Skip to main content
leaderboard
.cn
Toggle Sidebar
Search models or organizations…
⌘K
Explore
Frontier Models
Historical Trends
Local Models
Compare Models
Ranking Studio
Library
Models
Pricing
Organizations
Benchmarks
Data sources
Settings
Toggle Sidebar
leaderboard
.cn
Loading page content
Feedback
Loading page content
Back to models
gpt-oss-20b
Open
Share
Add to comparison
Tool use · Reasoning
Overview
Deployment
Evaluations
Evaluation overview
Overall rank
#115
62.8 points · 180 models
Open-weight rank
#51
68.4 points · 109 models
Data coverage
8 items
2 sources · updated through 2026-07-16
Domain performance
Research
#112 / 174
72.8
Evaluation highlights
All evaluations
MMLU-Redux
Reasoning · Qwen3.5-9B Technical Report
87.8%
47
/ 102
IFEval strict prompt
Instruction following · Qwen3.5-9B Technical Report
88.2%
19
/ 55
C-Eval
Chinese · Qwen3.5-9B Technical Report
71.4%
48
/ 64
SuperGPQA
Reasoning · Qwen3.5-9B Technical Report
48.5%
34
/ 65
MMLU-Pro
Reasoning · Qwen3.5-9B Technical Report
74.8%
51
/ 95
Arena Text Rating
Reasoning · Arena.ai Text
1,317.43Elo
207
/ 354
Basic information
Context (input / output)
131K / 131K
Parameters
21B / 3.6B active
Release date
2025-08
License
Apache 2.0
Input modalities
Text
Output modalities
Text
Availability
vLLM · MXFP4
Deployment options
MXFP4 · 16 GB VRAM
Related links
Official site
HuggingFace