GPT-4.1 Nano vs o3
Updated October 21, 2026. 67 benchmarks have a result for both. Coding is ranked on the Vibe Coding Index; every other board is shown as published.
Decision reading
Pick o3 for coding: it scores 70.7 on the Vibe Coding Index against 8.9 for GPT-4.1 Nano.
Pick GPT-4.1 Nano when output tokens cost 20.0x less, or when the context window is larger, 1.05M against 200K tokens.
- Shared results
- 67
- GPT-4.1 Nano only
- 2
- o3 only
- 30
- Like-for-like categories
- 8 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
o3
o3 scores 70.7 against 8.9.
1 and 2 benchmarks behind the scores
Intelligence
AA Intelligence Index
o3
o3 leads, 20.2 against 7.8.
Same board, both measured
Reasoning
GPQA Diamond
o3
o3 leads, 84.1% against 50.8%.
Same board, both measured
Math
AIME
o3
o3 leads, 85.3% against 26.5%.
Same board, both measured
Knowledge
MMLU Pro
o3
o3 leads, 85.6% against 63.5%.
Same board, both measured
Web design
Design Arena: websites
o3
o3 leads, 1036 against 973.
Same board, both measured
Long documents
Listed context window
GPT-4.1 Nano
GPT-4.1 Nano takes 1.05M tokens against 200K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
GPT-4.1 Nano
GPT-4.1 Nano $0.0003, o3 $0.0060 per turn.
List prices
Cost per solved task
One SWE-bench Verified task, solved
No call
Only o3 has the number, $0.571.
Directional only
At a glance
- Coding index
- GPT-4.1 Nano 8.9 from 1 benchmark, o3 70.7 from 2 benchmarks.
- Widest category
- Agentic work, 63.5 points apart on average over 1 shared benchmark.
- Widest single gap
- Aider polyglot: GPT-4.1 Nano 8.9% against o3 81.3%, 72.4 points apart on a 0 to 100 scale.
- Output price
- GPT-4.1 Nano $0.40 against o3 $8.00 per million output tokens, 20.0x apart.
- Context window
- GPT-4.1 Nano takes 1.05M tokens, o3 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-4.1 Nano | Bars | o3 | Ties |
|---|---|---|---|---|
| Coding | 0 | 7 | ||
| Intelligence | 0 | 2 | ||
| Agentic work | 0 | 1 | ||
| Reasoning | 0 | 11 | ||
| Math | 0 | 9 | ||
| Knowledge | 0 | 12 | ||
| Web design | 0 | 5 | ||
| General | 0 | 20 | ||
| All shared boards | 0 | 67 |
CodingLike-for-likeFour of these boards feed the Vibe Coding Index07
| Benchmark | GPT-4.1 Nano | o3 | Leader |
|---|---|---|---|
| Aider polyglot | 8.9% | 81.3% | o3 |
| SWE-bench Verified | Not measured | 58.4% | Only o3 measured |
| SWE-bench Multimodal | Not measured | 36.0% | Only o3 measured |
| AA Coding Index | 11.1 | Not measured | Only GPT-4.1 Nano measured |
| LiveCodeBench (Vals AI) | 42.7% | 83.9% | o3 |
| LiveCodeBench (Artificial Analysis run) | 32.6% | 80.8% | o3 |
| Terminal-Bench Hard (Artificial Analysis run) | 3.8% | 37.1% | o3 |
| GSO-Bench | Not measured | 8.8% | Only o3 measured |
| WeirdML | 19.0% | 52.4% | o3 |
| ALE-Bench | Not measured | 933.5 | Only o3 measured |
| LMArena Text: coding | 1306 | 1407 | o3 |
| LMArena Text: software and IT | 1305 | 1415 | o3 |
| Neither model has a result on the other 26 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index02
| Benchmark | GPT-4.1 Nano | o3 | Leader |
|---|---|---|---|
| AA Intelligence Index | 7.8 | 20.2 | o3 |
| Epoch Capabilities Index | 129.5 | 146.7 | o3 |
Agentic workLike-for-likePublic boards, shown as published, kept out of the index01
| Benchmark | GPT-4.1 Nano | o3 | Leader |
|---|---|---|---|
| τ²-Bench Telecom | 17.3% | 80.7% | o3 |
| METR time horizons | Not measured | 65.4% | Only o3 measured |
| GDPval | Not measured | 30.8% | Only o3 measured |
| DeepResearch Bench | Not measured | 45.2% | Only o3 measured |
| OSWorld | Not measured | 23.0% | Only o3 measured |
| Neither model has a result on the other 34 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index011
| Benchmark | GPT-4.1 Nano | o3 | Leader |
|---|---|---|---|
| GPQA Diamond | 50.8% | 84.1% | o3 |
| MMMU Pro (Vals AI) | 55.0% | 80.4% | o3 |
| GPQA Diamond (Artificial Analysis run) | 51.2% | 82.7% | o3 |
| Humanity's Last Exam (Artificial Analysis run) | 3.8% | 20.1% | o3 |
| GPQA Diamond (Epoch AI run) | 48.9% | 81.8% | o3 |
| ARC-AGI | 0.0% | 60.8% | o3 |
| ARC-AGI-2 | 0.0% | 6.5% | o3 |
| SimpleBench | Not measured | 53.1% | Only o3 measured |
| Chess puzzles | 0.0% | 37.0% | o3 |
| Mystery game puzzles | Not measured | 29.0% | Only o3 measured |
| VPCT | Not measured | 52.0% | Only o3 measured |
| LMArena Text: hard prompts | 1286 | 1402 | o3 |
| LMArena Text: expert | 1271 | 1402 | o3 |
| LMArena Text: hard prompts in English | 1293 | 1411 | o3 |
| LMArena Vision: diagrams | Not measured | 1220 | Only o3 measured |
| LMArena Vision: homework | Not measured | 1234 | Only o3 measured |
| Neither model has a result on the other 5 boards here | |||
MathLike-for-likePublic boards, shown as published, kept out of the index09
| Benchmark | GPT-4.1 Nano | o3 | Leader |
|---|---|---|---|
| AIME | 26.5% | 85.3% | o3 |
| MATH 500 (Vals AI) | 80.2% | 94.6% | o3 |
| MGSM (Vals AI) | 69.3% | 91.8% | o3 |
| AA Math Index | 24.0 | 88.3 | o3 |
| AIME 2025 (Artificial Analysis run) | 24.0% | 88.3% | o3 |
| OTIS Mock AIME | 28.9% | 84.4% | o3 |
| FrontierMath, tiers 1 to 3 | Not measured | 33.3% | Only o3 measured |
| MATH level 5 | 70.0% | 97.8% | o3 |
| LMArena Text: math | 1274 | 1426 | o3 |
| LMArena Text: mathematical work | 1274 | 1423 | o3 |
| Neither model has a result on the other 3 boards here | |||
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index012
| Benchmark | GPT-4.1 Nano | o3 | Leader |
|---|---|---|---|
| MMLU Pro | 63.5% | 85.6% | o3 |
| LegalBench (Vals AI) | 61.1% | 83.8% | o3 |
| CorpFin (Vals AI) | 42.1% | 59.7% | o3 |
| TaxEval (Vals AI) | 60.8% | 74.6% | o3 |
| MortgageTax (Vals AI) | 52.8% | 65.7% | o3 |
| MedQA (Vals AI) | 68.2% | 96.1% | o3 |
| MedCode (Vals AI) | Not measured | 47.3% | Only o3 measured |
| MMLU Pro (Artificial Analysis run) | 65.7% | 85.3% | o3 |
| SimpleQA Verified | 6.0% | 49.4% | o3 |
| GeoBench | Not measured | 74.0% | Only o3 measured |
| LMArena Text: science | 1297 | 1429 | o3 |
| LMArena Text: medicine and healthcare | 1276 | 1448 | o3 |
| LMArena Text: legal and government | 1300 | 1428 | o3 |
| LMArena Text: business and finance | 1267 | 1393 | o3 |
| Neither model has a result on the other 3 boards here | |||
Web designLike-for-likePublic boards, shown as published, kept out of the index05
| Benchmark | GPT-4.1 Nano | o3 | Leader |
|---|---|---|---|
| Design Arena: websites | 973 | 1036 | o3 |
| Design Arena: UI components | 916 | 1016 | o3 |
| Design Arena: game dev | 971 | 1034 | o3 |
| Design Arena: data viz | 891 | 1200 | o3 |
| Design Arena: 3D | 925 | Not measured | Only GPT-4.1 Nano measured |
| Design Arena: all code categories | 963 | 1021 | o3 |
| Neither model has a result on the other 3 boards here | |||
GeneralLike-for-likePublic boards, shown as published, kept out of the index020
| Benchmark | GPT-4.1 Nano | o3 | Leader |
|---|---|---|---|
| SAGE (Vals AI) | Not measured | 41.8% | Only o3 measured |
| MedScribe (Vals AI) | Not measured | 76.7% | Only o3 measured |
| IFBench | 32.0% | 71.4% | o3 |
| Long context reasoning (AA-LCR) | 20.3% | 74.7% | o3 |
| DTBench | 52.5% | 84.8% | o3 |
| LMCA | 5.5% | 39.7% | o3 |
| Fiction.LiveBench | 25.0% | 88.9% | o3 |
| Creative writing (Lech Mazur) | Not measured | 83.9% | Only o3 measured |
| CL-bench | Not measured | 17.8% | Only o3 measured |
| LMArena Text | 1285 | 1410 | o3 |
| LMArena Text: instruction following | 1266 | 1368 | o3 |
| LMArena Text: creative writing | 1260 | 1359 | o3 |
| LMArena Vision | 1063 | 1214 | o3 |
| LMArena Text: English | 1303 | 1417 | o3 |
| LMArena Text: non-English | 1260 | 1401 | o3 |
| LMArena Text: Chinese | 1270 | 1437 | o3 |
| LMArena Text: German | 1288 | 1420 | o3 |
| LMArena Text: Japanese | 1198 | 1403 | o3 |
| LMArena Text: Korean | Not measured | 1370 | Only o3 measured |
| LMArena Text: French | Not measured | 1430 | Only o3 measured |
| LMArena Text: Spanish | Not measured | 1395 | Only o3 measured |
| LMArena Text: Russian | 1261 | 1406 | o3 |
| LMArena Text: Polish | Not measured | 1438 | Only o3 measured |
| LMArena Text: multi-turn | 1277 | 1405 | o3 |
| LMArena Text: longer queries | 1283 | 1372 | o3 |
| LMArena Text: writing and language | 1261 | 1372 | o3 |
| LMArena Text: entertainment and media | 1243 | 1373 | o3 |
| LMArena Vision: English | 1101 | 1221 | o3 |
| LMArena Vision: Chinese | Not measured | 1237 | Only o3 measured |
| LMArena Vision: reading text | Not measured | 1218 | Only o3 measured |
| LMArena Vision: humor | Not measured | 1222 | Only o3 measured |
| LMArena Vision: captioning | Not measured | 1210 | Only o3 measured |
| LMArena Vision: recognizing things | Not measured | 1234 | Only o3 measured |
| LMArena Vision: creative writing | Not measured | 1201 | Only o3 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-4.1 Nano | o3 | 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-4.1 Nano costs less
Repository review
50K input + 3K output tokens
GPT-4.1 Nano costs less
Agent loop
200K input + 10K output tokens
GPT-4.1 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-4.1 Nano | OpenAI o3 |
|---|---|---|
| Maker | OpenAI | OpenAI |
| Weights | No public weights listed | No public weights listed |
| Released | April 14, 2025 | April 16, 2025 |
| Context window | 1.05M | 200K |
| Input $/Mtok | $0.10 | $2.00 |
| Output $/Mtok | $0.40 | $8.00 |
| Coding index | 8.9 | 70.7 |
| Independent measurements behind it | 1 | 2 |
| Cost per solved task | Not computable | $0.571 |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is GPT-4.1 Nano better than o3 for coding?
Pick o3 for coding: it scores 70.7 on the Vibe Coding Index against 8.9 for GPT-4.1 Nano. Pick GPT-4.1 Nano when output tokens cost 20.0x less, or when the context window is larger, 1.05M against 200K tokens.
Which is cheaper, GPT-4.1 Nano or o3?
GPT-4.1 Nano costs $0.10 per million input tokens and $0.40 per million output tokens; o3 costs $2.00 and $8.00. Cost per solved task is known for o3 only.
Which has the bigger context window, GPT-4.1 Nano or o3?
GPT-4.1 Nano, with 1.05M tokens against 200K.
How many benchmarks is the GPT-4.1 Nano vs o3 comparison based on?
67 benchmarks have a result for both models as of October 21, 2026. GPT-4.1 Nano's coding index rests on 1 independent benchmark and o3's on 2. Where only one model has a result, the page says so instead of naming a winner.