The AI arena is free today

Open Superagent

GPT-5.4 mini vs GPT-5.6 Luna

GPT-5.6 Luna leads the LLM Stats Score 45.1 to 30.1. GPT-5.6 Luna is 3.8x cheaper per token.

OpenAI · OpenAI · Updated for 2026

Which is better?

GPT-5.6 Luna leads the overall LLM Stats Score 45.1 to 30.1, ranking #32 overall.

In the 5 individual benchmarks reported for both models, GPT-5.6 Luna wins 5; this is a narrower head-to-head signal than the composite indexes.

On price, GPT-5.6 Luna is roughly 3.8x cheaper per token on a blended 3:1 input/output basis, which adds up quickly at production volume.

GPT-5.6 Luna also accepts a larger context window (1,050,000 input tokens), making it the stronger choice for long documents and large codebases.

Based on current LLM Stats indexes, shared benchmarks, pricing, and model metadata for 2026.

Choose GPT-5.4 mini

  • you want predictable pricing at $0.75/M input and $4.50/M output

Choose GPT-5.6 Luna

  • overall performance matters — it scores 45.1 and ranks #32 on LLM Stats
  • your work emphasizes reasoning and coding — it leads those capability indexes
  • you value its reported benchmark strengths — it wins 5 of 5 exact shared results
  • cost matters — it's about 3.8x cheaper per token
  • you process long inputs — it offers a 1,050,000 token context window
  • you want the most recent training data — it shipped Jul 2026

At a glance

The differences that matter most.

Core performance indexes
30.1
#120
45.1
#32
31.9
#105
44.2
#36
22.1
#82
36.3
#21
19.4
#63
31.7
#28
Cost, coverage & limits
Benchmark wins
0 of 5
5 of 5
Input price
$0.75 / M
$0.20 / M
Output price
$4.50 / M
$1.20 / M
Context window
400,000
1,050,000

Capability indexes

Additional strengths measured across groups of related public benchmarks

4 shared
Index
GPT-5.4 mini
GPT-5.6 Luna
20.2#69
25.0#48
16.5#80
25.9#32
7.8#90
21.2#24
22.8#58
26.0#43
Conservative TrueSkill rating · higher is betterHow scores work

Individual benchmarks

15 reported for GPT-5.4 mini · 45 for GPT-5.6 Luna

5 shared

GPT-5.4 mini outperforms in 0 benchmarks, while GPT-5.6 Luna is better at 5 benchmarks (GPQA, MMMU-Pro, MRCR v2 (8-needle), SWE-Bench Pro, Toolathlon).

GPT-5.6 Luna significantly outperforms across most benchmarks.

Sun Sep 13 2026 • llm-stats.com

Human preference

Blind head-to-head votes and playground preference scores

Pricing Analysis

Price comparison per million tokens

GPT-5.6 Luna costs less

For input processing, GPT-5.4 mini ($0.75/1M tokens) is 3.8x more expensive than GPT-5.6 Luna ($0.20/1M tokens).

For output processing, GPT-5.4 mini ($4.50/1M tokens) is 3.8x more expensive than GPT-5.6 Luna ($1.20/1M tokens).

In conclusion, GPT-5.4 mini is more expensive than GPT-5.6 Luna.*

* Using a 3:1 ratio of input to output tokens

Lowest available price from all providers
Sun Sep 13 2026 • llm-stats.com
OpenAI
GPT-5.4 mini
Input tokens$0.75
Output tokens$4.50
Best providerOpenAI
OpenAI
GPT-5.6 Luna
Input tokens$0.20
Output tokens$1.20
Best providerOpenAI
Notice missing or incorrect data?Start an Issue

Context Window

Maximum input and output token capacity

GPT-5.6 Luna accepts 1,050,000 input tokens compared to GPT-5.4 mini's 400,000 tokens. Both models can generate responses up to 128,000 tokens.

OpenAI
GPT-5.4 mini
Input400,000 tokens
Output128,000 tokens
OpenAI
GPT-5.6 Luna
Input1,050,000 tokens
Output128,000 tokens
Sun Sep 13 2026 • llm-stats.com

Input capabilities

Documented input modalities across available providers

Both GPT-5.4 mini and GPT-5.6 Luna support multimodal inputs.

They are both capable of processing various types of data, offering versatility in application.

GPT-5.4 mini

Text
Images
Audio
Video

GPT-5.6 Luna

Text
Images
Audio
Video

License

Usage and distribution terms

Both models are licensed under proprietary licenses.

Both models have usage restrictions defined by their respective organizations.

GPT-5.4 mini

Proprietary

Closed source

GPT-5.6 Luna

Proprietary

Closed source

Release Timeline

When each model was launched

GPT-5.4 mini was released on 2026-03-17, while GPT-5.6 Luna was released on 2026-07-09.

GPT-5.6 Luna is 4 months newer than GPT-5.4 mini.

GPT-5.4 mini

Mar 17, 2026

6 months ago

GPT-5.6 Luna

Jul 9, 2026

2 months ago

3mo newer

Knowledge Cutoff

When training data ends

GPT-5.4 mini has a knowledge cutoff of 2025-08-31, while GPT-5.6 Luna has a cutoff of 2026-02-16.

GPT-5.6 Luna has more recent training data (up to 2026-02-16), making it potentially better informed about events through that date compared to GPT-5.4 mini (2025-08-31).

GPT-5.4 mini

Aug 2025

GPT-5.6 Luna

Feb 2026

6 mo newer

Provider Availability

GPT-5.4 mini is available from OpenAI. GPT-5.6 Luna is available from OpenAI.

GPT-5.4 mini

openai logo
OpenAI
Input Price:Input: $0.75/1MOutput Price:Output: $4.50/1M

GPT-5.6 Luna

openai logo
OpenAI
Input Price:Input: $0.20/1MOutput Price:Output: $1.20/1M
* Prices shown are per million tokens

Outputs Comparison

Notice missing or incorrect data?Start an Issue discussion

Judge for yourself.

Run your own prompts against GPT-5.4 mini and GPT-5.6 Luna side-by-side, then vote on the output you prefer.

GPT-5.4 mini
✓ Preferred
GPT-5.6 Luna
Open in Playground

FAQ

Common questions about GPT-5.4 mini vs GPT-5.6 Luna.

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

GPT-5.6 Luna leads the LLM Stats Score 45.1 to 30.1. GPT-5.4 mini is made by OpenAI and GPT-5.6 Luna is made by OpenAI. The best choice depends on your use case — compare their capability indexes, individual benchmarks, pricing, and limits above.

How does GPT-5.4 mini compare to GPT-5.6 Luna in benchmarks?

GPT-5.4 mini scores Tau2 Telecom: 93.4%, GPQA: 88.0%, OmniDocBench 1.5: 87.4%, MMMU-Pro: 76.6%, Graphwalks BFS <128k: 76.3%. GPT-5.6 Luna scores Connectors: 99.9%, HealthBench Consensus: 95.1%, GPQA: 92.3%, Search and Function-Calling: 89.7%, Capture-the-Flag Challenges (Internal): 85.2%.

Is GPT-5.4 mini cheaper than GPT-5.6 Luna?

GPT-5.6 Luna is 3.8x cheaper for input tokens. GPT-5.4 mini costs $0.75/M input and $4.50/M output via openai. GPT-5.6 Luna costs $0.20/M input and $1.20/M output via openai.

What are the context window sizes for GPT-5.4 mini and GPT-5.6 Luna?

GPT-5.4 mini supports 400K tokens and GPT-5.6 Luna supports 1.1M tokens. A larger context window lets you process longer documents, conversations, or codebases in a single request.

What are the main differences between GPT-5.4 mini and GPT-5.6 Luna?

Key differences include LLM Stats Score (30.1 vs 45.1), context window (400K vs 1.1M), input pricing ($0.75 vs $0.20/M). See the full comparison above for benchmark-by-benchmark results.