GPT-4o-mini vs GPT-5 Mini
Updated October 21, 2026. 23 benchmarks have a result for both. Coding is ranked on the Vibe Coding Index; every other board is shown as published.
Decision reading
Only GPT-5 Mini has a coding score, 34.2 on the Vibe Coding Index; GPT-4o-mini has none, so the two cannot be ranked on coding.
GPT-4o-mini has the edge where output tokens cost 3.3x less.
- Shared results
- 23
- GPT-4o-mini only
- 4
- GPT-5 Mini only
- 75
- Like-for-like categories
- 6 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
Only GPT-5 Mini has a coding score, so no call is made.
One side not measured
Intelligence
AA Intelligence Index
GPT-5 Mini
GPT-5 Mini leads, 20.6 against 6.7.
Same board, both measured
Reasoning
GPQA Diamond
GPT-5 Mini
GPT-5 Mini leads, 80.3% against 44.2%.
Same board, both measured
Math
AIME
GPT-5 Mini
GPT-5 Mini leads, 91.5% against 11.5%.
Same board, both measured
Knowledge
MMLU Pro
GPT-5 Mini
GPT-5 Mini leads, 82.2% against 62.7%.
Same board, both measured
Web design
Design Arena: websites
No call
Only GPT-5 Mini has a Design Arena: websites result, 1125.
Directional only
Long documents
Listed context window
GPT-5 Mini
GPT-5 Mini takes 400K tokens against 128K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
GPT-4o-mini
GPT-4o-mini $0.0004, GPT-5 Mini $0.0013 per turn.
List prices
Cost per solved task
One SWE-bench Verified task, solved
No call
Only GPT-5 Mini has the number, $0.08.
Directional only
At a glance
- Coding index
- GPT-4o-mini not benchmarked, GPT-5 Mini 34.2 from 2 benchmarks.
- Widest category
- Coding, 60.3 points apart on average over 2 shared benchmarks.
- Widest single gap
- AIME: GPT-4o-mini 11.5% against GPT-5 Mini 91.5%, 80.0 points apart on a 0 to 100 scale.
- Output price
- GPT-4o-mini $0.60 against GPT-5 Mini $2.00 per million output tokens, 3.3x apart.
- Context window
- GPT-4o-mini takes 128K tokens, GPT-5 Mini 400K.
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-mini | Bars | GPT-5 Mini | Ties |
|---|---|---|---|---|
| Coding | 0 | 2 | ||
| Intelligence | 0 | 2 | ||
| Reasoning | 0 | 5 | ||
| Math | 0 | 5 | ||
| Knowledge | 0 | 6 | ||
| General | 0 | 3 | ||
| All shared boards | 0 | 23 |
CodingLike-for-likeSix of these boards feed the Vibe Coding Index02
| Benchmark | GPT-4o-mini | GPT-5 Mini | Leader |
|---|---|---|---|
| SWE-bench Verified | Not measured | 59.8% | Only GPT-5 Mini measured |
| SWE-bench Multilingual | Not measured | 39.7% | Only GPT-5 Mini measured |
| AA Coding Index | 11.4 | Not measured | Only GPT-4o-mini measured |
| LiveCodeBench (Vals AI) | 26.4% | 86.6% | GPT-5 Mini |
| SWE-bench Verified (Vals AI) | Not measured | 60.8% | Only GPT-5 Mini measured |
| Vibe Code Bench (Vals AI) | Not measured | 14.2% | Only GPT-5 Mini measured |
| LiveCodeBench (Artificial Analysis run) | 23.4% | 83.8% | GPT-5 Mini |
| SciCode | Not measured | 39.0% | Only GPT-5 Mini measured |
| Terminal-Bench Hard (Artificial Analysis run) | Not measured | 33.3% | Only GPT-5 Mini measured |
| Terminal-Bench | Not measured | 34.8% | Only GPT-5 Mini measured |
| WeirdML | Not measured | 52.7% | Only GPT-5 Mini measured |
| LMArena Text: coding | Not measured | 1406 | Only GPT-5 Mini measured |
| LMArena Text: software and IT | Not measured | 1394 | Only GPT-5 Mini measured |
| Neither model has a result on the other 25 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index02
| Benchmark | GPT-4o-mini | GPT-5 Mini | Leader |
|---|---|---|---|
| AA Intelligence Index | 6.7 | 20.6 | GPT-5 Mini |
| Epoch Capabilities Index | 126.5 | 145.3 | GPT-5 Mini |
Agentic workDirectional onlyPublic boards, shown as published, kept out of the index2 boards, none shared
| Benchmark | GPT-4o-mini | GPT-5 Mini | Leader |
|---|---|---|---|
| τ²-Bench Telecom | Not measured | 71.1% | Only GPT-5 Mini measured |
| Vending-Bench 2 | Not measured | -$31 | Only GPT-5 Mini measured |
| Neither model has a result on the other 37 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index05
| Benchmark | GPT-4o-mini | GPT-5 Mini | Leader |
|---|---|---|---|
| GPQA Diamond | 44.2% | 80.3% | GPT-5 Mini |
| MMMU Pro (Vals AI) | 56.6% | 78.9% | GPT-5 Mini |
| GPQA Diamond (Artificial Analysis run) | 42.6% | 82.8% | GPT-5 Mini |
| Humanity's Last Exam (Artificial Analysis run) | 4.2% | 21.5% | GPT-5 Mini |
| GPQA Diamond (Epoch AI run) | Not measured | 75.0% | Only GPT-5 Mini measured |
| ARC-AGI | Not measured | 54.3% | Only GPT-5 Mini measured |
| ARC-AGI-2 | 0.0% | 4.4% | GPT-5 Mini |
| Chess puzzles | Not measured | 24.0% | Only GPT-5 Mini measured |
| Mystery game puzzles | Not measured | 10.0% | Only GPT-5 Mini measured |
| VPCT | Not measured | 40.2% | Only GPT-5 Mini measured |
| LMArena Text: hard prompts | Not measured | 1380 | Only GPT-5 Mini measured |
| LMArena Text: expert | Not measured | 1379 | Only GPT-5 Mini measured |
| LMArena Text: hard prompts in English | Not measured | 1383 | Only GPT-5 Mini measured |
| LMArena Vision: diagrams | Not measured | 1202 | Only GPT-5 Mini measured |
| LMArena Vision: homework | Not measured | 1210 | Only GPT-5 Mini measured |
| Neither model has a result on the other 6 boards here | |||
MathLike-for-likePublic boards, shown as published, kept out of the index05
| Benchmark | GPT-4o-mini | GPT-5 Mini | Leader |
|---|---|---|---|
| AIME | 11.5% | 91.5% | GPT-5 Mini |
| MATH 500 (Vals AI) | 72.6% | 94.8% | GPT-5 Mini |
| MGSM (Vals AI) | 86.2% | 92.6% | GPT-5 Mini |
| AA Math Index | 14.7 | 90.7 | GPT-5 Mini |
| AIME 2025 (Artificial Analysis run) | 14.7% | 90.7% | GPT-5 Mini |
| OTIS Mock AIME | Not measured | 86.7% | Only GPT-5 Mini measured |
| FrontierMath, tiers 1 to 3 | Not measured | 46.7% | Only GPT-5 Mini measured |
| FrontierMath, tier 4 | Not measured | 12.2% | Only GPT-5 Mini measured |
| ProofBench | Not measured | 9.0% | Only GPT-5 Mini measured |
| MATH level 5 | Not measured | 97.8% | Only GPT-5 Mini measured |
| GSM8K | 91.3% | Not measured | Only GPT-4o-mini measured |
| LMArena Text: math | Not measured | 1378 | Only GPT-5 Mini measured |
| LMArena Text: mathematical work | Not measured | 1380 | Only GPT-5 Mini measured |
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index06
| Benchmark | GPT-4o-mini | GPT-5 Mini | Leader |
|---|---|---|---|
| MMLU Pro | 62.7% | 82.2% | GPT-5 Mini |
| LegalBench (Vals AI) | Not measured | 81.8% | Only GPT-5 Mini measured |
| CaseLaw (Vals AI) | Not measured | 68.5% | Only GPT-5 Mini measured |
| CorpFin (Vals AI) | 45.5% | 60.2% | GPT-5 Mini |
| TaxEval (Vals AI) | 60.5% | 75.2% | GPT-5 Mini |
| MortgageTax (Vals AI) | 54.5% | 66.9% | GPT-5 Mini |
| MedQA (Vals AI) | 72.4% | 96.1% | GPT-5 Mini |
| MedCode (Vals AI) | Not measured | 43.0% | Only GPT-5 Mini measured |
| MMLU Pro (Artificial Analysis run) | 64.8% | 83.7% | GPT-5 Mini |
| SimpleQA Verified | Not measured | 21.6% | Only GPT-5 Mini measured |
| MMLU | 81.8% | Not measured | Only GPT-4o-mini measured |
| LMArena Text: science | Not measured | 1371 | Only GPT-5 Mini measured |
| LMArena Text: medicine and healthcare | Not measured | 1380 | Only GPT-5 Mini measured |
| LMArena Text: legal and government | Not measured | 1375 | Only GPT-5 Mini measured |
| LMArena Text: business and finance | Not measured | 1358 | Only GPT-5 Mini measured |
| Neither model has a result on the other 2 boards here | |||
Web designDirectional onlyPublic boards, shown as published, kept out of the index8 boards, none shared
| Benchmark | GPT-4o-mini | GPT-5 Mini | Leader |
|---|---|---|---|
| Design Arena: websites | Not measured | 1125 | Only GPT-5 Mini measured |
| Design Arena: UI components | Not measured | 1106 | Only GPT-5 Mini measured |
| Design Arena: game dev | Not measured | 1129 | Only GPT-5 Mini measured |
| Design Arena: data viz | Not measured | 1130 | Only GPT-5 Mini measured |
| Design Arena: 3D | Not measured | 1037 | Only GPT-5 Mini measured |
| Design Arena: all code categories | Not measured | 1115 | Only GPT-5 Mini measured |
| Design Arena: SVG | Not measured | 1091 | Only GPT-5 Mini measured |
| Design Arena: ASCII art | Not measured | 1124 | Only GPT-5 Mini measured |
| Neither model has a result on the other 1 board here | |||
GeneralLike-for-likePublic boards, shown as published, kept out of the index03
| Benchmark | GPT-4o-mini | GPT-5 Mini | Leader |
|---|---|---|---|
| SAGE (Vals AI) | Not measured | 43.0% | Only GPT-5 Mini measured |
| MedScribe (Vals AI) | Not measured | 80.6% | Only GPT-5 Mini measured |
| IFBench | 31.0% | 75.4% | GPT-5 Mini |
| Long context reasoning (AA-LCR) | Not measured | 72.3% | Only GPT-5 Mini measured |
| DTBench | 54.4% | 80.5% | GPT-5 Mini |
| LMCA | 10.4% | 34.2% | GPT-5 Mini |
| Fiction.LiveBench | Not measured | 69.4% | Only GPT-5 Mini measured |
| Creative writing (Lech Mazur) | Not measured | 83.1% | Only GPT-5 Mini measured |
| PIQA | 88.7% | Not measured | Only GPT-4o-mini measured |
| LMArena Text | Not measured | 1373 | Only GPT-5 Mini measured |
| LMArena Text: instruction following | Not measured | 1357 | Only GPT-5 Mini measured |
| LMArena Text: creative writing | Not measured | 1325 | Only GPT-5 Mini measured |
| LMArena Vision | Not measured | 1202 | Only GPT-5 Mini measured |
| LMArena Text: English | Not measured | 1379 | Only GPT-5 Mini measured |
| LMArena Text: non-English | Not measured | 1363 | Only GPT-5 Mini measured |
| LMArena Text: Chinese | Not measured | 1386 | Only GPT-5 Mini measured |
| LMArena Text: German | Not measured | 1366 | Only GPT-5 Mini measured |
| LMArena Text: Japanese | Not measured | 1341 | Only GPT-5 Mini measured |
| LMArena Text: Korean | Not measured | 1308 | Only GPT-5 Mini measured |
| LMArena Text: French | Not measured | 1386 | Only GPT-5 Mini measured |
| LMArena Text: Spanish | Not measured | 1354 | Only GPT-5 Mini measured |
| LMArena Text: Russian | Not measured | 1362 | Only GPT-5 Mini measured |
| LMArena Text: Polish | Not measured | 1378 | Only GPT-5 Mini measured |
| LMArena Text: multi-turn | Not measured | 1363 | Only GPT-5 Mini measured |
| LMArena Text: longer queries | Not measured | 1355 | Only GPT-5 Mini measured |
| LMArena Text: writing and language | Not measured | 1344 | Only GPT-5 Mini measured |
| LMArena Text: entertainment and media | Not measured | 1340 | Only GPT-5 Mini measured |
| LMArena Vision: English | Not measured | 1216 | Only GPT-5 Mini measured |
| LMArena Vision: Chinese | Not measured | 1214 | Only GPT-5 Mini measured |
| LMArena Vision: reading text | Not measured | 1199 | Only GPT-5 Mini measured |
| LMArena Vision: humor | Not measured | 1205 | Only GPT-5 Mini measured |
| LMArena Vision: captioning | Not measured | 1217 | Only GPT-5 Mini measured |
| LMArena Vision: recognizing things | Not measured | 1226 | Only GPT-5 Mini measured |
| LMArena Vision: creative writing | Not measured | 1181 | Only GPT-5 Mini measured |
| Neither model has a result on the other 12 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | GPT-4o-mini | GPT-5 Mini | 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 costs less
Repository review
50K input + 3K output tokens
GPT-4o-mini costs less
Agent loop
200K input + 10K output tokens
GPT-4o-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-4o-mini | OpenAI GPT-5 Mini |
|---|---|---|
| Maker | OpenAI | OpenAI |
| Weights | No public weights listed | No public weights listed |
| Released | July 18, 2024 | August 7, 2025 |
| Context window | 128K | 400K |
| Input $/Mtok | $0.15 | $0.25 |
| Output $/Mtok | $0.60 | $2.00 |
| Coding index | Not benchmarked | 34.2 |
| Independent measurements behind it | 0 | 2 |
| Cost per solved task | Not computable | $0.08 |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is GPT-4o-mini better than GPT-5 Mini for coding?
Only GPT-5 Mini has a coding score, 34.2 on the Vibe Coding Index; GPT-4o-mini has none, so the two cannot be ranked on coding. GPT-4o-mini has the edge where output tokens cost 3.3x less.
Which is cheaper, GPT-4o-mini or GPT-5 Mini?
GPT-4o-mini costs $0.15 per million input tokens and $0.60 per million output tokens; GPT-5 Mini costs $0.25 and $2.00. Cost per solved task is known for GPT-5 Mini only.
Which has the bigger context window, GPT-4o-mini or GPT-5 Mini?
GPT-5 Mini, with 400K tokens against 128K.
How many benchmarks is the GPT-4o-mini vs GPT-5 Mini comparison based on?
23 benchmarks have a result for both models as of October 21, 2026. GPT-4o-mini's coding index rests on 0 independent benchmarks and GPT-5 Mini's on 2. Where only one model has a result, the page says so instead of naming a winner.