// head_to_head
Mistral Large 4 vs MiMo-V2.5-Pro
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.
MiMo-V2.5-Pro is the cheaper of the two; neither can be ranked on quality here.
MiMo-V2.5-Pro 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.
mistralai
Mistral Large 4
- Blended / 1M
- $1.05
- Context
- 1.0M
- Released
- Oct 6, 2026
- Overall score
- 43.9
xiaomi
MiMo-V2.5-Pro
- Blended / 1M
- $0.810
- Context
- 1.1M
- Released
- Apr 22, 2026
- Overall score
- Not evaluated
Specs and pricing
| Metric | Mistral Large 4 | MiMo-V2.5-Pro |
|---|---|---|
| LiveBench overall Weighted mean of the seven LiveBench category scores, 0–100. Higher is better. | 43.9 | — |
| Cost per point Measured benchmark spend divided by overall score — dollars per point of capability. | $0.0162 | — |
| Blended price / 1M 3:1 input:output mix, the usual shape of production traffic. | $1.05 | $0.810win |
| Input price / 1M | $0.700 | $0.480win |
| Output price / 1M | $2.10 | $1.80win |
| Cached input / 1M Price of an input token served from the prompt cache, where the provider publishes one. | $0.070win | $0.096 |
| Context window | 1.0M | 1.1M |
| Max output tokens | 262K | 236K |
Benchmarks by category
An overall score averages away the thing you probably care about. These are the seven LiveBench categories scored separately — Mistral Large 4 on top, MiMo-V2.5-Pro 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 | Mistral Large 4 | MiMo-V2.5-Pro |
|---|---|---|
| Support chatbot 1.2K in / 400 out × 200K requests | $290.64/mo | $231.55/mo |
| RAG assistant 8K in / 600 out × 100K requests | $434.00/mo | $338.40/mo |
| Coding agent 40K in / 4K out × 20K requests | $375.20/mo | $312.96/mo |
| Document extraction 20K in / 1.5K out × 50K requests | $826.00/mo | $595.80/mo |
| Bulk classification 500 in / 20 out × 5M requests | $1,645/mo | $1,188/mo |
Which should you pick?
You are cost-constrained
MiMo-V2.5-Pro
Cheaper on blended list price at $0.810 per million tokens.
Mistral Large 4 vs MiMo-V2.5-Pro FAQ
Which is better, Mistral Large 4 or MiMo-V2.5-Pro?
MiMo-V2.5-Pro is the cheaper of the two; neither can be ranked on quality here. MiMo-V2.5-Pro 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 Mistral Large 4 cheaper than MiMo-V2.5-Pro?
MiMo-V2.5-Pro is cheaper. On a 3:1 input:output blend, Mistral Large 4 lists at $1.05 per million tokens and MiMo-V2.5-Pro at $0.810 — MiMo-V2.5-Pro is 30% cheaper. Input and output are priced separately — Mistral Large 4 charges $0.700 in and $2.10 out, MiMo-V2.5-Pro charges $0.480 and $1.80 — so the model that looks cheaper flips depending on how output-heavy your workload is.
Does Mistral Large 4 or MiMo-V2.5-Pro have a bigger context window?
They are effectively the same — 1.0M for Mistral Large 4 and 1.1M for MiMo-V2.5-Pro.
Do Mistral Large 4 and MiMo-V2.5-Pro support prompt caching?
Both publish a cached-input rate: $0.070 per million for Mistral Large 4 and $0.096 for MiMo-V2.5-Pro, against full input rates of $0.700 and $0.480. 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 2026-10-25, 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.