// head_to_head
GPT-5.2-Codex vs GLM 5.3
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 5.3 wins outright — it scores higher and costs less.
GLM 5.3 leads by 2.2 points overall while listing 2.2× cheaper per blended million tokens. There is no trade-off to reason about here; the only reason to pick the other is a constraint this table does not show, like an existing contract, a region, or a provider you are already on. The two cost measures disagree here, which is worth knowing: GLM 5.3 has the lower sticker price, but GPT-5.2-Codex earns each point of capability for less — $0.1001 against $0.2460 — because per-token rates do not predict how many tokens a model actually spends on a task.
openai
GPT-5.2-Codex
- Blended / 1M
- $4.81
- Context
- 400K
- Released
- Jan 14, 2026
- Overall score
- 74.0
z-ai
GLM 5.3
- Blended / 1M
- $2.15
- Context
- 1.0M
- Released
- Aug 18, 2026
- Overall score
- 76.1
Specs and pricing
| Metric | GPT-5.2-Codex | GLM 5.3 |
|---|---|---|
| LiveBench overall Mean of the seven LiveBench category scores, 0–100. Higher is better. | 74.0 | 76.1win |
| Cost per point Measured benchmark spend divided by overall score — dollars per point of capability. | $0.1001win | $0.2460 |
| Blended price / 1M 3:1 input:output mix, the usual shape of production traffic. | $4.81 | $2.15win |
| Input price / 1M | $1.75 | $1.40win |
| Output price / 1M | $14.00 | $4.40win |
| Cached input / 1M Price of an input token served from the prompt cache, where the provider publishes one. | $0.175win | $0.260 |
| Context window | 400K | 1.0Mwin |
| Max output tokens | 128K | 131K |
Benchmarks by category
An overall score averages away the thing you probably care about. These are the seven LiveBench categories scored separately — GPT-5.2-Codex on top, GLM 5.3 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-5.2-Codex | GLM 5.3 |
|---|---|---|
| Support chatbot 1.2K in / 400 out × 200K requests | $1426.60/mo | $605.92/mo |
| RAG assistant 8K in / 600 out × 100K requests | $1610.00/mo | $928.00/mo |
| Coding agent 40K in / 4K out × 20K requests | $1638.00/mo | $833.60/mo |
| Document extraction 20K in / 1.5K out × 50K requests | $2721.25/mo | $1673.00/mo |
| Bulk classification 500 in / 20 out × 5M requests | $4987.50/mo | $3370.00/mo |
Which should you pick?
You are running this at volume
GPT-5.2-Codex
Lowest measured cost per point of capability at $0.1001 per point — the gap compounds with every request.
Quality matters more than the bill
GLM 5.3
Highest overall LiveBench score of the two at 76.1.
The workload is coding or agentic work
GLM 5.3
Leads on agentic coding — 60.9 against 49.4.
You need to fit large documents in one call
GLM 5.3
Wider context window — 1.0M against 400K.
GPT-5.2-Codex vs GLM 5.3 FAQ
Which is better, GPT-5.2-Codex or GLM 5.3?
GLM 5.3 wins outright — it scores higher and costs less. GLM 5.3 leads by 2.2 points overall while listing 2.2× cheaper per blended million tokens. There is no trade-off to reason about here; the only reason to pick the other is a constraint this table does not show, like an existing contract, a region, or a provider you are already on. The two cost measures disagree here, which is worth knowing: GLM 5.3 has the lower sticker price, but GPT-5.2-Codex earns each point of capability for less — $0.1001 against $0.2460 — because per-token rates do not predict how many tokens a model actually spends on a task.
Is GPT-5.2-Codex cheaper than GLM 5.3?
GLM 5.3 is cheaper. On a 3:1 input:output blend, GPT-5.2-Codex lists at $4.81 per million tokens and GLM 5.3 at $2.15 — GLM 5.3 is 2.2× cheaper. Input and output are priced separately — GPT-5.2-Codex charges $1.75 in and $14.00 out, GLM 5.3 charges $1.40 and $4.40 — so the model that looks cheaper flips depending on how output-heavy your workload is.
GPT-5.2-Codex vs GLM 5.3: which scores higher on benchmarks?
GPT-5.2-Codex scores 74.0 and GLM 5.3 scores 76.1 overall on LiveBench, the mean of its seven categories. That is a 2.2-point lead for GLM 5.3. Category scores differ from the overall figure — a model can lead on reasoning and trail on coding, which the per-category table above breaks out.
Which gives better value for money, GPT-5.2-Codex or GLM 5.3?
GPT-5.2-Codex. Cost per point divides the measured dollars LiveBench spent running the benchmark by the score it earned, so it captures something token pricing misses: a reasoning model can emit many times more tokens than its per-token rate suggests. GPT-5.2-Codex works out at $0.1001 per point and GLM 5.3 at $0.2460.
Does GPT-5.2-Codex or GLM 5.3 have a bigger context window?
GLM 5.3 has the larger context window: 400K for GPT-5.2-Codex against 1.0M for GLM 5.3. Note that a window you can fill is not a window you should fill — retrieval quality usually degrades well before the limit, and you pay for every token you put in it.
Do GPT-5.2-Codex and GLM 5.3 support prompt caching?
Both publish a cached-input rate: $0.175 per million for GPT-5.2-Codex and $0.260 for GLM 5.3, against full input rates of $1.75 and $1.40. 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 2026-06-25, 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.