// head_to_head
GPT-5.2-Codex vs MiMo-V2.6-Pro-UltraSpeed
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 is the cheaper of the two; neither can be ranked on quality here.
MiMo-V2.6-Pro-UltraSpeed 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-5.2-Codex
- Blended / 1M
- $4.81
- Context
- 400K
- Released
- Jan 14, 2026
- Overall score
- 74.0
xiaomi
MiMo-V2.6-Pro-UltraSpeed
- Blended / 1M
- $5.44
- Context
- 1.0M
- Released
- Sep 21, 2026
- Overall score
- Not evaluated
Specs and pricing
| Metric | GPT-5.2-Codex | MiMo-V2.6-Pro-UltraSpeed |
|---|---|---|
| LiveBench overall Mean of the seven LiveBench category scores, 0–100. Higher is better. | 74.0 | — |
| Cost per point Measured benchmark spend divided by overall score — dollars per point of capability. | $0.1001 | — |
| Blended price / 1M 3:1 input:output mix, the usual shape of production traffic. | $4.81win | $5.44 |
| Input price / 1M | $1.75win | $4.35 |
| Output price / 1M | $14.00 | $8.70win |
| Cached input / 1M Price of an input token served from the prompt cache, where the provider publishes one. | $0.175 | $0.036win |
| 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, MiMo-V2.6-Pro-UltraSpeed 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 | MiMo-V2.6-Pro-UltraSpeed |
|---|---|---|
| Support chatbot 1.2K in / 400 out × 200K requests | $1,427/mo | $1,429/mo |
| RAG assistant 8K in / 600 out × 100K requests | $1,610/mo | $2,276/mo |
| Coding agent 40K in / 4K out × 20K requests | $1,638/mo | $1,760/mo |
| Document extraction 20K in / 1.5K out × 50K requests | $2,721/mo | $4,787/mo |
| Bulk classification 500 in / 20 out × 5M requests | $4,988/mo | $9,588/mo |
Which should you pick?
You need to fit large documents in one call
MiMo-V2.6-Pro-UltraSpeed
Wider context window — 1.0M against 400K.
You are cost-constrained
GPT-5.2-Codex
Cheaper on blended list price at $4.81 per million tokens.
GPT-5.2-Codex vs MiMo-V2.6-Pro-UltraSpeed FAQ
Which is better, GPT-5.2-Codex or MiMo-V2.6-Pro-UltraSpeed?
GPT-5.2-Codex is the cheaper of the two; neither can be ranked on quality here. MiMo-V2.6-Pro-UltraSpeed 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-5.2-Codex cheaper than MiMo-V2.6-Pro-UltraSpeed?
GPT-5.2-Codex is cheaper. On a 3:1 input:output blend, GPT-5.2-Codex lists at $4.81 per million tokens and MiMo-V2.6-Pro-UltraSpeed at $5.44 — GPT-5.2-Codex is 13% cheaper. Input and output are priced separately — GPT-5.2-Codex charges $1.75 in and $14.00 out, MiMo-V2.6-Pro-UltraSpeed charges $4.35 and $8.70 — so the model that looks cheaper flips depending on how output-heavy your workload is.
Does GPT-5.2-Codex or MiMo-V2.6-Pro-UltraSpeed have a bigger context window?
MiMo-V2.6-Pro-UltraSpeed has the larger context window: 400K for GPT-5.2-Codex against 1.0M for MiMo-V2.6-Pro-UltraSpeed. 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 MiMo-V2.6-Pro-UltraSpeed support prompt caching?
Both publish a cached-input rate: $0.175 per million for GPT-5.2-Codex and $0.036 for MiMo-V2.6-Pro-UltraSpeed, against full input rates of $1.75 and $4.35. 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.