GPT-5 Nano vs o3 Mini
GPT-5 Nano leads o3 Mini on the Artificial Analysis Intelligence Index, 13.0 to 12.5, and GPT-5 Nano costs 11.0x less per output token ($0.40 vs $4.40 per million). Updated October 22, 2026; 61 benchmarks have a result for both.
GPT-5 Nano or o3 Mini: which to pick
Neither model has a coding score yet, so the two cannot be ranked on coding.
Pick GPT-5 Nano for output tokens 11.0x cheaper ($0.40 vs $4.40 per million) and a larger context window (400K against 200K tokens).
- Shared results
- 61
- GPT-5 Nano only
- 26
- o3 Mini only
- 10
- Like-for-like categories
- 7 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 12.5.
Same board, both measured
Reasoning
GPQA Diamond
o3 Mini
o3 Mini leads, 75.5% against 63.4%.
Same board, both measured
Math
AIME
o3 Mini
o3 Mini leads, 86.5% against 81.2%.
Same board, both measured
Knowledge
MMLU Pro
o3 Mini
o3 Mini leads, 78.7% against 76.1%.
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 200K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
GPT-5 Nano
GPT-5 Nano $0.0003, o3 Mini $0.0033 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-5 Nano not benchmarked, o3 Mini not benchmarked.
- Widest category
- Reasoning, 6.8 points apart on average over 11 shared benchmarks.
- Widest single gap
- LegalBench (Vals AI): GPT-5 Nano 50.1% against o3 Mini 71.5%, 21.4 points apart on a 0 to 100 scale.
- Output price
- GPT-5 Nano $0.40 against o3 Mini $4.40 per million output tokens, 11.0x apart.
- Context window
- GPT-5 Nano takes 400K tokens, o3 Mini 200K.
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 Nano | Bars | o3 Mini | Ties |
|---|---|---|---|---|
| Coding | 2 | 5 | ||
| Intelligence | 1 | 1 | ||
| Agentic work | 1 | 0 | ||
| Reasoning | 2 | 9 | ||
| Math | 4 | 5 | ||
| Knowledge | 1 | 9 | ||
| General | 5 | 16 | ||
| All shared boards | 16 | 45 |
CodingLike-for-likeSix of these boards feed the Vibe Coding Index25
| Benchmark | GPT-5 Nano | o3 Mini | Leader |
|---|---|---|---|
| Aider polyglot | Not measured | 60.4% | Only o3 Mini measured |
| SWE-bench Verified | 34.8% | 42.4% | o3 Mini |
| SWE-bench Lite | Not measured | 32.3% | Only o3 Mini measured |
| LiveCodeBench (Vals AI) | 70.2% | 71.5% | o3 Mini |
| LiveCodeBench (Artificial Analysis run) | 78.9% | 73.4% | GPT-5 Nano |
| SciCode | Not measured | 42.8% | Only o3 Mini measured |
| Terminal-Bench Hard (Artificial Analysis run) | 17.4% | 6.8% | GPT-5 Nano |
| Terminal-Bench | 21.8% | Not measured | Only GPT-5 Nano measured |
| GSO-Bench | Not measured | 1.3% | Only o3 Mini measured |
| WeirdML | 38.1% | 43.7% | o3 Mini |
| Cybench | Not measured | 22.5% | Only o3 Mini measured |
| LMArena Text: coding | 1351 | 1378 | o3 Mini |
| LMArena Text: software and IT | 1345 | 1364 | o3 Mini |
| SciCode | Not measured | 7.7% | Only o3 Mini measured |
| Neither model has a result on the other 25 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index11
| Benchmark | GPT-5 Nano | o3 Mini | Leader |
|---|---|---|---|
| AA Intelligence Index | 13.0 | 12.5 | GPT-5 Nano |
| Epoch Capabilities Index | 139.2 | 140.2 | o3 Mini |
Agentic workLike-for-likePublic boards, shown as published, kept out of the index10
| Benchmark | GPT-5 Nano | o3 Mini | Leader |
|---|---|---|---|
| τ²-Bench Telecom | 36.5% | 31.3% | GPT-5 Nano |
| Berkeley Function Calling Leaderboard (BFCL) | 51.4% | Not measured | 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 index29
| Benchmark | GPT-5 Nano | o3 Mini | Leader |
|---|---|---|---|
| GPQA Diamond | 63.4% | 75.5% | o3 Mini |
| MMMU Pro (Vals AI) | 70.9% | Not measured | Only GPT-5 Nano measured |
| GPQA Diamond (Artificial Analysis run) | 67.6% | 77.3% | o3 Mini |
| Humanity's Last Exam (Artificial Analysis run) | 9.5% | 12.0% | o3 Mini |
| GPQA Diamond (Epoch AI run) | 69.4% | 77.0% | o3 Mini |
| ARC-AGI | 20.7% | 34.5% | o3 Mini |
| ARC-AGI-2 | 2.6% | 3.0% | o3 Mini |
| SimpleBench | Not measured | 22.8% | Only o3 Mini measured |
| Chess puzzles | 22.0% | 15.0% | GPT-5 Nano |
| Mystery game puzzles | 9.0% | 7.0% | GPT-5 Nano |
| VPCT | 37.2% | Not measured | Only GPT-5 Nano measured |
| LMArena Text: hard prompts | 1328 | 1365 | o3 Mini |
| LMArena Text: expert | 1321 | 1364 | o3 Mini |
| LMArena Text: hard prompts in English | 1338 | 1375 | o3 Mini |
| LMArena Vision: diagrams | 1141 | Not measured | Only GPT-5 Nano measured |
| LMArena Vision: homework | 1157 | Not measured | Only GPT-5 Nano measured |
| Kagi LLM Benchmark | 62.2% | Not measured | Only GPT-5 Nano measured |
| Neither model has a result on the other 5 boards here | |||
MathLike-for-likePublic boards, shown as published, kept out of the index45
| Benchmark | GPT-5 Nano | o3 Mini | Leader |
|---|---|---|---|
| AIME | 81.2% | 86.5% | o3 Mini |
| MATH 500 (Vals AI) | 93.8% | 91.8% | GPT-5 Nano |
| MGSM (Vals AI) | 89.3% | 91.3% | o3 Mini |
| AA Math Index | 83.7 | Not measured | Only GPT-5 Nano measured |
| AIME 2025 (Artificial Analysis run) | 83.7% | Not measured | Only GPT-5 Nano measured |
| OTIS Mock AIME | 81.1% | 76.9% | GPT-5 Nano |
| FrontierMath, tiers 1 to 3 | 20.0% | 18.6% | GPT-5 Nano |
| FrontierMath, tier 4 | 2.4% | 0.0% | GPT-5 Nano |
| ProofBench | 12.0% | Not measured | Only GPT-5 Nano measured |
| MATH level 5 | 95.2% | 96.5% | o3 Mini |
| LMArena Text: math | 1317 | 1396 | o3 Mini |
| LMArena Text: mathematical work | 1326 | 1399 | o3 Mini |
| Neither model has a result on the other 1 board here | |||
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index19
| Benchmark | GPT-5 Nano | o3 Mini | Leader |
|---|---|---|---|
| MMLU Pro | 76.1% | 78.7% | o3 Mini |
| LegalBench (Vals AI) | 50.1% | 71.5% | o3 Mini |
| CaseLaw (Vals AI) | 52.6% | Not measured | Only GPT-5 Nano measured |
| CorpFin (Vals AI) | Not measured | 45.3% | Only o3 Mini measured |
| TaxEval (Vals AI) | 67.4% | 69.4% | o3 Mini |
| MortgageTax (Vals AI) | 53.6% | Not measured | Only GPT-5 Nano measured |
| MedQA (Vals AI) | 93.3% | 94.8% | o3 Mini |
| MedCode (Vals AI) | 30.4% | Not measured | Only GPT-5 Nano measured |
| MMLU Pro (Artificial Analysis run) | 78.0% | 80.2% | o3 Mini |
| SimpleQA Verified | 11.7% | 15.3% | o3 Mini |
| LMArena Text: science | 1318 | 1339 | o3 Mini |
| LMArena Text: medicine and healthcare | 1335 | 1330 | GPT-5 Nano |
| LMArena Text: legal and government | 1298 | 1328 | o3 Mini |
| LMArena Text: business and finance | 1311 | 1313 | o3 Mini |
| Neither model has a result on the other 4 boards here | |||
Web designDirectional onlyPublic boards, shown as published, kept out of the index6 boards, none shared
| Benchmark | GPT-5 Nano | o3 Mini | Leader |
|---|---|---|---|
| Design Arena: websites | 1101 | Not measured | Only GPT-5 Nano measured |
| Design Arena: UI components | 1064 | Not measured | Only GPT-5 Nano measured |
| Design Arena: game dev | 1044 | Not measured | Only GPT-5 Nano measured |
| Design Arena: data viz | 1056 | Not measured | Only GPT-5 Nano measured |
| Design Arena: 3D | 965 | Not measured | Only GPT-5 Nano measured |
| Design Arena: all code categories | 1084 | Not measured | 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 index516
| Benchmark | GPT-5 Nano | o3 Mini | Leader |
|---|---|---|---|
| SAGE (Vals AI) | 30.4% | Not measured | Only GPT-5 Nano measured |
| MedScribe (Vals AI) | 72.9% | Not measured | Only GPT-5 Nano measured |
| IFBench | 67.6% | 67.1% | GPT-5 Nano |
| Long context reasoning (AA-LCR) | 45.0% | 43.0% | GPT-5 Nano |
| DTBench | 62.7% | 68.8% | o3 Mini |
| LMCA | 7.9% | 19.0% | o3 Mini |
| Fiction.LiveBench | 44.4% | 50.0% | o3 Mini |
| Creative writing (Lech Mazur) | Not measured | 61.7% | Only o3 Mini measured |
| LMArena Text | 1320 | 1337 | o3 Mini |
| LMArena Text: instruction following | 1306 | 1337 | o3 Mini |
| LMArena Text: creative writing | 1249 | 1286 | o3 Mini |
| LMArena Vision | 1159 | Not measured | Only GPT-5 Nano measured |
| LMArena Text: English | 1321 | 1351 | o3 Mini |
| LMArena Text: non-English | 1313 | 1319 | o3 Mini |
| LMArena Text: Chinese | 1356 | 1379 | o3 Mini |
| LMArena Text: German | 1327 | 1303 | GPT-5 Nano |
| LMArena Text: Japanese | 1227 | 1286 | o3 Mini |
| LMArena Text: Korean | 1269 | 1313 | o3 Mini |
| LMArena Text: French | Not measured | 1334 | Only o3 Mini measured |
| LMArena Text: Spanish | 1360 | 1321 | GPT-5 Nano |
| LMArena Text: Russian | 1296 | 1304 | o3 Mini |
| LMArena Text: Polish | 1314 | 1294 | GPT-5 Nano |
| LMArena Text: multi-turn | 1311 | 1320 | o3 Mini |
| LMArena Text: longer queries | 1312 | 1343 | o3 Mini |
| LMArena Text: writing and language | 1283 | 1313 | o3 Mini |
| LMArena Text: entertainment and media | 1268 | 1283 | o3 Mini |
| LMArena Vision: English | 1170 | Not measured | Only GPT-5 Nano measured |
| LMArena Vision: Chinese | 1176 | Not measured | Only GPT-5 Nano measured |
| LMArena Vision: reading text | 1152 | Not measured | Only GPT-5 Nano measured |
| LMArena Vision: humor | 1110 | Not measured | Only GPT-5 Nano measured |
| Neither model has a result on the other 16 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | GPT-5 Nano | o3 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-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-5 Nano | OpenAI o3 Mini |
|---|---|---|
| Maker | OpenAI | OpenAI |
| Weights | No public weights listed | No public weights listed |
| Released | August 7, 2025 | January 31, 2025 |
| Context window | 400K | 200K |
| Input $/Mtok | $0.05 | $1.10 |
| Output $/Mtok | $0.40 | $4.40 |
| Coding index | Not benchmarked | Not benchmarked |
| Independent measurements behind it | 0 | 0 |
| Cost per solved task | $0.109 | Not computable |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is GPT-5 Nano better than o3 Mini for coding?
Neither model has a coding score yet, so the two cannot be ranked on coding. Pick GPT-5 Nano for output tokens 11.0x cheaper ($0.40 vs $4.40 per million) and a larger context window (400K against 200K tokens).
Which is cheaper, GPT-5 Nano or o3 Mini?
GPT-5 Nano costs $0.05 per million input tokens and $0.40 per million output tokens; o3 Mini costs $1.10 and $4.40. Cost per solved task is known for GPT-5 Nano only.
Which has the bigger context window, GPT-5 Nano or o3 Mini?
GPT-5 Nano, with 400K tokens against 200K.
How many benchmarks is the GPT-5 Nano vs o3 Mini comparison based on?
61 benchmarks have a result for both models as of October 22, 2026. GPT-5 Nano's coding index rests on 0 independent benchmarks and o3 Mini's on 0. Where only one model has a result, the page says so instead of naming a winner.