GPT-5 Image vs GPT-5 Image Mini
Updated October 21, 2026. 3 benchmarks have a result for both. Coding is ranked on the Vibe Coding Index; every other board is shown as published.
Decision reading
Neither model has a coding score yet, so the two cannot be ranked on coding.
GPT-5 Image has the edge where the benchmark that matters is Design Arena: logos, where it leads.
- Shared results
- 3
- GPT-5 Image only
- 0
- GPT-5 Image Mini only
- 0
- Like-for-like categories
- 1 of 9
Shared results can support a head-to-head reading. Results only one model has describe coverage, not superiority.
Which one for your work
Each card is decided by one number both models carry. Where only one has it, the card says so and makes no call.
Coding
Vibe Coding Index, six public coding benchmarks
No call
Neither has a coding score yet.
One side not measured
Image generation
Design Arena: images
GPT-5 Image
GPT-5 Image leads, 1191 against 1184.
Same board, both measured
Long documents
Listed context window
No call
Both take 400K tokens.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
GPT-5 Image Mini
GPT-5 Image $0.015, GPT-5 Image Mini $0.0035 per turn.
List prices
At a glance
- Coding index
- GPT-5 Image not benchmarked, GPT-5 Image Mini not benchmarked.
- Widest category
- Image generation, 0.9 points apart on average over 3 shared benchmarks.
- Widest single gap
- Design Arena: logos: GPT-5 Image 1202 against GPT-5 Image Mini 1209, 0.9 points apart on a 0 to 100 scale.
- Output price
- GPT-5 Image $10.00 against GPT-5 Image Mini $2.00 per million output tokens, 5.0x apart.
- Context window
- Both take 400K tokens.
Benchmark by benchmark
First the score: boards each model leads, per category, where both have a result. Then every board, a category to a fold; bars are each result on a 0 to 100 scale, so compare the two in a row, not one row with another.
| Category | GPT-5 Image | Bars | GPT-5 Image Mini | Ties |
|---|---|---|---|---|
| Image generation | 2 | 1 | ||
| All shared boards | 2 | 1 |
CodingNot comparableSix of these boards feed the Vibe Coding Index0 boards, none shared
| Benchmark | GPT-5 Image | GPT-5 Image Mini | Leader |
|---|---|---|---|
| Neither model has a result on 38 boards here | |||
IntelligenceNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | GPT-5 Image | GPT-5 Image Mini | Leader |
|---|---|---|---|
| Neither model has a result on 2 boards here | |||
Agentic workNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | GPT-5 Image | GPT-5 Image Mini | Leader |
|---|---|---|---|
| Neither model has a result on 39 boards here | |||
ReasoningNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | GPT-5 Image | GPT-5 Image Mini | Leader |
|---|---|---|---|
| Neither model has a result on 21 boards here | |||
MathNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | GPT-5 Image | GPT-5 Image Mini | Leader |
|---|---|---|---|
| Neither model has a result on 13 boards here | |||
KnowledgeNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | GPT-5 Image | GPT-5 Image Mini | Leader |
|---|---|---|---|
| Neither model has a result on 17 boards here | |||
Web designNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | GPT-5 Image | GPT-5 Image Mini | Leader |
|---|---|---|---|
| Neither model has a result on 9 boards here | |||
GeneralNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | GPT-5 Image | GPT-5 Image Mini | Leader |
|---|---|---|---|
| Neither model has a result on 46 boards here | |||
Image generationLike-for-likePublic boards, shown as published, kept out of the index21
| Benchmark | GPT-5 Image | GPT-5 Image Mini | Leader |
|---|---|---|---|
| Design Arena: images | 1191 | 1184 | GPT-5 Image |
| Design Arena: graphic design | 1172 | 1165 | GPT-5 Image |
| Design Arena: logos | 1202 | 1209 | GPT-5 Image Mini |
| Neither model has a result on the other 2 boards here | |||
What each workload costs
Three fixed token mixes at each model's listed price, so per-token rates become a bill.
Chat turn
1K input + 500 output tokens
GPT-5 Image Mini costs less
Repository review
50K input + 3K output tokens
GPT-5 Image Mini costs less
Agent loop
200K input + 10K output tokens
GPT-5 Image Mini costs less
Listed OpenRouter rates, without cache or batch discounts. A workload that does not fit a model's context window would need splitting.
Specification differences
The leading value in a row is marked; a row with a missing value names no leader. Our two rows are marked in red.
| Specification | OpenAI GPT-5 Image | OpenAI GPT-5 Image Mini |
|---|---|---|
| Maker | OpenAI | OpenAI |
| Weights | No public weights listed | No public weights listed |
| Released | October 14, 2025 | October 16, 2025 |
| Context window | 400K | 400K |
| Input $/Mtok | $10.00 | $2.50 |
| Output $/Mtok | $10.00 | $2.00 |
| Coding index | Not benchmarked | Not benchmarked |
| Independent measurements behind it | 0 | 0 |
| Cost per solved task | Not computable | Not computable |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is GPT-5 Image better than GPT-5 Image Mini for coding?
Neither model has a coding score yet, so the two cannot be ranked on coding. GPT-5 Image has the edge where the benchmark that matters is Design Arena: logos, where it leads.
Which is cheaper, GPT-5 Image or GPT-5 Image Mini?
GPT-5 Image costs $10.00 per million input tokens and $10.00 per million output tokens; GPT-5 Image Mini costs $2.50 and $2.00. Cost per solved task is known for neither of them.
Which has the bigger context window, GPT-5 Image or GPT-5 Image Mini?
Neither: both take 400K tokens.
How many benchmarks is the GPT-5 Image vs GPT-5 Image Mini comparison based on?
3 benchmarks have a result for both models as of October 21, 2026. GPT-5 Image's coding index rests on 0 independent benchmarks and GPT-5 Image Mini's on 0. Where only one model has a result, the page says so instead of naming a winner.