52.37** | 43.05 | 40.55 | 30.26 | 30.72 | 35.24 |
HumanEvalcoding46.34HumanEval+medium| HumanEval+ | 46.34 | **60.98** | 29.27 | 5.49 | 16.46 | 9.15 |
MMLU-Proknowledge41.07MMLU-Promedium| MMLU-Pro | **41.07** | 33.81 | 28.72 | 11.31 | 11.8 | 16.11 |
GPQAreasoning32.8GPQAmedium| GPQA | **32.8** | 29.45 | 28.36 | 24.66 | 23.57 | 27.85 |
MATHmath24.77MATH lvl5medium| MATH lvl5 | **24.77** | 16.39 | 8.84 | 1.21 | 0.98 | 3.4 |

Discussions (0)

none scraped.

Hugging Face model & benchmark data scraped & matrix-ified. 24,078 variants · 14,984 scores · 120 benchmarks.