// head_to_head
DeepSeek V4 Flash 0731 vs MiMo-V2.5
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.
DeepSeek V4 Flash 0731 and MiMo-V2.5 are priced within ~10% of each other.
MiMo-V2.5 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.
deepseek
DeepSeek V4 Flash 0731
- Blended / 1M
- $0.190
- Context
- 1.3M
- Released
- Jul 31, 2026
- Overall score
- 74.2
xiaomi
MiMo-V2.5
- Blended / 1M
- $0.175
- Context
- 1.1M
- Released
- Apr 22, 2026
- Overall score
- Not evaluated
Specs and pricing
| Metric | DeepSeek V4 Flash 0731 | MiMo-V2.5 |
|---|---|---|
| LiveBench overall Mean of the seven LiveBench category scores, 0–100. Higher is better. | 74.2 | — |
| Cost per point Measured benchmark spend divided by overall score — dollars per point of capability. | $0.0356 | — |
| Blended price / 1M 3:1 input:output mix, the usual shape of production traffic. | $0.190 | $0.175 |
| Input price / 1M | $0.040win | $0.140 |
| Output price / 1M | $0.640 | $0.280win |
| Cached input / 1M Price of an input token served from the prompt cache, where the provider publishes one. | $0.016 | $0.0028win |
| Context window | 1.3M | 1.1M |
| Max output tokens | 944Kwin | 131K |
Benchmarks by category
An overall score averages away the thing you probably care about. These are the seven LiveBench categories scored separately — DeepSeek V4 Flash 0731 on top, MiMo-V2.5 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 | DeepSeek V4 Flash 0731 | MiMo-V2.5 |
|---|---|---|
| Support chatbot 1.2K in / 400 out × 200K requests | $59.07/mo | $46.12/mo |
| RAG assistant 8K in / 600 out × 100K requests | $60.80/mo | $73.92/mo |
| Coding agent 40K in / 4K out × 20K requests | $69.76/mo | $57.57/mo |
| Document extraction 20K in / 1.5K out × 50K requests | $86.80/mo | $154.14/mo |
| Bulk classification 500 in / 20 out × 5M requests | $152.00/mo | $309.40/mo |
DeepSeek V4 Flash 0731 vs MiMo-V2.5 FAQ
Which is better, DeepSeek V4 Flash 0731 or MiMo-V2.5?
DeepSeek V4 Flash 0731 and MiMo-V2.5 are priced within ~10% of each other. MiMo-V2.5 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 DeepSeek V4 Flash 0731 cheaper than MiMo-V2.5?
They cost about the same. Both land near $0.190 per million tokens on a 3:1 input:output blend, so price is unlikely to be the deciding factor between them.
Does DeepSeek V4 Flash 0731 or MiMo-V2.5 have a bigger context window?
They are effectively the same — 1.3M for DeepSeek V4 Flash 0731 and 1.1M for MiMo-V2.5.
Do DeepSeek V4 Flash 0731 and MiMo-V2.5 support prompt caching?
Both publish a cached-input rate: $0.016 per million for DeepSeek V4 Flash 0731 and $0.0028 for MiMo-V2.5, against full input rates of $0.040 and $0.140. 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.