HF Model & Benchmark Matrix
Overview
Benchmarks
Speech
Models
Orgs
24,078 variants · 14,984 scores · 120 benchmarks
Home
/
Models
/
Qwen/WebWorld-32B
WebWorld-32B
Qwen/WebWorld-32B
kind
original
quant
bf16 (16-bit)
family
qwen
modality
text-generation
root model
Qwen/Qwen3-8B
provider
Qwen
license
apache-2.0
language
en, zh
context
—
library
transformers
vRAM (GB)
—
size on disk
—
downloads
348
likes
75
created
—
last modified
2026-05-08T12:11:35+00:00
(2026)
huggingface
https://huggingface.co/Qwen/WebWorld-32B
tags
transformers
safetensors
qwen3
text-generation
WebWorld
web-agent
world-model
simulator
browser
a11y
html
xml
markdown
long-horizon
long-context
synthetic-trajectories
instruction-tuning
conversational
en
zh
dataset:Qwen/WebWorldData
arxiv:2602.14721
base_model:Qwen/Qwen3-8B
base_model:finetune:Qwen/Qwen3-8B
Benchmark scores (1)
benchmark
category
score
context
conf
evidence
WebArena
agentic
26.6
low
| GPT-4o | 64.3% | 26.6% |
Discussions (0)
none scraped.
Hugging Face model & benchmark data scraped & matrix-ified. 24,078 variants · 14,984 scores · 120 benchmarks.