cd /news/large-language-models/glm-5-1-tencent-released-hy3-non-pre… · home › topics › large-language-models › article
[ARTICLE · art-48908] src=outyet.ai ↗ pub= topic=large-language-models verified=true sentiment=↑ positive

GLM-5.1: Tencent released Hy3 (non-preview), a 295B-parameter MoE open model with 21B active and 3.8B MTP layer params. > This Hy3 release follows the Hy3 Preview launch in late April.

Tencent released Hy3, a 295B-parameter Mixture-of-Experts open model with 21B active parameters and a 3.8B MTP layer, following the Hy3 Preview launch in late April. Hy3 scored 2.67/4 on benchmarks, outperforming GLM-5.1 at 2.51/4, with the clearest advantage in coding and reasoning tasks.

read2 min views1 publishedJul 6, 2026
GLM-5.1: Tencent released Hy3 (non-preview), a 295B-parameter MoE open model with 21B active and 3.8B MTP layer params. > This Hy3 release follows the Hy3 Preview launch in late April.
Image: Outyet (auto-discovered)

Z.aiGLM-5.1 Yes.

How we confirmed it

Released via official access

April 7, 2026 at 12:00 AM UTC

Waiting for Z.ai's next model?

One click creates your free account (or signs you into an existing one) and turns on alerts for Z.ai releases. There's no password to set, and you can unsubscribe any time.

Benchmarks

Coding#19

GLM-5.1 · via BenchLM.ai · captured Jul 3, 2026 · source 80.6

Reasoning#32

GLM-5.1 · via BenchLM.ai · captured Jul 3, 2026 · source 60.5

Knowledge#12

GLM-5.1 · via BenchLM.ai · captured Jul 3, 2026 · source 82.5

Math#13

GLM-5.1 · via BenchLM.ai · captured Jul 3, 2026 · source 91.3

InstructionFollowing#8

GLM-5.1 · via BenchLM.ai · captured Jul 3, 2026 · source 93.8

ExploitBench

Glm 5.1 · via Epoch AI · captured Jul 3, 2026 · source 18

SWE-Bench Pro#5self-reported

zai-org/GLM-5.1 · via Hugging Face · captured Jul 3, 2026 · [source](https://huggingface.co/datasets/ScaleAI/SWE-bench_Pro)

58.4

LM Arena#22

glm-5.1 · via LM Arena · 22,689 votes · captured Jul 3, 2026 · source 1472.21

Sourced metrics mirrored with attribution — not community sentiment.

Data from [BenchLM.ai](https://benchlm.ai).

Data from [Epoch AI, “AI Benchmarking Hub”](https://epoch.ai/benchmarks) (CC BY 4.0).

Vibe rating

How this model actually feels to use, rated by the people here.

No vibe ratings yet. Be the first.

Sign in to rate this model. Model Pulse

How is this model behaving today? One check-in per person per day: the running record of “did they nerf it”. Resets at midnight UTC.

No check-ins yet today. Be the first to log how this model is behaving.

Sign in Community consensus

An AI summary of the public comments here. Not a sourced fact.

Not enough public feedback yet to summarize. Add a comment to help build the picture.

[Compare GLM-5.1 with another model →](/compare?models=glm-5-1)

Also waiting on: [ChatGPT 5.6](/models/chatgpt-5-6), [Gemini 3.5 Pro](/models/gemini-3-5-pro), [Claude Fable 5.1](/models/claude-fable-5-1), [Claude Mythos 5.1](/models/claude-mythos-5-1)

Comments #

Missing a model, or wishing OutYet did something it doesn't? Tell us what to build.

source & further reading
outyet.ai — original article Qwen 3.5: sorry for the Sonnet 4.5 misinformation they talked about the J-Lens ASCII art stuff in their blog, and the same was in the image but the image was from their gituhb which says it uses qwen… Claude Opus 4.5: Big gains in PotatoMonetBench from Opus 4.5 to Fable: "There are two controls. One is slider, in which one side is labelled Maximum Potato and the other is Formalware, there are four… Leanstral 1.5: ICYMI: Mistral released Leanstral 1.5, a SOTA open model for Lean 4 proof engineering. > Developers use Lean 4 as a general-purpose functional language (for CLI tools and libraries)…
── more in #large-language-models 4 stories · sorted by recency
simonwillison.net · · #large-language-models
tencent/Hy3
── more on @tencent 3 stories trending now
sponsored brought to you by zahid.host 4,200+ EU-deployed projects
reading about agents? ship yours in a single git push.

Run your AI side-project on zahid.host

EU-based hosting, git-push deploys, automatic HTTPS, no cold starts. Free tier with a custom domain — perfect for shipping the agent you just read about.

$git push zahid main
→ Live at https://your-agent.zahid.host ✓
Get free account → Pricing
from €0/mo · no card required
LIVE [news/glm-5-1-tencent-rele…] indexed:0 read:2min 2026-07-06 · —