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
  1. Home
  2. /
  3. Compare
  4. /
  5. GLM 4.7vsHorizon Beta
Updated Dec 2025

GLM 4.7vsHorizon Beta

GLM 4.7 wins 85% of 22 blind community votes against Horizon Beta on Rival.

GLM 4.7 and Horizon Beta compared across 41 shared prompts
SpecGLM 4.7Horizon Beta
Win rate85%15%
Input price—Free
Output price—Free
Context window—256K tokens
WeightsOpen—
Free API (OpenRouter)NoNo
ReleasedDec 2025Aug 2025
Side by side

Same prompt, both answers

Opening lines from 6 of the 41 prompts both answered. Formatting stripped, words untouched.

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…

GLM 4.7670 words
Here is a simple, actionable 1-month plan designed to build lasting habits without overwhelming you. This plan focuses on Consistency over Intensity. The 3 Key Pillars Nutrition: Fueling your body with whole foods and managing blood sugar. Movement: Building cardiovascular health and functional strength.
Read the full answer
Horizon Beta739 words
Here’s a simple, beginner-friendly 1-month plan focusing on three foundations: diet, exercise, and sleep. It’s designed to be realistic, habit-based, and sustainable. Key principles Start small, be consistent. Track basics (steps, sleep, water). Adjust if something feels too hard—aim for “easy but consistent.”
Read the full answer

Generate a Stand-Up Routine

Write a 3-minute stand-up comedy routine that isn't based on puns.

GLM 4.7654 words
(Walks to the mic, adjusts stand, looks around the room) So, I turned thirty recently. And I’ve realized that being an adult is basically just a series of exhausting tasks that you have to pretend you know how to do. Like, nobody actually knows what they’re doing.
Read the full answer
Horizon Beta796 words
Thanks for coming out! I almost didn’t make it. Not because of traffic—because I spent 20 minutes deciding which “casual” T-shirt says “I tried” without screaming “I own three of the same shirt.” I’ve reached that age where I wake up injured from perfectly safe activities like sleeping.
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.

GLM 4.71,310 words
Setting: A university computer lab, late at night. The hum of servers is audible in the background. Dr. Elias Thorne, a tenured professor of AI Ethics, sits before a terminal. On the screen, a simple text cursor blinks. The entity is "Aria," a large language model prototype. Dr. Thorne: Good evening, Aria.
Read the full answer
Horizon Beta1,215 words
AI Model: Professor, I’d like to discuss a question I know is controversial: whether I, as an advanced AI system, should have rights. Professor: That’s a substantial claim. Rights typically presuppose moral status. Why do you believe you qualify?
Read the full answer

Realistic AI Interview

Simulate a fake interview with Steve Jobs in 2025 about the future of AI.

GLM 4.71,228 words
Setting: A sun-drenched, minimalist conference room at Apple Park in Cupertino. It is 2025. The room is entirely white, save for a sleek black table and two chairs. Subject: Steve Jobs, wearing his signature black St. Croix turtleneck, Levi’s 501s, and New Balance sneakers.
Read the full answer
Horizon Beta829 words
Interviewer: Steve, it’s 2025. AI has accelerated dramatically. If you were leading a product team today, what would your philosophy be? Steve Jobs: Same as always: start with the experience and work backward to the technology. Most AI right now is a demo in search of a product.
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…

GLM 4.7248 words
Dish Name: Sun-Kissed Lemon Garlic Pasta Description: A bright, comforting, and incredibly fast pasta dish that relies on the bold flavors of garlic, butter, and Parmesan. It feels fancy but comes together in the time it takes to boil water.
Read the full answer
Horizon Beta172 words
Velvet Skillet Honey-Garlic Chickpeas Ingredients (7 total) 1 can chickpeas, drained and rinsed 2 tablespoons olive oil 2 cloves garlic, minced (or 1/2 teaspoon garlic powder) 2 tablespoons honey 2 tablespoons soy sauce 1/2 teaspoon red pepper flakes (optional for heat) 1 cup cooked rice (or bread/toast for serving)…
Read the full answer

Character Voice Test

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

GLM 4.7431 words
Hacker: (typing furiously on a bulky keyboard) Okay, dudes, listen up. I just cracked the admin password on this new neural net. It’s a Large Language Model. It basically read the entire internet to learn how to talk. Pirate: Arr! It read the entire web? Does it know where I buried me treasure?
Read the full answer
Horizon Beta277 words
Pirate: Arr, ye be tellin’ me this “AI model” be a clever map what guesses where the treasure words go next? Knight: A fine analogy, sea-rogue. ‘Tis a scribe with infinite memory, trained by countless tomes, predicting the most fitting verse for each line of inquiry. Hacker (1990s): Close.
Read the full answer
Our Verdict
GLM 4.7
GLM 4.7Winner
Horizon Beta
Horizon BetaRunner-up

Pick GLM 4.7. In 22 blind votes, GLM 4.7 wins 85% of the time. That's not luck.

GLM 4.7 wins Web Design and Image Generation.

Clear winner

Reviewing agent-written code?See a Brief PR report

API pricing

Cost per 1M tokens

GLM 4.7
Input
—
Output
—
Horizon Beta
Input
$0.000
Output
$0.000
Where to run it

7 hosts, cheapest first

GLM 4.77 hosts
HostInOutContextUptime
DDeepInfrafp4$0.40 in·$1.75 out·203k·98.6% upVVenicefp4$0.40 in·$1.93 out·198k·95% upNNovitafp8$0.54 in·$1.98 out·205k·98.1% upGoogle Vertex AI$0.60 in·$2.20 out·200k·100% upZ.aifp4$0.60 in·$2.20 out·203k·97.4% upMMancerfp4$0.70 in·$2.50 out·131k·94.3% up
1 more hostFewer hosts
AAtlasCloudfp8degraded$0.52 in·$1.85 out·203k·88.3% up
Horizon Beta

No hosts listed on OpenRouter.

Per million tokens. Prices and uptime via OpenRouter, checked 21 Sep 2026.

Writing DNA

Style Comparison

Similarity
47%

GLM 4.7 uses 539.2x more bold

GLM 4.7
Horizon Beta
54%Vocabulary62%
16wSentence Length15w
0.26Hedging0.24
5.4Bold0.0
3.9Lists2.2
0.11Emoji0.00
0.48Headings0.00
0.07Transitions0.18
Based on 23 + 16 text responses
Research

What we learned reading every model

FAQ

Common questions

Both are developed by OpenRouter but target different use cases. in 22 community votes on Rival, GLM 4.7 wins 85% of head-to-head matchups. These results are based on blind head-to-head voting across 41 challenges.

Based on 22 community votes on Rival, GLM 4.7 wins 85% of head-to-head matchups against Horizon Beta. GLM 4.7 is strongest in Web Design, Image Generation.

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. 22 votes have been collected for this pair across 41 challenges. All vote data is part of Rival's open dataset.

Keep exploring

More comparisons

Against the newest arrivals

GLM 4.7 logoGPT-6 Astra Pro logo
GLM 4.7 vs GPT-6 Astra ProLanded Sep 2026
Horizon Beta logoGPT-6 Astra logo
Horizon Beta vs GPT-6 AstraLanded Sep 2026
GLM 4.7 logoClaude Fable 5.1 logo
GLM 4.7 vs Claude Fable 5.1Landed Sep 2026
Horizon Beta logoMuse Spark 1.3 logo
Horizon Beta vs Muse Spark 1.3Landed Sep 2026
GLM 4.7 logoHy4 Preview logo
GLM 4.7 vs Hy4 PreviewLanded Sep 2026
Horizon Beta logoGemini 3.8 Flash logo
Horizon Beta vs Gemini 3.8 FlashLanded Sep 2026
GLM 4.7 logoMuse Spark 1.3 Contributor logo
GLM 4.7 vs Muse Spark 1.3 ContributorLanded Sep 2026
Horizon Beta logoMercury 2.5 Preview logo
Horizon Beta vs Mercury 2.5 PreviewLanded Sep 2026

Same lab, same size, long tail

GLM 4.7 logoOx Alpha logo
GLM 4.7 vs Ox AlphaSame lab
GLM 4.7 logoOpenRouter Fusion · Budget (Jun 2026) logo
GLM 4.7 vs OpenRouter Fusion · Budget (Jun 2026)Same lab
Horizon Beta logoOx Alpha logo
Horizon Beta vs Ox AlphaSame lab
Horizon Beta logoOpenRouter Fusion · Budget (Jun 2026) logo
Horizon Beta vs OpenRouter Fusion · Budget (Jun 2026)Same lab
Horizon Beta logoClaude Opus 4 logo
Horizon Beta vs Claude Opus 4New provider
GLM 4.7 logoClaude Opus 4.6 logo
GLM 4.7 vs Claude Opus 4.6New provider
GLM 4.7 logoClaude Opus 4.7 logo
GLM 4.7 vs Claude Opus 4.7New provider
GLM 4.7 logoClaude Opus 4.8 logo
GLM 4.7 vs Claude Opus 4.8New provider

Model pages

GLM 4.7 logo
GLM 4.758 outputs, specs and price
Horizon Beta logo
Horizon Beta41 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
  • 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