GPT-4o vs GPT-4o-mini (2024-07-18)
Updated October 21, 2026. 1 benchmarks have a result for both. Coding is ranked on the Vibe Coding Index; every other board is shown as published.
Decision reading
GPT-4o scores 38.8 and GPT-4o-mini (2024-07-18) 3.6 on the Vibe Coding Index, but no coding benchmark measured both, so the gap is directional, not a ranking.
Pick GPT-4o when the benchmark that matters is MMLU, where it leads; pick GPT-4o-mini (2024-07-18) when output tokens cost 16.7x less.
- Shared results
- 1
- GPT-4o only
- 25
- GPT-4o-mini (2024-07-18) only
- 45
- 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, four public coding benchmarks
No call
38.8 against 3.6, from different benchmarks with none in common.
Directional only
Web design
Design Arena: websites
No call
Only GPT-4o has a Design Arena: websites result, 831.
Directional only
Long documents
Listed context window
No call
Both take 128K tokens.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
GPT-4o-mini (2024-07-18)
GPT-4o $0.0075, GPT-4o-mini (2024-07-18) $0.0004 per turn.
List prices
At a glance
- Coding index
- GPT-4o 38.8 from 1 benchmark, GPT-4o-mini (2024-07-18) 3.6 from 1 benchmark.
- Widest category
- Knowledge, 11.4 points apart on average over 1 shared benchmark.
- Widest single gap
- MMLU: GPT-4o 88.1% against GPT-4o-mini (2024-07-18) 76.7%, 11.4 points apart on a 0 to 100 scale.
- Output price
- GPT-4o $10.00 against GPT-4o-mini (2024-07-18) $0.60 per million output tokens, 16.7x apart.
- Context window
- Both take 128K 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-4o | Bars | GPT-4o-mini (2024-07-18) | Ties |
|---|---|---|---|---|
| Knowledge | 1 | 0 | ||
| All shared boards | 1 | 0 |
CodingDirectional onlyFour of these boards feed the Vibe Coding Index10 boards, none shared
| Benchmark | GPT-4o | GPT-4o-mini (2024-07-18) | Leader |
|---|---|---|---|
| Aider polyglot | Not measured | 3.6% | Only GPT-4o-mini (2024-07-18) measured |
| SWE-bench Verified | 38.8% | Not measured | Only GPT-4o measured |
| SWE-bench Lite | 38.0% | Not measured | Only GPT-4o measured |
| SWE-bench (full test set) | 18.8% | Not measured | Only GPT-4o measured |
| SWE-bench Multimodal | 30.4% | Not measured | Only GPT-4o measured |
| LiveCodeBench (Artificial Analysis run) | 30.9% | Not measured | Only GPT-4o measured |
| Terminal-Bench Hard (Artificial Analysis run) | 8.3% | Not measured | Only GPT-4o measured |
| WeirdML | Not measured | 11.8% | Only GPT-4o-mini (2024-07-18) measured |
| LMArena Text: coding | Not measured | 1290 | Only GPT-4o-mini (2024-07-18) measured |
| LMArena Text: software and IT | Not measured | 1291 | Only GPT-4o-mini (2024-07-18) measured |
| Neither model has a result on the other 28 boards here | |||
IntelligenceNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | GPT-4o | GPT-4o-mini (2024-07-18) | Leader |
|---|---|---|---|
| Neither model has a result on 2 boards here | |||
Agentic workDirectional onlyPublic boards, shown as published, kept out of the index3 boards, none shared
| Benchmark | GPT-4o | GPT-4o-mini (2024-07-18) | Leader |
|---|---|---|---|
| τ²-Bench Telecom | 25.1% | Not measured | Only GPT-4o measured |
| GDPval | 9.9% | Not measured | Only GPT-4o measured |
| BALROG | Not measured | 17.4% | Only GPT-4o-mini (2024-07-18) measured |
| Neither model has a result on the other 36 boards here | |||
ReasoningDirectional onlyPublic boards, shown as published, kept out of the index12 boards, none shared
| Benchmark | GPT-4o | GPT-4o-mini (2024-07-18) | Leader |
|---|---|---|---|
| GPQA Diamond (Artificial Analysis run) | 54.3% | Not measured | Only GPT-4o measured |
| Humanity's Last Exam (Artificial Analysis run) | 2.4% | Not measured | Only GPT-4o measured |
| GPQA Diamond (Epoch AI run) | Not measured | 37.7% | Only GPT-4o-mini (2024-07-18) measured |
| ARC-AGI | 4.5% | Not measured | Only GPT-4o measured |
| ARC-AGI-2 | 0.0% | Not measured | Only GPT-4o measured |
| SimpleBench | Not measured | 10.7% | Only GPT-4o-mini (2024-07-18) measured |
| Chess puzzles | Not measured | 3.0% | Only GPT-4o-mini (2024-07-18) measured |
| Mystery game puzzles | Not measured | 12.0% | Only GPT-4o-mini (2024-07-18) measured |
| VPCT | Not measured | 34.0% | Only GPT-4o-mini (2024-07-18) measured |
| LMArena Text: hard prompts | Not measured | 1267 | Only GPT-4o-mini (2024-07-18) measured |
| LMArena Text: expert | Not measured | 1234 | Only GPT-4o-mini (2024-07-18) measured |
| LMArena Text: hard prompts in English | Not measured | 1278 | Only GPT-4o-mini (2024-07-18) measured |
| Neither model has a result on the other 9 boards here | |||
MathDirectional onlyPublic boards, shown as published, kept out of the index7 boards, none shared
| Benchmark | GPT-4o | GPT-4o-mini (2024-07-18) | Leader |
|---|---|---|---|
| AA Math Index | 6.0 | Not measured | Only GPT-4o measured |
| AIME 2025 (Artificial Analysis run) | 6.0% | Not measured | Only GPT-4o measured |
| OTIS Mock AIME | Not measured | 6.9% | Only GPT-4o-mini (2024-07-18) measured |
| FrontierMath, tiers 1 to 3 | Not measured | 0.7% | Only GPT-4o-mini (2024-07-18) measured |
| MATH level 5 | Not measured | 52.6% | Only GPT-4o-mini (2024-07-18) measured |
| LMArena Text: math | Not measured | 1267 | Only GPT-4o-mini (2024-07-18) measured |
| LMArena Text: mathematical work | Not measured | 1271 | Only GPT-4o-mini (2024-07-18) measured |
| Neither model has a result on the other 6 boards here | |||
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index10
| Benchmark | GPT-4o | GPT-4o-mini (2024-07-18) | Leader |
|---|---|---|---|
| MMLU Pro (Artificial Analysis run) | 74.8% | Not measured | Only GPT-4o measured |
| SimpleQA Verified | Not measured | 8.3% | Only GPT-4o-mini (2024-07-18) measured |
| MMLU | 88.1% | 76.7% | GPT-4o |
| GeoBench | Not measured | 64.0% | Only GPT-4o-mini (2024-07-18) measured |
| LMArena Text: science | Not measured | 1286 | Only GPT-4o-mini (2024-07-18) measured |
| LMArena Text: medicine and healthcare | Not measured | 1282 | Only GPT-4o-mini (2024-07-18) measured |
| LMArena Text: legal and government | Not measured | 1305 | Only GPT-4o-mini (2024-07-18) measured |
| LMArena Text: business and finance | Not measured | 1265 | Only GPT-4o-mini (2024-07-18) measured |
| Neither model has a result on the other 9 boards here | |||
Web designDirectional onlyPublic boards, shown as published, kept out of the index6 boards, none shared
| Benchmark | GPT-4o | GPT-4o-mini (2024-07-18) | Leader |
|---|---|---|---|
| Design Arena: websites | 831 | Not measured | Only GPT-4o measured |
| Design Arena: UI components | 885 | Not measured | Only GPT-4o measured |
| Design Arena: game dev | 906 | Not measured | Only GPT-4o measured |
| Design Arena: data viz | 858 | Not measured | Only GPT-4o measured |
| Design Arena: 3D | 869 | Not measured | Only GPT-4o measured |
| Design Arena: all code categories | 861 | Not measured | Only GPT-4o measured |
| Neither model has a result on the other 3 boards here | |||
GeneralDirectional onlyPublic boards, shown as published, kept out of the index25 boards, none shared
| Benchmark | GPT-4o | GPT-4o-mini (2024-07-18) | Leader |
|---|---|---|---|
| IFBench | 34.3% | Not measured | Only GPT-4o measured |
| Long context reasoning (AA-LCR) | 49.3% | Not measured | Only GPT-4o measured |
| DTBench | 64.5% | Not measured | Only GPT-4o measured |
| LMCA | 16.6% | Not measured | Only GPT-4o measured |
| Creative writing (Lech Mazur) | Not measured | 67.2% | Only GPT-4o-mini (2024-07-18) measured |
| LMArena Text | Not measured | 1286 | Only GPT-4o-mini (2024-07-18) measured |
| LMArena Text: instruction following | Not measured | 1258 | Only GPT-4o-mini (2024-07-18) measured |
| LMArena Text: creative writing | Not measured | 1268 | Only GPT-4o-mini (2024-07-18) measured |
| LMArena Vision | Not measured | 1066 | Only GPT-4o-mini (2024-07-18) measured |
| LMArena Text: English | Not measured | 1301 | Only GPT-4o-mini (2024-07-18) measured |
| LMArena Text: non-English | Not measured | 1266 | Only GPT-4o-mini (2024-07-18) measured |
| LMArena Text: Chinese | Not measured | 1265 | Only GPT-4o-mini (2024-07-18) measured |
| LMArena Text: German | Not measured | 1272 | Only GPT-4o-mini (2024-07-18) measured |
| LMArena Text: Japanese | Not measured | 1216 | Only GPT-4o-mini (2024-07-18) measured |
| LMArena Text: Korean | Not measured | 1195 | Only GPT-4o-mini (2024-07-18) measured |
| LMArena Text: French | Not measured | 1297 | Only GPT-4o-mini (2024-07-18) measured |
| LMArena Text: Spanish | Not measured | 1276 | Only GPT-4o-mini (2024-07-18) measured |
| LMArena Text: Russian | Not measured | 1275 | Only GPT-4o-mini (2024-07-18) measured |
| LMArena Text: Polish | Not measured | 1244 | Only GPT-4o-mini (2024-07-18) measured |
| LMArena Text: multi-turn | Not measured | 1285 | Only GPT-4o-mini (2024-07-18) measured |
| LMArena Text: longer queries | Not measured | 1289 | Only GPT-4o-mini (2024-07-18) measured |
| LMArena Text: writing and language | Not measured | 1282 | Only GPT-4o-mini (2024-07-18) measured |
| LMArena Text: entertainment and media | Not measured | 1253 | Only GPT-4o-mini (2024-07-18) measured |
| LMArena Vision: English | Not measured | 1072 | Only GPT-4o-mini (2024-07-18) measured |
| LMArena Vision: Chinese | Not measured | 1033 | Only GPT-4o-mini (2024-07-18) measured |
| Neither model has a result on the other 21 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | GPT-4o | GPT-4o-mini (2024-07-18) | Leader |
|---|---|---|---|
| Neither model has a result on 5 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-4o-mini (2024-07-18) costs less
Repository review
50K input + 3K output tokens
GPT-4o-mini (2024-07-18) costs less
Agent loop
200K input + 10K output tokens
GPT-4o-mini (2024-07-18) 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-4o | OpenAI GPT-4o-mini (2024-07-18) |
|---|---|---|
| Maker | OpenAI | OpenAI |
| Weights | No public weights listed | No public weights listed |
| Released | May 13, 2024 | July 18, 2024 |
| Context window | 128K | 128K |
| Input $/Mtok | $2.50 | $0.15 |
| Output $/Mtok | $10.00 | $0.60 |
| Coding index | 38.8 | 3.6 |
| Independent measurements behind it | 1 | 1 |
| Cost per solved task | Not computable | Not computable |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is GPT-4o better than GPT-4o-mini (2024-07-18) for coding?
GPT-4o scores 38.8 and GPT-4o-mini (2024-07-18) 3.6 on the Vibe Coding Index, but no coding benchmark measured both, so the gap is directional, not a ranking. Pick GPT-4o when the benchmark that matters is MMLU, where it leads; pick GPT-4o-mini (2024-07-18) when output tokens cost 16.7x less.
Which is cheaper, GPT-4o or GPT-4o-mini (2024-07-18)?
GPT-4o costs $2.50 per million input tokens and $10.00 per million output tokens; GPT-4o-mini (2024-07-18) costs $0.15 and $0.60. Cost per solved task is known for neither of them.
Which has the bigger context window, GPT-4o or GPT-4o-mini (2024-07-18)?
Neither: both take 128K tokens.
How many benchmarks is the GPT-4o vs GPT-4o-mini (2024-07-18) comparison based on?
1 benchmarks have a result for both models as of October 21, 2026. GPT-4o's coding index rests on 1 independent benchmark and GPT-4o-mini (2024-07-18)'s on 1. Where only one model has a result, the page says so instead of naming a winner.