// head_to_head
GPT-6.1 Terra vs GLM 5.2
Published LiveBench scores across all seven categories, live list pricing, context windows, and the measured cost of a point of capability — for both models, side by side.
GLM 5.2 is the cheaper of the two; neither can be ranked on quality here.
GLM 5.2 does not have a published LiveBench run, so this comparison covers price, context and declared capabilities only. A missing score means "not evaluated", not "worse" — the right way to separate these two is an eval on your own workload.
openai
GPT-6.1 Terra
- Blended / 1M
- $2.00
- Context
- 1.1M
- Released
- Oct 26, 2026
- Overall score
- 77.8
z-ai
GLM 5.2
- Blended / 1M
- $1.78
- Context
- 1.0M
- Released
- Jun 16, 2026
- Overall score
- Not evaluated
Specs and pricing
| Metric | GPT-6.1 Terra | GLM 5.2 |
|---|---|---|
| LiveBench overall Weighted mean of the seven LiveBench category scores, 0–100. Higher is better. | 77.8 | — |
| Cost per point Measured benchmark spend divided by overall score — dollars per point of capability. | $0.0067 | — |
| Blended price / 1M 3:1 input:output mix, the usual shape of production traffic. | $2.00 | $1.78win |
| Input price / 1M | $1.00 | $0.034win |
| Output price / 1M | $5.00win | $7.00 |
| Cached input / 1M Price of an input token served from the prompt cache, where the provider publishes one. | $0.050 | $0.033win |
| Context window | 1.1M | 1.0M |
| Max output tokens | 128K | 944Kwin |
Benchmarks by category
An overall score averages away the thing you probably care about. These are the seven LiveBench categories scored separately — GPT-6.1 Terra on top, GLM 5.2 below, both out of 100.
What each one costs to run
Per-token prices are hard to feel. These are monthly list costs for both models across five workload shapes, using each provider's published cached-input rate where there is one.
| Workload | GPT-6.1 Terra | GLM 5.2 |
|---|---|---|
| Support chatbot 1.2K in / 400 out × 200K requests | $571.60/mo | $568.11/mo |
| RAG assistant 8K in / 600 out × 100K requests | $720.00/mo | $446.88/mo |
| Coding agent 40K in / 4K out × 20K requests | $668.00/mo | $586.72/mo |
| Document extraction 20K in / 1.5K out × 50K requests | $1,328/mo | $559.05/mo |
| Bulk classification 500 in / 20 out × 5M requests | $2,525/mo | $784.75/mo |
Which should you pick?
You are cost-constrained
GLM 5.2
Cheaper on blended list price at $1.78 per million tokens.
GPT-6.1 Terra vs GLM 5.2 FAQ
Which is better, GPT-6.1 Terra or GLM 5.2?
GLM 5.2 is the cheaper of the two; neither can be ranked on quality here. GLM 5.2 does not have a published LiveBench run, so this comparison covers price, context and declared capabilities only. A missing score means "not evaluated", not "worse" — the right way to separate these two is an eval on your own workload.
Is GPT-6.1 Terra cheaper than GLM 5.2?
GLM 5.2 is cheaper. On a 3:1 input:output blend, GPT-6.1 Terra lists at $2.00 per million tokens and GLM 5.2 at $1.78 — GLM 5.2 is 13% cheaper. Input and output are priced separately — GPT-6.1 Terra charges $1.00 in and $5.00 out, GLM 5.2 charges $0.034 and $7.00 — so the model that looks cheaper flips depending on how output-heavy your workload is.
Does GPT-6.1 Terra or GLM 5.2 have a bigger context window?
They are effectively the same — 1.1M for GPT-6.1 Terra and 1.0M for GLM 5.2.
Do GPT-6.1 Terra and GLM 5.2 support prompt caching?
Both publish a cached-input rate: $0.050 per million for GPT-6.1 Terra and $0.033 for GLM 5.2, against full input rates of $1.00 and $0.034. On a workload with a long stable prefix — a system prompt, a tool schema, a retrieved corpus — that changes the economics more than the headline price does.
Related comparisons
How these numbers are produced
- Price — provider list price from OpenRouter, refreshed every 15 minutes. “Blended” is a 3:1 input:output mix.
- Scores — LiveBench release 2026-10-25, using their own category map. Each model shows its strongest published run. A blank means “not evaluated”, never “bad”.
- Cost per point — the measured dollars LiveBench spent on the run, divided by the score it earned.
- “Win” — awarded only past a threshold: one full point on a benchmark score, 10% on a price, 25% on a context window. Anything tighter reports as a tie, because effort settings alone move a LiveBench score by more than that.
Published benchmarks rank models on someone else's tasks. Before committing, see LLM & agent evaluation for building an eval on your own.