HF Model & Benchmark Matrix
Overview
Benchmarks
Speech
Models
Orgs
24,078 variants · 14,984 scores · 120 benchmarks
Home
/
Benchmarks
/
DeepSWE
DeepSWE
swe · deepswestack/deepswe · 17 scores
https://huggingface.co/spaces/deepswestack/deepswe
rank
variant
root
org
score
conf
context
1
GLM-5.2-FP8
zai-org/GLM-5.2
zai-org
46.2
medium
DeepSWE
2
GLM-5.2
zai-org/GLM-5.2
zai-org
46.2
medium
DeepSWE
3
GLM-5.2-GGUF
zai-org/GLM-5.2
unsloth
46.2
medium
DeepSWE
4
GLM-5.2-FP8
zai-org/GLM-5.2
unsloth
46.2
medium
DeepSWE
5
GLM-5.2
zai-org/GLM-5.2
unsloth
46.2
medium
DeepSWE
6
Devstral-Small-2507
mistralai/Mistral-Small-3.1-24B-Instruct-2503
mistralai
42.2
medium
DeepSWE
7
Devstral-Small-2507-GGUF
mistralai/Devstral-Small-2507
unsloth
42.2
medium
DeepSWE
8
SERA-32B
allenai/SERA-32B
allenai
42.2
medium
DeepSWE
9
FrogBoss-32B-2510
Qwen/Qwen3-32B
microsoft
42.2
medium
DeepSWE‑32B‑Preview
10
Devstral-Small-2507
mistralai/Mistral-Small-3.1-24B-Instruct-2503
unsloth
42.2
medium
DeepSWE
11
Devstral-Small-2507-bnb-4bit
mistralai/Devstral-Small-2507
unsloth
42.2
medium
DeepSWE
12
SERA-8B
allenai/SERA-8B
allenai
42.2
medium
DeepSWE
13
FrogMini-14B-2510
Qwen/Qwen3-14B
microsoft
42.2
medium
DeepSWE‑32B‑Preview
14
Devstral-Small-2507-unsloth-bnb-4bit
mistralai/Devstral-Small-2507
unsloth
42.2
medium
DeepSWE
15
Laguna-S-2.1-GGUF
poolside/Laguna-S-2.1
unsloth
40.4
low
16
Laguna-S-2.1
poolside/Laguna-S-2.1
unsloth
40.4
low
17
Nex-N2-mini-GGUF
nex-agi/Nex-N2-mini
Mungert
8.0
medium
DeepSWE
Hugging Face model & benchmark data scraped & matrix-ified. 24,078 variants · 14,984 scores · 120 benchmarks.