GPT-4o-mini vs GPT-5 Nano
GPT-5 Nano leads GPT-4o-mini on the Artificial Analysis Intelligence Index, 13.0 to 6.7, and GPT-5 Nano costs 1.5x less per output token ($0.40 vs $0.60 per million). Updated October 21, 2026; 23 benchmarks have a result for both.
GPT-4o-mini or GPT-5 Nano: which to pick
Neither model has a coding score yet, so the two cannot be ranked on coding.
Pick GPT-4o-mini for work measured by LiveCodeBench (Vals AI) or LiveCodeBench (Artificial Analysis run), where it leads.
- Shared results
- 23
- GPT-4o-mini only
- 6
- GPT-5 Nano only
- 64
- Like-for-like categories
- 6 of 9
Only benchmarks that tested both models count toward a pick; a result only one model has is shown but not compared.
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
Intelligence
AA Intelligence Index
GPT-5 Nano
GPT-5 Nano leads, 13.0 against 6.7.
Same board, both measured
Reasoning
GPQA Diamond
GPT-5 Nano
GPT-5 Nano leads, 63.4% against 44.2%.
Same board, both measured
Math
AIME
GPT-5 Nano
GPT-5 Nano leads, 81.2% against 11.5%.
Same board, both measured
Knowledge
MMLU Pro
GPT-5 Nano
GPT-5 Nano leads, 76.1% against 62.7%.
Same board, both measured
Web design
Design Arena: websites
No call
Only GPT-5 Nano has a Design Arena: websites result, 1101.
Directional only
Long documents
Listed context window
GPT-5 Nano
GPT-5 Nano takes 400K tokens against 128K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
GPT-5 Nano
GPT-4o-mini $0.0004, GPT-5 Nano $0.0003 per turn.
List prices
Cost per solved task
One SWE-bench Verified task, solved
No call
Only GPT-5 Nano has the number, $0.109.
Directional only
At a glance
- Coding index
- GPT-4o-mini not benchmarked, GPT-5 Nano not benchmarked.
- Widest category
- Coding, 49.6 points apart on average over 2 shared benchmarks.
- Widest single gap
- AIME: GPT-4o-mini 11.5% against GPT-5 Nano 81.2%, 69.7 points apart on a 0 to 100 scale.
- Output price
- GPT-4o-mini $0.60 against GPT-5 Nano $0.40 per million output tokens, 1.5x apart.
- Context window
- GPT-4o-mini takes 128K tokens, GPT-5 Nano 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 Nano | Ties |
|---|---|---|---|---|
| Coding | 0 | 2 | ||
| Intelligence | 0 | 2 | ||
| Reasoning | 0 | 6 | ||
| Math | 0 | 5 | ||
| Knowledge | 1 | 4 | ||
| General | 1 | 2 | ||
| All shared boards | 2 | 21 |
CodingLike-for-likeSix of these boards feed the Vibe Coding Index02
| Benchmark | GPT-4o-mini | GPT-5 Nano | Leader |
|---|---|---|---|
| SWE-bench Verified | Not measured | 34.8% | Only GPT-5 Nano measured |
| AA Coding Index | 11.4 | Not measured | Only GPT-4o-mini measured |
| LiveCodeBench (Vals AI) | 26.4% | 70.2% | GPT-5 Nano |
| LiveCodeBench (Artificial Analysis run) | 23.4% | 78.9% | GPT-5 Nano |
| Terminal-Bench Hard (Artificial Analysis run) | Not measured | 17.4% | Only GPT-5 Nano measured |
| Terminal-Bench | Not measured | 21.8% | Only GPT-5 Nano measured |
| WeirdML | Not measured | 38.1% | Only GPT-5 Nano measured |
| LMArena Text: coding | Not measured | 1351 | Only GPT-5 Nano measured |
| LMArena Text: software and IT | Not measured | 1345 | Only GPT-5 Nano measured |
| SciCode | 1.5% | Not measured | Only GPT-4o-mini measured |
| Neither model has a result on the other 29 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index02
| Benchmark | GPT-4o-mini | GPT-5 Nano | Leader |
|---|---|---|---|
| AA Intelligence Index | 6.7 | 13.0 | GPT-5 Nano |
| Epoch Capabilities Index | 126.5 | 139.2 | GPT-5 Nano |
Agentic workDirectional onlyPublic boards, shown as published, kept out of the index2 boards, none shared
| Benchmark | GPT-4o-mini | GPT-5 Nano | Leader |
|---|---|---|---|
| τ²-Bench Telecom | Not measured | 36.5% | Only GPT-5 Nano measured |
| Berkeley Function Calling Leaderboard (BFCL) | Not measured | 51.4% | Only GPT-5 Nano measured |
| Neither model has a result on the other 39 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index06
| Benchmark | GPT-4o-mini | GPT-5 Nano | Leader |
|---|---|---|---|
| GPQA Diamond | 44.2% | 63.4% | GPT-5 Nano |
| MMMU Pro (Vals AI) | 56.6% | 70.9% | GPT-5 Nano |
| GPQA Diamond (Artificial Analysis run) | 42.6% | 67.6% | GPT-5 Nano |
| Humanity's Last Exam (Artificial Analysis run) | 4.2% | 9.5% | GPT-5 Nano |
| GPQA Diamond (Epoch AI run) | Not measured | 69.4% | Only GPT-5 Nano measured |
| ARC-AGI | Not measured | 20.7% | Only GPT-5 Nano measured |
| ARC-AGI-2 | 0.0% | 2.6% | GPT-5 Nano |
| Chess puzzles | Not measured | 22.0% | Only GPT-5 Nano measured |
| Mystery game puzzles | Not measured | 9.0% | Only GPT-5 Nano measured |
| VPCT | Not measured | 37.2% | Only GPT-5 Nano measured |
| LMArena Text: hard prompts | Not measured | 1328 | Only GPT-5 Nano measured |
| LMArena Text: expert | Not measured | 1321 | Only GPT-5 Nano measured |
| LMArena Text: hard prompts in English | Not measured | 1338 | Only GPT-5 Nano measured |
| LMArena Vision: diagrams | Not measured | 1141 | Only GPT-5 Nano measured |
| LMArena Vision: homework | Not measured | 1157 | Only GPT-5 Nano measured |
| Kagi LLM Benchmark | 28.8% | 62.2% | GPT-5 Nano |
| 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 Nano | Leader |
|---|---|---|---|
| AIME | 11.5% | 81.2% | GPT-5 Nano |
| MATH 500 (Vals AI) | 72.6% | 93.8% | GPT-5 Nano |
| MGSM (Vals AI) | 86.2% | 89.3% | GPT-5 Nano |
| AA Math Index | 14.7 | 83.7 | GPT-5 Nano |
| AIME 2025 (Artificial Analysis run) | 14.7% | 83.7% | GPT-5 Nano |
| OTIS Mock AIME | Not measured | 81.1% | Only GPT-5 Nano measured |
| FrontierMath, tiers 1 to 3 | Not measured | 20.0% | Only GPT-5 Nano measured |
| FrontierMath, tier 4 | Not measured | 2.4% | Only GPT-5 Nano measured |
| ProofBench | Not measured | 12.0% | Only GPT-5 Nano measured |
| MATH level 5 | Not measured | 95.2% | Only GPT-5 Nano measured |
| GSM8K | 91.3% | Not measured | Only GPT-4o-mini measured |
| LMArena Text: math | Not measured | 1317 | Only GPT-5 Nano measured |
| LMArena Text: mathematical work | Not measured | 1326 | Only GPT-5 Nano measured |
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index14
| Benchmark | GPT-4o-mini | GPT-5 Nano | Leader |
|---|---|---|---|
| MMLU Pro | 62.7% | 76.1% | GPT-5 Nano |
| LegalBench (Vals AI) | Not measured | 50.1% | Only GPT-5 Nano measured |
| CaseLaw (Vals AI) | Not measured | 52.6% | Only GPT-5 Nano measured |
| CorpFin (Vals AI) | 45.5% | Not measured | Only GPT-4o-mini measured |
| TaxEval (Vals AI) | 60.5% | 67.4% | GPT-5 Nano |
| MortgageTax (Vals AI) | 54.5% | 53.6% | GPT-4o-mini |
| MedQA (Vals AI) | 72.4% | 93.3% | GPT-5 Nano |
| MedCode (Vals AI) | Not measured | 30.4% | Only GPT-5 Nano measured |
| MMLU Pro (Artificial Analysis run) | 64.8% | 78.0% | GPT-5 Nano |
| SimpleQA Verified | Not measured | 11.7% | Only GPT-5 Nano measured |
| MMLU | 81.8% | Not measured | Only GPT-4o-mini measured |
| LMArena Text: science | Not measured | 1318 | Only GPT-5 Nano measured |
| LMArena Text: medicine and healthcare | Not measured | 1335 | Only GPT-5 Nano measured |
| LMArena Text: legal and government | Not measured | 1298 | Only GPT-5 Nano measured |
| LMArena Text: business and finance | Not measured | 1311 | Only GPT-5 Nano measured |
| Neither model has a result on the other 3 boards here | |||
Web designDirectional onlyPublic boards, shown as published, kept out of the index6 boards, none shared
| Benchmark | GPT-4o-mini | GPT-5 Nano | Leader |
|---|---|---|---|
| Design Arena: websites | Not measured | 1101 | Only GPT-5 Nano measured |
| Design Arena: UI components | Not measured | 1067 | Only GPT-5 Nano measured |
| Design Arena: game dev | Not measured | 1045 | Only GPT-5 Nano measured |
| Design Arena: data viz | Not measured | 1056 | Only GPT-5 Nano measured |
| Design Arena: 3D | Not measured | 966 | Only GPT-5 Nano measured |
| Design Arena: all code categories | Not measured | 1084 | Only GPT-5 Nano measured |
| Neither model has a result on the other 3 boards here | |||
GeneralLike-for-likePublic boards, shown as published, kept out of the index12
| Benchmark | GPT-4o-mini | GPT-5 Nano | Leader |
|---|---|---|---|
| SAGE (Vals AI) | Not measured | 30.4% | Only GPT-5 Nano measured |
| MedScribe (Vals AI) | Not measured | 72.9% | Only GPT-5 Nano measured |
| IFBench | 31.0% | 67.6% | GPT-5 Nano |
| Long context reasoning (AA-LCR) | Not measured | 45.0% | Only GPT-5 Nano measured |
| DTBench | 54.4% | 62.7% | GPT-5 Nano |
| LMCA | 10.4% | 7.9% | GPT-4o-mini |
| Fiction.LiveBench | Not measured | 44.4% | Only GPT-5 Nano measured |
| PIQA | 88.7% | Not measured | Only GPT-4o-mini measured |
| LMArena Text | Not measured | 1320 | Only GPT-5 Nano measured |
| LMArena Text: instruction following | Not measured | 1306 | Only GPT-5 Nano measured |
| LMArena Text: creative writing | Not measured | 1249 | Only GPT-5 Nano measured |
| LMArena Vision | Not measured | 1159 | Only GPT-5 Nano measured |
| LMArena Text: English | Not measured | 1321 | Only GPT-5 Nano measured |
| LMArena Text: non-English | Not measured | 1313 | Only GPT-5 Nano measured |
| LMArena Text: Chinese | Not measured | 1356 | Only GPT-5 Nano measured |
| LMArena Text: German | Not measured | 1327 | Only GPT-5 Nano measured |
| LMArena Text: Japanese | Not measured | 1227 | Only GPT-5 Nano measured |
| LMArena Text: Korean | Not measured | 1269 | Only GPT-5 Nano measured |
| LMArena Text: Spanish | Not measured | 1360 | Only GPT-5 Nano measured |
| LMArena Text: Russian | Not measured | 1296 | Only GPT-5 Nano measured |
| LMArena Text: Polish | Not measured | 1314 | Only GPT-5 Nano measured |
| LMArena Text: multi-turn | Not measured | 1311 | Only GPT-5 Nano measured |
| LMArena Text: longer queries | Not measured | 1312 | Only GPT-5 Nano measured |
| LMArena Text: writing and language | Not measured | 1283 | Only GPT-5 Nano measured |
| LMArena Text: entertainment and media | Not measured | 1268 | Only GPT-5 Nano measured |
| LMArena Vision: English | Not measured | 1170 | Only GPT-5 Nano measured |
| LMArena Vision: Chinese | Not measured | 1176 | Only GPT-5 Nano measured |
| LMArena Vision: reading text | Not measured | 1152 | Only GPT-5 Nano measured |
| LMArena Vision: humor | Not measured | 1110 | Only GPT-5 Nano measured |
| Neither model has a result on the other 17 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | GPT-4o-mini | GPT-5 Nano | 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-5 Nano costs less
Repository review
50K input + 3K output tokens
GPT-5 Nano costs less
Agent loop
200K input + 10K output tokens
GPT-5 Nano 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 Nano |
|---|---|---|
| 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 | $0.05 |
| Output $/Mtok | $0.60 | $0.40 |
| Coding index | Not benchmarked | Not benchmarked |
| Independent measurements behind it | 0 | 0 |
| Cost per solved task | Not computable | $0.109 |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is GPT-4o-mini better than GPT-5 Nano for coding?
Neither model has a coding score yet, so the two cannot be ranked on coding. Pick GPT-4o-mini for work measured by LiveCodeBench (Vals AI) or LiveCodeBench (Artificial Analysis run), where it leads.
Which is cheaper, GPT-4o-mini or GPT-5 Nano?
GPT-4o-mini costs $0.15 per million input tokens and $0.60 per million output tokens; GPT-5 Nano costs $0.05 and $0.40. Cost per solved task is known for GPT-5 Nano only.
Which has the bigger context window, GPT-4o-mini or GPT-5 Nano?
GPT-5 Nano, with 400K tokens against 128K.
How many benchmarks is the GPT-4o-mini vs GPT-5 Nano 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 Nano's on 0. Where only one model has a result, the page says so instead of naming a winner.