HF Model & Benchmark Matrix

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

Falcon-H1-0.5B-Base

tiiuae/Falcon-H1-0.5B-Base

kind
original
quant
bf16 (16-bit)
family
falcon
modality
text-generation
root model
tiiuae/Falcon-H1-0.5B-Base
provider
tiiuae
license
other
language
en
context
—
library
transformers
vRAM (GB)
—
size on disk
—
downloads
139,056
likes
17
created
—
last modified
2025-07-31T03:51:29+00:00 (2025)
huggingface
https://huggingface.co/tiiuae/Falcon-H1-0.5B-Base
tags
transformerssafetensorsfalcon_h1text-generationfalcon-h1enarxiv:2507.22448license:otherendpoints_compatibleregion:us

Benchmark scores (13)

benchmarkcategoryscorecontextconfevidence
GSM8Kmath60.2GSM8kmedium| GSM8k | **60.2** | 50.04 | 34.8 | 2.2 | 7.05 | 34.95 |
WinoGrandeknowledge59.43Winograndemedium| Winogrande | 59.43 | 60.54 | 56.83 | 62.59 | **62.75** | 61.17 |
MMLUknowledge57.12MMLU-stemmedium| MMLU-stem | **57.12** | 50.11 | 43.74 | 27.59 | 30.19 | 40.06 |
HellaSwagknowledge56.3HellaSwagmedium| HellaSwag | 56.3 | 53.51 | 51.79 | 62.94 | **65.73** | 62.3 |
MMLUknowledge55.04MMLUmedium| MMLU | **55.04** | 52.64 | 47.61 | 26.33 | 32.39 | 45.14 |
MBPPcoding52.12MBPPmedium| MBPP | **52.12** | 51.06 | 40.74 | 12.7 | 35.98 | 12.43 |
MBPPcoding43.39MBPP+medium| MBPP+ | **43.39** | 42.33 | 34.66 | 9.52 | 29.89 | 9.52 |
BBHreasoning40.22BBHmedium| BBH | **40.22** | 36.07 | 32.62 | 30.26 | 30.72 | 35.24 |
HumanEvalcoding35.98HumanEvalmedium| HumanEval | **35.98** | 31.71 | 29.27 | 6.71 | 18.9 | 10.37 |
HumanEvalcoding31.1HumanEval+medium| HumanEval+ | **31.1** | 27.44 | 25.0 | 5.49 | 16.46 | 9.15 |
MMLU-Proknowledge30.04MMLU-Promedium| MMLU-Pro | **30.04** | 22.99 | 18.98 | 11.31 | 11.8 | 16.11 |
GPQAreasoning29.7GPQAmedium| GPQA | **29.7** | 29.11 | 27.94 | 24.66 | 23.57 | 27.85 |
MATHmath15.18MATH lvl5medium| MATH lvl5 | **15.18** | 9.29 | 4.23 | 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.