HF Model & Benchmark Matrix

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

Falcon-H1-1.5B-Base

tiiuae/Falcon-H1-1.5B-Base

kind
original
quant
bf16 (16-bit)
family
falcon
modality
text-generation
root model
tiiuae/Falcon-H1-1.5B-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
3,571
likes
2
created
—
last modified
2025-07-31T03:54:55+00:00 (2025)
huggingface
https://huggingface.co/tiiuae/Falcon-H1-1.5B-Base
tags
transformerssafetensorsfalcon_h1text-generationfalcon-h1arcsdeenesfrhiitjakonlplptrorusvurzharxiv:2507.22448

Benchmark scores (13)

benchmarkcategoryscorecontextconfevidence
HellaSwagknowledge66.76HellaSwagmedium| HellaSwag | 66.76 | 67.09 | **67.86** | 62.94 | 65.73 | 62.3 |
WinoGrandeknowledge65.59Winograndemedium| Winogrande | 65.59 | **66.3** | 64.56 | 62.59 | 62.75 | 61.17 |
MBPPcoding65.08MBPPmedium| MBPP | 65.08 | **67.72** | 60.05 | 12.7 | 35.98 | 12.43 |
MMLUknowledge63.37MMLU-stemmedium| MMLU-stem | **63.37** | 61.53 | 54.93 | 27.59 | 30.19 | 40.06 |
MMLUknowledge61.81MMLUmedium| MMLU | 61.81 | **62.46** | 61.13 | 26.33 | 32.39 | 45.14 |
MBPPcoding55.03MBPP+medium| MBPP+ | 55.03 | **58.99** | 49.47 | 9.52 | 29.89 | 9.52 |
GSM8Kmath52.01GSM8kmedium| GSM8k | 52.01 | **70.74** | 63.0 | 2.2 | 7.05 | 34.95 |
HumanEvalcoding50.0HumanEvalmedium| HumanEval | 50.0 | **67.68** | 35.37 | 6.71 | 18.9 | 10.37 |
BBHreasoning46.57BBHmedium| BBH | **46.57** | 43.05 | 40.55 | 30.26 | 30.72 | 35.24 |
HumanEvalcoding42.68HumanEval+medium| HumanEval+ | 42.68 | **60.98** | 29.27 | 5.49 | 16.46 | 9.15 |
MMLU-Proknowledge35.53MMLU-Promedium| MMLU-Pro | **35.53** | 33.81 | 28.72 | 11.31 | 11.8 | 16.11 |
GPQAreasoning29.11GPQAmedium| GPQA | 29.11 | **29.45** | 28.36 | 24.66 | 23.57 | 27.85 |
MATHmath20.39MATH lvl5medium| MATH lvl5 | **20.39** | 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.