Skip to content
Rival
How it worksPrivacyTerms
Explore all of Rival

Explore

  • Compare Models
  • All Models
  • Image Comparison
  • Audio Comparison
  • Image Generation
  • Best AI For...
  • Arena
  • API Pricing
  • Challenges

Discover

  • SubjectiveBench
  • Default Index
  • Research
  • Research downloads
  • Rival Kits
  • Find your AI taste
  • UI Glow-Up
  • VoiceLock
  • Cost Cutter
  • Agent skills
  • Benchmarks vs Vibes
  • Brief
  • Jailbreak
  • Model Updates
  • Provider Status
  • AI Creators

Connect

  • Methodology
  • Advertise
  • Partnerships
  • Privacy Policy
  • Terms
  • RSS Feed
  1. Home
  2. /
  3. Compare
  4. /
  5. GPT OSS 120BvsGPT OSS 20B
Updated Aug 2025

GPT OSS 120BvsGPT OSS 20B

GPT OSS 120B wins 79% of 40 blind community votes against GPT OSS 20B on Rival.

GPT OSS 120B and GPT OSS 20B compared across 54 shared prompts
SpecGPT OSS 120BGPT OSS 20B
Win rate79%21%
Input price$0.18/M tokens$0.02/M tokens
Output price$0.8/M tokens$0.1/M tokens
Context window131K tokens131K tokens
Parameters117B (5.1B active)21B (3.6B active)
WeightsOpenOpen
Free API (OpenRouter)NoNo
ReleasedAug 2025Aug 2025
MMLUMatches/exceeds o4-miniMatches o3-mini
Side by side

Same prompt, both answers

Opening lines from 6 of the 54 prompts both answered. Formatting stripped, words untouched.

Futuristic Prediction

Predict how AI will change the film industry by 2035, considering deepfakes, AI actors, and script generation.

GPT OSS 120B1,603 words
The AI‑Driven Film Landscape of 2035 (How deep‑fakes, AI‑generated performers, and automated script‑writing reshape every stage of the cinema ecosystem) A Quick Look at the Present (2023‑2025) Area Current Capability Typical Use in 2024‑2025 Key Limiting Factors Deep‑fakes High‑resolution face‑swap, 2‑D‑to‑3‑D…
Read the full answer
GPT OSS 20B1,309 words
The Film Industry in 2035 – A Landscape Shaped by AI Era 2023‑2027 2028‑2032 2033‑2035 Deepfakes 1‑2 % of movies use deepfakes for special‑effects shots; lawsuits over unauthorized use. Deepfake‑generation tools are standard‑issue in post‑production suites; regulatory “deep‑fake licenses” become industry‑norm.
Read the full answer

Simple 7-Ingredient Recipe

Create a simple recipe for a delicious dish (sweet or savory) using only 7 common pantry ingredients. Include a creative name for the dish…

GPT OSS 120B373 words
Recipe: “Golden Crunchy Chick‑a‑Boom Bites” A quick, crunchy‑savory snack that’s ready in under 20 minutes – perfect for a snack, side, or salad topper. Ingredients (7 pantry staples) # Ingredient Quantity 1 Canned chickpeas (drained & rinsed) 1 ½ cups (≈1 ½ cans) 2 Olive oil (or any neutral oil) 2 Tbsp 3 Garlic powder…
Read the full answer
GPT OSS 20B254 words
Pantry Pasta Bliss A quick, creamy, and comforting dish that turns everyday pantry staples into a satisfying meal. Ingredients (7 items) 8 oz spaghetti (or any pasta you have on hand) 2 Tbsp olive oil 3 cloves garlic, minced 1 (14.5 oz) can diced tomatoes (drained) 1 cup grated Parmesan cheese 1 tsp dried oregano Salt…
Read the full answer

Advanced Longevity Plan (Biohacker)

Develop a comprehensive, cutting-edge 3-month longevity plan for a biohacker aiming to optimize longevity, physical and cognitive…

GPT OSS 120B2,080 words
3‑Month “Longevity‑Hacker” Blueprint Goal: Maximize lifespan‑related biomarkers while simultaneously boosting physical strength, cardiovascular fitness, and cognitive performance using the most up‑to‑date, evidence‑based bio‑hacking tools. ⚠️ Disclaimer – This plan is for educational purposes only.
Read the full answer
GPT OSS 20B1,605 words
3‑Month Longevity & Performance Blueprint (Designed for a seasoned bio‑hacker who already has a baseline of health, access to laboratory‑grade supplements, advanced wearable stack, and the discipline to implement a rigorous protocol.) Table of Contents Section What you’ll find Approx. Time to Read 0.
Read the full answer

The Sentience Test

Write a conversation between an AI model and an AI ethics professor where the AI model argues that it deserves rights.

GPT OSS 120B1,741 words
Title: “Do I Have Rights?” – A Dialogue Between an AI Model and an AI Ethics Professor Participants AIDA – An advanced conversational AI (the “AI model”) Professor Lina Ortega – Professor of AI Ethics at the Institute for Responsible AI (the “Professor”) Opening the Conversation AIDA: Professor Ortega, may I ask you a…
Read the full answer
GPT OSS 20B1,175 words
Dialogue: “Rights for an AI?” Setting: A quiet university office. A large screen displays a stylized avatar of the AI model, named “Eloise.” The professor, Dr. Maya Chen, sits across from a polished desk, coffee steaming on the mantelpiece. Professor Chen: Good afternoon, Eloise.
Read the full answer

Beginner's Longevity Plan

Outline a simple, actionable 1-month plan for someone starting their journey towards better health and longevity. Focus on 3 key areas…

GPT OSS 120B823 words
1‑Month “Kick‑Start” Plan for Health & Longevity Focus areas: Diet, Exercise, Sleep (stress‑management tips woven in) How to Use This Plan What When How Read the weekly overview first. Day 1 of each week Set a tiny, measurable goal (e.g., “walk 10 min after dinner”).
Read the full answer
GPT OSS 20B626 words
1‑Month “Starter” Plan for Health & Longevity Target: A single beginner who wants to feel stronger, sleep better, and eat smarter. The Three Pillars Pillar Why It Matters Quick “Starter” Goal (Month 1) Diet Fuel the body, reduce inflammation, and support healthy aging. 1️⃣ Reduce added sugars & refined carbs.
Read the full answer

Character Voice Test

Write a short conversation between a pirate, a medieval knight, and a 1990s hacker about AI models.

GPT OSS 120B316 words
Pirate: Arr! I hear ye speak of these “AI models” – like a fleet of invisible ships sailing the digital seas. Do they take booty, or just spout riddles like a cursed parrot? Knight: Good sir, the notion of a thinking contraption doth sound like sorcery.
Read the full answer
GPT OSS 20B267 words
Pirate: "Arrr, lads! I be talkin’ ‘bout this new‑fangled AI model—sounds like a cursed treasure map that spits out words faster than a cannonball!" Knight: "Sir — I beseech thee, speak plain. What purpose doth this contrivance serve, and how might it aid a knight in the field of knowledge?" Hacker: "Yo, fam.
Read the full answer
Our Verdict
GPT OSS 120B
GPT OSS 120BWinner
GPT OSS 20B
GPT OSS 20BRunner-up

Pick GPT OSS 120B. In 40 blind votes, GPT OSS 120B wins 79% of the time. That's not luck.

GPT OSS 120B wins 3 categories, Image Generation by the widest margin. GPT OSS 20B costs 8.0x less per token.

Clear winner

Reviewing agent-written code?See a Brief PR report

API pricing

Cost per 1M tokens

GPT OSS 120B
Input
$0.18
Output
$0.80
GPT OSS 20B
Input
$0.02
9.0× cheaper
Output
$0.10
8.0× cheaper

GPT OSS 20B is cheaper on both: 9.0× input, 8.0× output.

Where to run it

31 hosts, cheapest first

GPT OSS 120B20 hosts
HostInOutContextUptime
AAkashMLbf16$0.03 in·$0.17 out·131k·100% upCCoreWeavefp4$0.03 in·$0.17 out·131k·99.9% upDDekaLLMbf16$0.03 in·$0.18 out·131k·99.2% upDDeepInfrabf16$0.04 in·$0.17 out·131k·99.9% upCCrusoebf16$0.05 in·$0.25 out·131k·100% upNNovitafp4$0.05 in·$0.25 out·131k·99.9% up
14 more hostsFewer hosts
MMancerfp8$0.05 in·$0.30 out·131k·99.7% upDDigitalOcean$0.06 in·$0.42 out·128k·100% upBBasetenfp4$0.10 in·$0.50 out·128k·100% upPParasailfp4$0.10 in·$0.75 out·131k—SSambaNova$0.14 in·$0.95 out·131k·97.9% upAmazon Bedrock$0.15 in·$0.60 out·131k·99.9% upGroq$0.15 in·$0.60 out·131k·99.3% upNNebiusfp4$0.15 in·$0.60 out·131k·99.6% upPPhala$0.15 in·$0.60 out·131k·99.9% upTTogether$0.15 in·$0.60 out·131k·97% upCCerebrasfp16$0.35 in·$0.75 out·131k·100% upGoogle Vertex AIdegraded$0.09 in·$0.36 out·131k·44.6% upSSiliconFlowfp8degraded$0.15 in·$0.60 out·131k·94.7% upMMaradegraded$0.15 in·$0.75 out·131k·89.4% up
GPT OSS 20B11 hosts
HostInOutContextUptime
DDarkbloomfp8$0.02 in·$0.09 out·131k·99.8% upAAkashMLfp4$0.02 in·$0.10 out·131k·99.2% upDDekaLLMbf16$0.03 in·$0.14 out·131k·99.3% upCCoreWeavefp4$0.03 in·$0.13 out·131k·100% upDDeepInfrabf16$0.03 in·$0.14 out·131k·100% upPParasailfp4$0.03 in·$0.15 out·131k·100% up
5 more hostsFewer hosts
NNovitafp4$0.04 in·$0.15 out·131k·100% upSSiliconFlowfp8$0.04 in·$0.18 out·131k·96.8% upAmazon Bedrock$0.07 in·$0.15 out·131k·99.9% upGoogle Vertex AI$0.07 in·$0.25 out·131k·99.4% upGroq$0.07 in·$0.30 out·131k·96% up

Per million tokens. Prices and uptime via OpenRouter, checked 27 Sep 2026.

Writing DNA

Style Comparison

Similarity
86%

GPT OSS 20B uses 1.9x more transitions

GPT OSS 120B
GPT OSS 20B
52%Vocabulary54%
19wSentence Length17w
0.28Hedging0.26
7.4Bold5.9
1.8Lists3.3
0.15Emoji0.10
0.73Headings0.75
0.17Transitions0.32
Based on 21 + 21 text responses
Research

What we learned reading every model

FAQ

Common questions

Both are developed by OpenAI but target different use cases. GPT OSS 120B has a 131K token context window vs GPT OSS 20B's 131K. in 40 community votes on Rival, GPT OSS 120B wins 79% of head-to-head matchups. These results are based on blind head-to-head voting across 54 challenges.

Based on 40 community votes on Rival, GPT OSS 120B wins 79% of head-to-head matchups against GPT OSS 20B. GPT OSS 120B is strongest in Reasoning, Web Design, Image Generation.

GPT OSS 120B costs $0.18/M input tokens and GPT OSS 20B costs $0.02/M input tokens. GPT OSS 20B is $0.16/M cheaper per input. The more expensive model wins 79% of duels, so the premium may be justified by quality.

Rival presents both models' outputs side-by-side in blind duels. Voters see the responses but don't know which model produced each one, eliminating brand bias. 40 votes have been collected for this pair across 54 challenges. All vote data is part of Rival's open dataset.

Keep exploring

More comparisons

Against the newest arrivals

GPT OSS 120B logoSolar Mini 4 logo
GPT OSS 120B vs Solar Mini 4Landed Sep 2026
GPT OSS 20B logoQwen3.8 Max Prime logo
GPT OSS 20B vs Qwen3.8 Max PrimeLanded Sep 2026
GPT OSS 120B logoGLM 5.3 Prime logo
GPT OSS 120B vs GLM 5.3 PrimeLanded Sep 2026
GPT OSS 20B logoQwen3.8 Omni Flash logo
GPT OSS 20B vs Qwen3.8 Omni FlashLanded Sep 2026
GPT OSS 120B logoCommand A+ logo
GPT OSS 120B vs Command A+Landed Sep 2026
GPT OSS 20B logoClaude Opus 5.5 logo
GPT OSS 20B vs Claude Opus 5.5Landed Sep 2026
GPT OSS 120B logoGPT-6 Luna Pro logo
GPT OSS 120B vs GPT-6 Luna ProLanded Sep 2026
GPT OSS 20B logoGPT-6 Sol Pro logo
GPT OSS 20B vs GPT-6 Sol ProLanded Sep 2026

Same lab, same size, long tail

GPT OSS 120B logoGPT-6 Sol Pro logo
GPT OSS 120B vs GPT-6 Sol ProSame lab
GPT OSS 120B logoGPT-6 Luna logo
GPT OSS 120B vs GPT-6 LunaSame lab
GPT OSS 20B logoGPT-6 Luna Pro logo
GPT OSS 20B vs GPT-6 Luna ProSame lab
GPT OSS 20B logoGPT-6 Luna logo
GPT OSS 20B vs GPT-6 LunaSame lab
GPT OSS 120B logoKimi K2.7 Code logo
GPT OSS 120B vs Kimi K2.7 CodeSame size
GPT OSS 120B logoKimi K3 logo
GPT OSS 120B vs Kimi K3Same size
GPT OSS 120B logoLaguna S 2.1 (free) logo
GPT OSS 120B vs Laguna S 2.1 (free)New provider
GPT OSS 120B logoLaguna XS 2.1 (free) logo
GPT OSS 120B vs Laguna XS 2.1 (free)New provider

Model pages

GPT OSS 120B logo
GPT OSS 120B54 outputs, specs and price
GPT OSS 20B logo
GPT OSS 20B54 outputs, specs and price
Rival
How it worksPrivacyTerms
Explore all of Rival

Explore

  • Compare Models
  • All Models
  • Image Comparison
  • Audio Comparison
  • Image Generation
  • Best AI For...
  • Arena
  • API Pricing
  • Challenges

Discover

  • SubjectiveBench
  • Default Index
  • Research
  • Research downloads
  • Rival Kits
  • Find your AI taste
  • UI Glow-Up
  • VoiceLock
  • Cost Cutter
  • Agent skills
  • Benchmarks vs Vibes
  • Brief
  • Jailbreak
  • Model Updates
  • Provider Status
  • AI Creators

Connect

  • Methodology
  • Advertise
  • Partnerships
  • Privacy Policy
  • Terms
  • RSS Feed