// head_to_head

GPT-5.4 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.

OpenRouter + LiveBenchAll comparisonsFull leaderboard

GPT-5.4 scores higher, GPT-5.6 Luna costs less — it depends on your workload.

GPT-5.4 is ahead by 4.4 points overall, and GPT-5.6 Luna lists 13× cheaper per blended million tokens. Whether 4.4 points is worth that depends on how much a wrong answer costs you. GPT-5.6 Luna also leads on measured cost per point of capability, at $0.0911 per point.

openai

GPT-5.4

Blended / 1M
$5.63
Context
1.1M
Released
Mar 5, 2026
Overall score
78.0
reasoningtool callingimage inputfile inputprompt caching

openai

GPT-5.6 Luna

Blended / 1M
$0.450
Context
1.1M
Released
Jul 9, 2026
Overall score
73.6
reasoningtool callingfile inputimage inputprompt caching

Specs and pricing

MetricGPT-5.4GPT-5.6 Luna
LiveBench overall

Mean of the seven LiveBench category scores, 0–100. Higher is better.

78.0win73.6
Cost per point

Measured benchmark spend divided by overall score — dollars per point of capability.

$0.2198$0.0911win
Blended price / 1M

3:1 input:output mix, the usual shape of production traffic.

$5.63$0.450win
Input price / 1M$2.50$0.200win
Output price / 1M$15.00$1.20win
Cached input / 1M

Price of an input token served from the prompt cache, where the provider publishes one.

$0.250$0.020win
Context window1.1M1.1M
Max output tokens128K128K

Benchmarks by category

An overall score averages away the thing you probably care about. These are the seven LiveBench categories scored separately — GPT-5.4 on top, GPT-5.6 Luna below, both out of 100.

Agentic coding
53.8
48.4
Coding
77.5
82.9
Reasoning
88.1
85.6
Mathematics
94.1
87.2
Data analysis
79.3
78.0
Language
82.6
72.6
Instruction following
70.2
60.1

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.

WorkloadGPT-5.4GPT-5.6 Luna
Support chatbot

1.2K in / 400 out × 200K requests

$1638.00/mo$131.04/mo
RAG assistant

8K in / 600 out × 100K requests

$2000.00/mo$160.00/mo
Coding agent

40K in / 4K out × 20K requests

$1940.00/mo$155.20/mo
Document extraction

20K in / 1.5K out × 50K requests

$3512.50/mo$281.00/mo
Bulk classification

500 in / 20 out × 5M requests

$6625.00/mo$530.00/mo
Run these two through the cost calculator

Which should you pick?

You are running this at volume

GPT-5.6 Luna

Lowest measured cost per point of capability at $0.0911 per point — the gap compounds with every request.

Quality matters more than the bill

GPT-5.4

Highest overall LiveBench score of the two at 78.0.

The workload is coding or agentic work

GPT-5.4

Leads on agentic coding — 53.8 against 48.4.

GPT-5.4 vs GPT-5.6 Luna FAQ

Which is better, GPT-5.4 or GPT-5.6 Luna?

GPT-5.4 scores higher, GPT-5.6 Luna costs less — it depends on your workload. GPT-5.4 is ahead by 4.4 points overall, and GPT-5.6 Luna lists 13× cheaper per blended million tokens. Whether 4.4 points is worth that depends on how much a wrong answer costs you. GPT-5.6 Luna also leads on measured cost per point of capability, at $0.0911 per point.

Is GPT-5.4 cheaper than GPT-5.6 Luna?

GPT-5.6 Luna is cheaper. On a 3:1 input:output blend, GPT-5.4 lists at $5.63 per million tokens and GPT-5.6 Luna at $0.450 — GPT-5.6 Luna is 13× cheaper. Input and output are priced separately — GPT-5.4 charges $2.50 in and $15.00 out, GPT-5.6 Luna charges $0.200 and $1.20 — so the model that looks cheaper flips depending on how output-heavy your workload is.

GPT-5.4 vs GPT-5.6 Luna: which scores higher on benchmarks?

GPT-5.4 scores 78.0 and GPT-5.6 Luna scores 73.6 overall on LiveBench, the mean of its seven categories. That is a 4.4-point lead for GPT-5.4. 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-5.4 or GPT-5.6 Luna?

GPT-5.6 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-5.4 works out at $0.2198 per point and GPT-5.6 Luna at $0.0911.

Does GPT-5.4 or GPT-5.6 Luna have a bigger context window?

They are effectively the same — 1.1M for GPT-5.4 and 1.1M for GPT-5.6 Luna.

Do GPT-5.4 and GPT-5.6 Luna support prompt caching?

Both publish a cached-input rate: $0.250 per million for GPT-5.4 and $0.020 for GPT-5.6 Luna, against full input rates of $2.50 and $0.200. 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.
  • ScoresLiveBench 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.