GLM-5.1 vs Hy3
GLM-5.1 and Hy3 are closely matched at 38.9 and 42.6 on the LLM Stats Score. Hy3 is 6.7x cheaper per token.
Zhipu AI · Tencent · Updated for 2026
Which is better?
GLM-5.1 and Hy3 are closely matched on the overall LLM Stats Score at 38.9 and 42.6.
In the 7 individual benchmarks reported for both models, Hy3 wins 6; this is a narrower head-to-head signal than the composite indexes.
On price, Hy3 is roughly 6.7x cheaper per token on a blended 3:1 input/output basis, which adds up quickly at production volume.
Hy3 also accepts a larger context window (262,144 input tokens), making it the stronger choice for long documents and large codebases.
Based on current LLM Stats indexes, shared benchmarks, pricing, and model metadata for 2026.
Choose GLM-5.1
- you want predictable pricing at $1.05/M input and $3.50/M output
Choose Hy3
- you value its reported benchmark strengths — it wins 6 of 7 exact shared results
- cost matters — it's about 6.7x cheaper per token
- you process long inputs — it offers a 262,144 token context window
- you want the most recent training data — it shipped Jul 2026
At a glance
The differences that matter most.
Capability indexes
Additional strengths measured across groups of related public benchmarks
Individual benchmarks
18 reported for GLM-5.1 · 31 for Hy3
GLM-5.1 outperforms in 1 benchmarks (SWE-Bench Pro), while Hy3 is better at 6 benchmarks (BrowseComp, GPQA, IMO-AnswerBench, MCP Atlas, NL2Repo, Toolathlon).
Hy3 significantly outperforms across most benchmarks.
Human preference
Blind head-to-head votes and playground preference scores
Pricing Analysis
Price comparison per million tokens
For input processing, GLM-5.1 ($1.05/1M tokens) is 7.5x more expensive than Hy3 ($0.14/1M tokens).
For output processing, GLM-5.1 ($3.50/1M tokens) is 6.0x more expensive than Hy3 ($0.58/1M tokens).
In conclusion, GLM-5.1 is more expensive than Hy3.*
* Using a 3:1 ratio of input to output tokens
Model Size
Parameter count comparison
GLM-5.1 has 459.0B more parameters than Hy3, making it 155.6% larger.
Context Window
Maximum input and output token capacity
Hy3 accepts 262,144 input tokens compared to GLM-5.1's 202,752 tokens. Hy3 can generate longer responses up to 262,144 tokens, while GLM-5.1 is limited to 202,752 tokens.
License
Usage and distribution terms
GLM-5.1 is licensed under MIT, while Hy3 uses Apache 2.0.
License differences may affect how you can use these models in commercial or open-source projects.
MIT
Open weights
Apache 2.0
Open weights
Release Timeline
When each model was launched
GLM-5.1 was released on 2026-04-07, while Hy3 was released on 2026-07-06.
Hy3 is 3 months newer than GLM-5.1.
Apr 7, 2026
6 months ago
Jul 6, 2026
3 months ago
3mo newerKnowledge Cutoff
When training data ends
Neither model specifies a knowledge cutoff date.
Unable to compare the recency of their training data.
Provider Availability
GLM-5.1 is available from DeepInfra, FriendliAI, ZAI. Hy3 is available from DeepInfra.
GLM-5.1
Hy3
Outputs Comparison
Judge for yourself.
Run your own prompts against GLM-5.1 and Hy3 side-by-side, then vote on the output you prefer.
FAQ
Common questions about GLM-5.1 vs Hy3.