// head_to_head

Kimi K3 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

Kimi K3 scores higher, GLM 5.2 costs less — it depends on your workload.

Kimi K3 is ahead by 6.0 points overall, and GLM 5.2 lists 4.0× cheaper per blended million tokens. Whether 6.0 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.

moonshotai

Kimi K3

Blended / 1M
$6.00
Context
1.0M
Released
Jul 16, 2026
Overall score
79.2
reasoningtool callingimage inputvideo 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

MetricKimi K3GLM 5.2
LiveBench overall

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

79.2win73.2
Cost per point

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

$0.1909$0.1260win
Blended price / 1M

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

$6.00$1.48win
Input price / 1M$3.00$0.966win
Output price / 1M$15.00$3.04win
Cached input / 1M

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

$0.300$0.193win
Context window1.0M1.0M
Max output tokens131K

Benchmarks by category

An overall score averages away the thing you probably care about. These are the seven LiveBench categories scored separately — Kimi K3 on top, GLM 5.2 below, both out of 100.

Agentic coding
62.2
51.8
Coding
81.4
79.7
Reasoning
90.7
78.6
Mathematics
84.4
89.8
Data analysis
78.7
73.7
Language
85.5
76.2
Instruction following
71.4
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.

WorkloadKimi K3GLM 5.2
Support chatbot

1.2K in / 400 out × 200K requests

$1725.60/mo$419.08/mo
RAG assistant

8K in / 600 out × 100K requests

$2220.00/mo$645.84/mo
Coding agent

40K in / 4K out × 20K requests

$2088.00/mo$582.91/mo
Document extraction

20K in / 1.5K out × 50K requests

$3990.00/mo$1155.06/mo
Bulk classification

500 in / 20 out × 5M requests

$7650.00/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

Kimi K3

Highest overall LiveBench score of the two at 79.2.

The workload is coding or agentic work

Kimi K3

Leads on agentic coding — 62.2 against 51.8.

Kimi K3 vs GLM 5.2 FAQ

Which is better, Kimi K3 or GLM 5.2?

Kimi K3 scores higher, GLM 5.2 costs less — it depends on your workload. Kimi K3 is ahead by 6.0 points overall, and GLM 5.2 lists 4.0× cheaper per blended million tokens. Whether 6.0 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 Kimi K3 cheaper than GLM 5.2?

GLM 5.2 is cheaper. On a 3:1 input:output blend, Kimi K3 lists at $6.00 per million tokens and GLM 5.2 at $1.48 — GLM 5.2 is 4.0× cheaper. Input and output are priced separately — Kimi K3 charges $3.00 in and $15.00 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.

Kimi K3 vs GLM 5.2: which scores higher on benchmarks?

Kimi K3 scores 79.2 and GLM 5.2 scores 73.2 overall on LiveBench, the mean of its seven categories. That is a 6.0-point lead for Kimi K3. 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, Kimi K3 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. Kimi K3 works out at $0.1909 per point and GLM 5.2 at $0.1260.

Does Kimi K3 or GLM 5.2 have a bigger context window?

They are effectively the same — 1.0M for Kimi K3 and 1.0M for GLM 5.2.

Do Kimi K3 and GLM 5.2 support prompt caching?

Both publish a cached-input rate: $0.300 per million for Kimi K3 and $0.193 for GLM 5.2, against full input rates of $3.00 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.