// head_to_head
DeepSeek V3 vs GPT-5.6 Luna
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 V3 and GPT-5.6 Luna are priced within ~10% of each other.
DeepSeek V3 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 V3
- Blended / 1M
- $0.462
- Context
- 164K
- Released
- Dec 26, 2024
- Overall score
- Not evaluated
openai
GPT-5.6 Luna
- Blended / 1M
- $0.450
- Context
- 1.1M
- Released
- Jul 9, 2026
- Overall score
- 73.6
Specs and pricing
| Metric | DeepSeek V3 | GPT-5.6 Luna |
|---|---|---|
| LiveBench overall Mean of the seven LiveBench category scores, 0–100. Higher is better. | — | 73.6 |
| Cost per point Measured benchmark spend divided by overall score — dollars per point of capability. | — | $0.0911 |
| Blended price / 1M 3:1 input:output mix, the usual shape of production traffic. | $0.462 | $0.450 |
| Input price / 1M | $0.320 | $0.200win |
| Output price / 1M | $0.890win | $1.20 |
| Cached input / 1M Price of an input token served from the prompt cache, where the provider publishes one. | — | $0.020 |
| Context window | 164K | 1.1Mwin |
| Max output tokens | 16K | 128Kwin |
Benchmarks by category
An overall score averages away the thing you probably care about. These are the seven LiveBench categories scored separately — DeepSeek V3 on top, GPT-5.6 Luna 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 V3 | GPT-5.6 Luna |
|---|---|---|
| Support chatbot 1.2K in / 400 out × 200K requests | $148.00/mo | $131.04/mo |
| RAG assistant 8K in / 600 out × 100K requests | $309.40/mo | $160.00/mo |
| Coding agent 40K in / 4K out × 20K requests | $327.20/mo | $155.20/mo |
| Document extraction 20K in / 1.5K out × 50K requests | $386.75/mo | $281.00/mo |
| Bulk classification 500 in / 20 out × 5M requests | $889.00/mo | $530.00/mo |
Which should you pick?
You need to fit large documents in one call
GPT-5.6 Luna
Wider context window — 1.1M against 164K.
DeepSeek V3 vs GPT-5.6 Luna FAQ
Which is better, DeepSeek V3 or GPT-5.6 Luna?
DeepSeek V3 and GPT-5.6 Luna are priced within ~10% of each other. DeepSeek V3 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 V3 cheaper than GPT-5.6 Luna?
They cost about the same. Both land near $0.462 per million tokens on a 3:1 input:output blend, so price is unlikely to be the deciding factor between them.
Does DeepSeek V3 or GPT-5.6 Luna have a bigger context window?
GPT-5.6 Luna has the larger context window: 164K for DeepSeek V3 against 1.1M for GPT-5.6 Luna. 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 DeepSeek V3 and GPT-5.6 Luna support prompt caching?
GPT-5.6 Luna publishes a cached-input rate of $0.020 per million tokens against a full input rate of $0.200. The catalogue lists no separate cached rate for DeepSeek V3, which means the provider does not price it separately here — not that caching is unavailable.
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.