// head_to_head
Kimi K2.6 vs GPT-5.2-Codex
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.
GPT-5.2-Codex scores higher, Kimi K2.6 costs less — it depends on your workload.
GPT-5.2-Codex is ahead by 3.4 points overall, and Kimi K2.6 lists 4.8× cheaper per blended million tokens. Whether 3.4 points is worth that depends on how much a wrong answer costs you.
moonshotai
Kimi K2.6
- Blended / 1M
- $1.01
- Context
- 262K
- Released
- Apr 20, 2026
- Overall score
- 70.5
openai
GPT-5.2-Codex
- Blended / 1M
- $4.81
- Context
- 400K
- Released
- Jan 14, 2026
- Overall score
- 74.0
Specs and pricing
| Metric | Kimi K2.6 | GPT-5.2-Codex |
|---|---|---|
| LiveBench overall Mean of the seven LiveBench category scores, 0–100. Higher is better. | 70.5 | 74.0win |
| Cost per point Measured benchmark spend divided by overall score — dollars per point of capability. | $0.0918 | $0.1001 |
| Blended price / 1M 3:1 input:output mix, the usual shape of production traffic. | $1.01win | $4.81 |
| Input price / 1M | $0.560win | $1.75 |
| Output price / 1M | $2.36win | $14.00 |
| Cached input / 1M Price of an input token served from the prompt cache, where the provider publishes one. | $0.094win | $0.175 |
| Context window | 262K | 400Kwin |
| Max output tokens | 262Kwin | 128K |
Benchmarks by category
An overall score averages away the thing you probably care about. These are the seven LiveBench categories scored separately — Kimi K2.6 on top, GPT-5.2-Codex 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 | Kimi K2.6 | GPT-5.2-Codex |
|---|---|---|
| Support chatbot 1.2K in / 400 out × 200K requests | $289.76/mo | $1426.60/mo |
| RAG assistant 8K in / 600 out × 100K requests | $403.56/mo | $1610.00/mo |
| Coding agent 40K in / 4K out × 20K requests | $376.18/mo | $1638.00/mo |
| Document extraction 20K in / 1.5K out × 50K requests | $714.19/mo | $2721.25/mo |
| Bulk classification 500 in / 20 out × 5M requests | $1404.20/mo | $4987.50/mo |
Which should you pick?
Quality matters more than the bill
GPT-5.2-Codex
Highest overall LiveBench score of the two at 74.0.
The workload is coding or agentic work
GPT-5.2-Codex
Leads on agentic coding — 49.4 against 46.9.
You need to fit large documents in one call
GPT-5.2-Codex
Wider context window — 400K against 262K.
You are cost-constrained
Kimi K2.6
Cheaper on blended list price at $1.01 per million tokens.
Kimi K2.6 vs GPT-5.2-Codex FAQ
Which is better, Kimi K2.6 or GPT-5.2-Codex?
GPT-5.2-Codex scores higher, Kimi K2.6 costs less — it depends on your workload. GPT-5.2-Codex is ahead by 3.4 points overall, and Kimi K2.6 lists 4.8× cheaper per blended million tokens. Whether 3.4 points is worth that depends on how much a wrong answer costs you.
Is Kimi K2.6 cheaper than GPT-5.2-Codex?
Kimi K2.6 is cheaper. On a 3:1 input:output blend, Kimi K2.6 lists at $1.01 per million tokens and GPT-5.2-Codex at $4.81 — Kimi K2.6 is 4.8× cheaper. Input and output are priced separately — Kimi K2.6 charges $0.560 in and $2.36 out, GPT-5.2-Codex charges $1.75 and $14.00 — so the model that looks cheaper flips depending on how output-heavy your workload is.
Kimi K2.6 vs GPT-5.2-Codex: which scores higher on benchmarks?
Kimi K2.6 scores 70.5 and GPT-5.2-Codex scores 74.0 overall on LiveBench, the mean of its seven categories. That is a 3.4-point lead for GPT-5.2-Codex. 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 K2.6 or GPT-5.2-Codex?
They are close. Kimi K2.6 costs $0.0918 per point of overall capability and GPT-5.2-Codex costs $0.1001, a difference small enough that workload shape will matter more than the rate.
Does Kimi K2.6 or GPT-5.2-Codex have a bigger context window?
GPT-5.2-Codex has the larger context window: 262K for Kimi K2.6 against 400K for GPT-5.2-Codex. 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 Kimi K2.6 and GPT-5.2-Codex support prompt caching?
Both publish a cached-input rate: $0.094 per million for Kimi K2.6 and $0.175 for GPT-5.2-Codex, against full input rates of $0.560 and $1.75. 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.