// head_to_head

GPT-5.5 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.

OpenRouter + LiveBenchAll comparisonsFull leaderboard

GPT-5.5 scores higher, GLM 5.2 costs less — it depends on your workload.

GPT-5.5 is ahead by 7.0 points overall, and GLM 5.2 lists 7.6× cheaper per blended million tokens. Whether 7.0 points is worth that depends on how much a wrong answer costs you. GLM 5.2 also leads on measured cost per point of capability, at $0.1260 per point.

openai

GPT-5.5

Blended / 1M
$11.25
Context
1.1M
Released
Apr 24, 2026
Overall score
80.2
reasoningtool callingfile inputimage inputprompt caching

z-ai

GLM 5.2

Blended / 1M
$1.48
Context
1.0M
Released
Jun 16, 2026
Overall score
73.2
reasoningtool callingprompt caching

Specs and pricing

MetricGPT-5.5GLM 5.2
LiveBench overall

Mean of the seven LiveBench category scores, 0–100. Higher is better.

80.2win73.2
Cost per point

Measured benchmark spend divided by overall score — dollars per point of capability.

$0.2417$0.1260win
Blended price / 1M

3:1 input:output mix, the usual shape of production traffic.

$11.25$1.48win
Input price / 1M$5.00$0.966win
Output price / 1M$30.00$3.04win
Cached input / 1M

Price of an input token served from the prompt cache, where the provider publishes one.

$0.500$0.193win
Context window1.1M1.0M
Max output tokens128K131K

Benchmarks by category

An overall score averages away the thing you probably care about. These are the seven LiveBench categories scored separately — GPT-5.5 on top, GLM 5.2 below, both out of 100.

Agentic coding
54.0
51.8
Coding
82.1
79.7
Reasoning
89.7
78.6
Mathematics
95.9
89.8
Data analysis
81.6
73.7
Language
87.4
76.2
Instruction following
70.7
62.3

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.

WorkloadGPT-5.5GLM 5.2
Support chatbot

1.2K in / 400 out × 200K requests

$3276.00/mo$419.08/mo
RAG assistant

8K in / 600 out × 100K requests

$4000.00/mo$645.84/mo
Coding agent

40K in / 4K out × 20K requests

$3880.00/mo$582.91/mo
Document extraction

20K in / 1.5K out × 50K requests

$7025.00/mo$1155.06/mo
Bulk classification

500 in / 20 out × 5M requests

$13,250/mo$2332.20/mo
Run these two through the cost calculator

Which should you pick?

You are running this at volume

GLM 5.2

Lowest measured cost per point of capability at $0.1260 per point — the gap compounds with every request.

Quality matters more than the bill

GPT-5.5

Highest overall LiveBench score of the two at 80.2.

The workload is coding or agentic work

GPT-5.5

Leads on agentic coding — 54.0 against 51.8.

GPT-5.5 vs GLM 5.2 FAQ

Which is better, GPT-5.5 or GLM 5.2?

GPT-5.5 scores higher, GLM 5.2 costs less — it depends on your workload. GPT-5.5 is ahead by 7.0 points overall, and GLM 5.2 lists 7.6× cheaper per blended million tokens. Whether 7.0 points is worth that depends on how much a wrong answer costs you. GLM 5.2 also leads on measured cost per point of capability, at $0.1260 per point.

Is GPT-5.5 cheaper than GLM 5.2?

GLM 5.2 is cheaper. On a 3:1 input:output blend, GPT-5.5 lists at $11.25 per million tokens and GLM 5.2 at $1.48 — GLM 5.2 is 7.6× cheaper. Input and output are priced separately — GPT-5.5 charges $5.00 in and $30.00 out, GLM 5.2 charges $0.966 and $3.04 — so the model that looks cheaper flips depending on how output-heavy your workload is.

GPT-5.5 vs GLM 5.2: which scores higher on benchmarks?

GPT-5.5 scores 80.2 and GLM 5.2 scores 73.2 overall on LiveBench, the mean of its seven categories. That is a 7.0-point lead for GPT-5.5. 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-5.5 or GLM 5.2?

GLM 5.2. 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-5.5 works out at $0.2417 per point and GLM 5.2 at $0.1260.

Does GPT-5.5 or GLM 5.2 have a bigger context window?

They are effectively the same — 1.1M for GPT-5.5 and 1.0M for GLM 5.2.

Do GPT-5.5 and GLM 5.2 support prompt caching?

Both publish a cached-input rate: $0.500 per million for GPT-5.5 and $0.193 for GLM 5.2, against full input rates of $5.00 and $0.966. 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.
  • ScoresLiveBench 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.