// head_to_head
GPT-5.6 Terra vs GPT-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.
GPT-5.6 Terra scores higher, GPT-6 Luna costs less — it depends on your workload.
GPT-5.6 Terra is ahead by 3.2 points overall, and GPT-6 Luna lists 23× cheaper per blended million tokens. Whether 3.2 points is worth that depends on how much a wrong answer costs you. GPT-6 Luna also leads on measured cost per point of capability, at $0.0012 per point.
openai
GPT-5.6 Terra
- Blended / 1M
- $4.50
- Context
- 1.1M
- Released
- Jul 9, 2026
- Overall score
- 67.8
openai
GPT-6 Luna
- Blended / 1M
- $0.200
- Context
- 1.1M
- Released
- Sep 22, 2026
- Overall score
- 64.6
Specs and pricing
| Metric | GPT-5.6 Terra | GPT-6 Luna |
|---|---|---|
| LiveBench overall Weighted mean of the seven LiveBench category scores, 0–100. Higher is better. | 67.8win | 64.6 |
| Cost per point Measured benchmark spend divided by overall score — dollars per point of capability. | $0.0192 | $0.0012win |
| Blended price / 1M 3:1 input:output mix, the usual shape of production traffic. | $4.50 | $0.200win |
| Input price / 1M | $2.00 | $0.100win |
| Output price / 1M | $12.00 | $0.500win |
| Cached input / 1M Price of an input token served from the prompt cache, where the provider publishes one. | $0.200 | $0.010win |
| Context window | 1.1M | 1.1M |
| Max output tokens | 128K | 128K |
Benchmarks by category
An overall score averages away the thing you probably care about. These are the seven LiveBench categories scored separately — GPT-5.6 Terra on top, GPT-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 | GPT-5.6 Terra | GPT-6 Luna |
|---|---|---|
| Support chatbot 1.2K in / 400 out × 200K requests | $1,310/mo | $57.52/mo |
| RAG assistant 8K in / 600 out × 100K requests | $1,600/mo | $74.00/mo |
| Coding agent 40K in / 4K out × 20K requests | $1,552/mo | $69.60/mo |
| Document extraction 20K in / 1.5K out × 50K requests | $2,810/mo | $133.00/mo |
| Bulk classification 500 in / 20 out × 5M requests | $5,300/mo | $255.00/mo |
Which should you pick?
You are running this at volume
GPT-6 Luna
Lowest measured cost per point of capability at $0.0012 per point — the gap compounds with every request.
Quality matters more than the bill
GPT-5.6 Terra
Highest overall LiveBench score of the two at 67.8.
The workload is coding or agentic work
GPT-5.6 Terra
Leads on long-horizon agentic — 33.1 against 30.9.
GPT-5.6 Terra vs GPT-6 Luna FAQ
Which is better, GPT-5.6 Terra or GPT-6 Luna?
GPT-5.6 Terra scores higher, GPT-6 Luna costs less — it depends on your workload. GPT-5.6 Terra is ahead by 3.2 points overall, and GPT-6 Luna lists 23× cheaper per blended million tokens. Whether 3.2 points is worth that depends on how much a wrong answer costs you. GPT-6 Luna also leads on measured cost per point of capability, at $0.0012 per point.
Is GPT-5.6 Terra cheaper than GPT-6 Luna?
GPT-6 Luna is cheaper. On a 3:1 input:output blend, GPT-5.6 Terra lists at $4.50 per million tokens and GPT-6 Luna at $0.200 — GPT-6 Luna is 23× cheaper. Input and output are priced separately — GPT-5.6 Terra charges $2.00 in and $12.00 out, GPT-6 Luna charges $0.100 and $0.500 — so the model that looks cheaper flips depending on how output-heavy your workload is.
GPT-5.6 Terra vs GPT-6 Luna: which scores higher on benchmarks?
GPT-5.6 Terra scores 67.8 and GPT-6 Luna scores 64.6 overall on LiveBench, the weighted mean of its seven categories. That is a 3.2-point lead for GPT-5.6 Terra. 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, GPT-5.6 Terra or GPT-6 Luna?
GPT-6 Luna. Cost per point divides the measured dollars LiveBench spent running the benchmark by the score it earned, so it captures something token pricing misses: a reasoning model can emit many times more tokens than its per-token rate suggests. GPT-5.6 Terra works out at $0.0192 per point and GPT-6 Luna at $0.0012.
Does GPT-5.6 Terra or GPT-6 Luna have a bigger context window?
They are effectively the same — 1.1M for GPT-5.6 Terra and 1.1M for GPT-6 Luna.
Do GPT-5.6 Terra and GPT-6 Luna support prompt caching?
Both publish a cached-input rate: $0.200 per million for GPT-5.6 Terra and $0.010 for GPT-6 Luna, against full input rates of $2.00 and $0.100. 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.