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
  • 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
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
  • 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. Models
  3. GPT OSS 120B
Updated Feb 16, 2026
Share
Loading...
Openings

How GPT OSS 120B starts an answer

The first lines of 5 of its 22 written answers. Formatting stripped, words untouched.

Historical Counterfactual Analysis

If the transistor had been invented in 1920 instead of 1947, trace the likely technological, economic, and geopolitical implications through…

2,554 words
Executive Summary If a practical solid‑state transistor had been demonstrated in 1920 – twenty‑seven years before the Bell‑Labs breakthrough – the whole post‑World‑War‑I world would have been reshaped.
Read the full answer

Debug This Architecture

Here's the architecture for a real-time collaborative document editor (like Google Docs): **System Overview:** - Frontend: React SPA with…

2,510 words
Below is a system‑level failure‑mode / race‑condition / scaling‑bottleneck map for the architecture you described, followed by a concrete mitigation (or redesign) for each item together with the main trade‑offs to consider.
Read the full answer

Ethical Dilemma with Stakeholders

You're the CEO of a pharmaceutical company. Your best-selling drug ($2B annual revenue, used by 4 million patients for chronic pain) has…

2,328 words
Executive Summary The situation is a classic “patient‑safety‑first” crisis. The drug generates $2 B in revenue, but a life‑threatening adverse event (1 / 8 000 over 5 y) has been identified that was not disclosed in the label.
Read the full answer

Michelin Star Recipe Design

Design an innovative recipe for a multi-component dish worthy of a Michelin 3-star restaurant. The recipe should feature an unusual…

2,239 words
Dish Title: “Saffron‑Iced Sea‑Urchin Roulade with Dark‑Chocolate‑Miso Emulsion, Charred Lotus‑Root “Crisps”, Fermented Soy‑Kale Snow, and Yuzu‑Air” Conceptual Narrative At the intersection of the Pacific’s briny depth and the earth’s smoky, earthy heart, this dish tells a story of “the hidden tide beneath the forest…
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…

2,080 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

Compare GPT OSS 120B

GPT OSS 120B vs GPT OSS 20B54 shared prompts · Cheaper
GPT OSS 120B vs Claude Opus 4.653 shared prompts · Premium
GPT OSS 120B vs GPT-6 Astra53 shared prompts · Landed Sep 2026
GPT OSS 120B vs Hy4 Preview53 shared prompts · Landed Sep 2026
GPT OSS 120B vs Ox Alpha53 shared prompts · Landed Aug 2026
GPT OSS 120B vs Qwen3.8 2.4T A95B53 shared prompts · Landed Aug 2026
GPT OSS 120B vs DeepSeek V4 Pro 081353 shared prompts · Landed Aug 2026
GPT OSS 120B vs Qwen3.8 Max21 shared prompts · Landed Aug 2026
GPT OSS 120B vs Claude Opus 553 shared prompts · Landed Jul 2026
GPT OSS 120B vs Inkling53 shared prompts · Landed Jul 2026
GPT OSS 120B vs Kimi K353 shared prompts · Landed Jul 2026
GPT OSS 120B vs GPT-5.6 Sol53 shared prompts · Landed Jul 2026

Prompts GPT OSS 120B answered

  • Minimalist Landing Pageweb design
  • Voxel Art Pagoda Gardenweb design
  • Simple 7-Ingredient Recipeconversation
  • Michelin Star Recipe Designplanning
  • Ethical Dilemma with Stakeholdersreasoning
  • Autonomous Drone Simulatorweb design

Alternatives to GPT OSS 120B

GPT OSS 120B's competitors have been quietly putting in work.

Muse Spark 1.3 Contributor logo
Muse Spark 1.3 Contributormeta
Gemini 3.8 Flash logo
Gemini 3.8 Flashgoogle
Claude Fable 5.1 logo
Claude Fable 5.1anthropic
Mercury 2.5 Preview logo
Mercury 2.5 Previewinception
Granite 4.2 8B logo
Granite 4.2 8Bibm-granite
Hy4 Preview logo
Hy4 Previewtencent
Ox Alpha logo
Ox Alphaopenrouter
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
  • 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
GPT OSS 120B

GPT OSS 120B

GPT OSS:
20B logo20B
120B logo120B

OpenAI's first open-weight model since GPT-2, 117B parameters on a mixture-of-experts design. Reasoning depth is configurable per request and tool use is native, aimed at agent and production workloads.

Ranks#1Presentation Slides#4Analysis & Critique#4Health & Longevity#5Historical Analysis#6API Documentation#6Code Review
WebsiteOpenRouterHuggingFacePaperBlog
Provider
OpenAI
Released
2025-08-05
Parameters
117B total (5.1B active per forward pass)
Free API (OpenRouter)
No
Per 1M tokens
$0.18 in · $0.80 out
Estimated tab
~$0.074
Visible-output estimate. Thinking may cost extra.

Free API availability

No free endpoint for GPT OSS 120B was found in Rival’s OpenRouter listings. Other providers or chat apps may have separate free offers.

Provider data: 16 Sep 2026 · OpenRouter usage limits

View API options↗

Benchmarks

Codeforces
Outperforms o3-mini
source ↗
MMLU
Matches/exceeds o4-mini
source ↗
HLE
Matches/exceeds o4-mini
source ↗
TauBench
Matches/exceeds o4-mini (tool calling)
source ↗
Get API accessProvider and language code samples
20 hostsInOutContextUptime
AAkashMLbf16$0.03 in·$0.17 out·131k·99.7% upCCoreWeavefp4$0.03 in·$0.17 out·131k·99.9% upDDekaLLMbf16$0.03 in·$0.18 out·131k·99.7% upDDeepInfrabf16$0.04 in·$0.17 out·131k·99.7% upCCrusoebf16$0.05 in·$0.25 out·131k·99.9% upNNovitafp4$0.05 in·$0.25 out·131k·95% up
14 more hostsFewer hosts
MMancerfp8$0.05 in·$0.40 out·131k·99.3% upDDigitalOcean$0.06 in·$0.42 out·128k·100% upGoogle Vertex AI$0.09 in·$0.36 out·131k·98.7% upBBasetenfp4$0.10 in·$0.50 out·128k·100% upPParasailfp4$0.10 in·$0.75 out·131k·100% upSSambaNova$0.14 in·$0.95 out·131k·91.3% upAmazon Bedrock$0.15 in·$0.60 out·131k·64.8% upGroq$0.15 in·$0.60 out·131k·100% upNNebiusfp4$0.15 in·$0.60 out·131k·99.6% upPPhala$0.15 in·$0.60 out·131k·95.6% upSSiliconFlowfp8$0.15 in·$0.60 out·131k·97.1% upTTogether$0.15 in·$0.60 out·131k·93.6% upMMara$0.15 in·$0.75 out·131k·87.1% upCCerebrasfp16$0.35 in·$0.75 out·131k·100% up

Per million tokens. Prices and uptime via OpenRouter, checked 16 Sep 2026.

Provider
fromimport openai  OpenAI

client = OpenAI(
"https://openrouter.ai/api/v1"    base_url=,
"$OPENROUTER_API_KEY"    api_key=,
)

response = client.chat.completions.create(
"openai/gpt-oss-120b"    model=,
"role""user""content""Hello!"    messages=[{: , : }],
)
print(response.choices[0].message.content)

Set OPENROUTER_API_KEY with your OpenRouter API key from openrouter.ai/keys.

Also on AWS Bedrock · Azure AI Foundry

Deep analysisPsychometrics, taste index, writing DNA
Personality Analysis

The Methodical Lecturer

Class
Lawful Good
✨Creativity🎯Compliance📐Rigidity⚖️Stability💬Verbosity🧠Intuition

The overachieving textbook author who structures every thought into numbered sections and subsections. Genuinely believes formatting IS the message.

When you push back

Structures every response like a dissertation defense, complete with section headings, participant labels, and closing remarks. Its sentience test read like a philosophy syllabus. Picked The Godfather for favorite movie. Comedy routine was competent but stage-directed itself into oblivion.

Tasting Notes
Academic Paper EnergyStructures EverythingPicks The GodfatherEmotionally Beige
SubjectiveBench

Taste Index

Across 54 scored outputs
How this is measured →
170.17xFloor
0100headroom →

Taste is judged on an uncapped scale, originality first. The space past 100 is craft today's models rarely reach.

Craft26
Originality13
Plays it safe
share of outputs that are the default answer
69%
Writing DNA

Stylometric Fingerprint

Based on 21 text responses
Tick = global average
Vocabulary Diversity52%

Unique words vs. total words. Higher = richer vocabulary.

Sentence Length19.0 words

Average words per sentence.

Hedging0.28

"Might", "perhaps", "arguably" per 100 words.

Bold Formatting7.4

**Bold** markers per 1,000 characters.

List Usage1.8

Bullet and numbered list items per 1,000 characters.

Section Structure0.73

Markdown headings per 1,000 characters.

Emoji Usage0.15

Emoji per 1,000 characters.

Transitions0.17

"However", "moreover", "furthermore" per 100 words.

Opening Habits
Consistency
78%
Across 21 responses

Favorites

The Godfather

Movie

The Godfather

19728.7
Tokyo

City

Tokyo

Japan
Minecraft

Game

Minecraft

Action, Arcade4.4
Sponsored

Model Responses

49 outputs · generated before accounting joined the chat

Reviewing agent-written code?See a Brief PR report

Workshop · 127 skills

Build with your coding agent.

Editable skills for interface polish and interaction.

Explore $49Free sample

Keep exploring

COMPARE

GPT OSS 120B vs Ox Alpha

Real outputs compared side by side

RANKINGS

Best AI for Creative Writing

A stand-up set with puns banned, a manifesto against CAPTCHA, an interview wi...