GPT-5 Nano vs o3
o3 leads GPT-5 Nano on the Artificial Analysis Intelligence Index, 20.2 to 13.0, and GPT-5 Nano costs 20.0x less per output token ($0.40 vs $8.00 per million). Updated October 22, 2026; 82 benchmarks have a result for both.
GPT-5 Nano or o3: 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 20.0x cheaper ($0.40 vs $8.00 per million) and a lower cost per solved task ($0.109 against $0.571).
- Shared results
- 82
- GPT-5 Nano only
- 5
- o3 only
- 20
- Like-for-like categories
- 8 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
o3
o3 leads, 20.2 against 13.0.
Same board, both measured
Reasoning
GPQA Diamond
o3
o3 leads, 84.1% against 63.4%.
Same board, both measured
Math
AIME
o3
o3 leads, 85.3% against 81.2%.
Same board, both measured
Knowledge
MMLU Pro
o3
o3 leads, 85.6% against 76.1%.
Same board, both measured
Web design
Design Arena: websites
GPT-5 Nano
GPT-5 Nano leads, 1101 against 1036.
Same board, both measured
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 $0.0060 per turn.
List prices
Cost per solved task
One SWE-bench Verified task, solved
GPT-5 Nano
GPT-5 Nano $0.109, o3 $0.571.
Published attempt cost and pass rate
At a glance
- Coding index
- GPT-5 Nano not benchmarked, o3 not benchmarked.
- Widest category
- Agentic work, 27.9 points apart on average over 2 shared benchmarks.
- Widest single gap
- Fiction.LiveBench: GPT-5 Nano 44.4% against o3 88.9%, 44.5 points apart on a 0 to 100 scale.
- Output price
- GPT-5 Nano $0.40 against o3 $8.00 per million output tokens, 20.0x apart.
- Context window
- GPT-5 Nano takes 400K 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-5 Nano | Bars | o3 | Ties |
|---|---|---|---|---|
| Coding | 0 | 7 | ||
| Intelligence | 0 | 2 | ||
| Agentic work | 0 | 2 | ||
| Reasoning | 0 | 16 | ||
| Math | 0 | 10 | ||
| Knowledge | 0 | 12 | ||
| Web design | 4 | 1 | ||
| General | 0 | 28 | ||
| All shared boards | 4 | 78 |
CodingLike-for-likeSix of these boards feed the Vibe Coding Index07
| Benchmark | GPT-5 Nano | o3 | Leader |
|---|---|---|---|
| Aider polyglot | Not measured | 81.3% | Only o3 measured |
| SWE-bench Verified | 34.8% | 58.4% | o3 |
| SWE-bench Multimodal | Not measured | 36.0% | Only o3 measured |
| LiveCodeBench (Vals AI) | 70.2% | 83.9% | o3 |
| LiveCodeBench (Artificial Analysis run) | 78.9% | 80.8% | o3 |
| Terminal-Bench Hard (Artificial Analysis run) | 17.4% | 37.1% | o3 |
| Terminal-Bench | 21.8% | Not measured | Only GPT-5 Nano measured |
| GSO-Bench | Not measured | 8.8% | Only o3 measured |
| WeirdML | 38.1% | 52.4% | o3 |
| ALE-Bench | Not measured | 933.5 | Only o3 measured |
| LMArena Text: coding | 1351 | 1407 | o3 |
| LMArena Text: software and IT | 1345 | 1415 | o3 |
| SciCode | Not measured | 9.2% | Only o3 measured |
| 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-5 Nano | o3 | Leader |
|---|---|---|---|
| AA Intelligence Index | 13.0 | 20.2 | o3 |
| Epoch Capabilities Index | 139.2 | 146.7 | o3 |
Agentic workLike-for-likePublic boards, shown as published, kept out of the index02
| Benchmark | GPT-5 Nano | o3 | Leader |
|---|---|---|---|
| τ²-Bench Telecom | 36.5% | 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 |
| Berkeley Function Calling Leaderboard (BFCL) | 51.4% | 63.0% | o3 |
| BrowseComp-Plus | Not measured | 65.9% | 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 index016
| Benchmark | GPT-5 Nano | o3 | Leader |
|---|---|---|---|
| GPQA Diamond | 63.4% | 84.1% | o3 |
| MMMU Pro (Vals AI) | 70.9% | 80.4% | o3 |
| GPQA Diamond (Artificial Analysis run) | 67.6% | 82.7% | o3 |
| Humanity's Last Exam (Artificial Analysis run) | 9.5% | 20.1% | o3 |
| GPQA Diamond (Epoch AI run) | 69.4% | 81.8% | o3 |
| ARC-AGI | 20.7% | 60.8% | o3 |
| ARC-AGI-2 | 2.6% | 6.5% | o3 |
| SimpleBench | Not measured | 53.1% | Only o3 measured |
| Chess puzzles | 22.0% | 37.0% | o3 |
| Mystery game puzzles | 9.0% | 29.0% | o3 |
| VPCT | 37.2% | 52.0% | o3 |
| LMArena Text: hard prompts | 1328 | 1402 | o3 |
| LMArena Text: expert | 1321 | 1402 | o3 |
| LMArena Text: hard prompts in English | 1338 | 1411 | o3 |
| LMArena Vision: diagrams | 1141 | 1220 | o3 |
| LMArena Vision: homework | 1157 | 1234 | o3 |
| Kagi LLM Benchmark | 62.2% | 67.6% | o3 |
| Neither model has a result on the other 5 boards here | |||
MathLike-for-likePublic boards, shown as published, kept out of the index010
| Benchmark | GPT-5 Nano | o3 | Leader |
|---|---|---|---|
| AIME | 81.2% | 85.3% | o3 |
| MATH 500 (Vals AI) | 93.8% | 94.6% | o3 |
| MGSM (Vals AI) | 89.3% | 91.8% | o3 |
| AA Math Index | 83.7 | 88.3 | o3 |
| AIME 2025 (Artificial Analysis run) | 83.7% | 88.3% | o3 |
| OTIS Mock AIME | 81.1% | 84.4% | o3 |
| FrontierMath, tiers 1 to 3 | 20.0% | 33.3% | o3 |
| FrontierMath, tier 4 | 2.4% | Not measured | Only GPT-5 Nano measured |
| ProofBench | 12.0% | Not measured | Only GPT-5 Nano measured |
| MATH level 5 | 95.2% | 97.8% | o3 |
| LMArena Text: math | 1317 | 1426 | o3 |
| LMArena Text: mathematical work | 1326 | 1423 | o3 |
| Neither model has a result on the other 1 board here | |||
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index012
| Benchmark | GPT-5 Nano | o3 | Leader |
|---|---|---|---|
| MMLU Pro | 76.1% | 85.6% | o3 |
| LegalBench (Vals AI) | 50.1% | 83.8% | o3 |
| CaseLaw (Vals AI) | 52.6% | Not measured | Only GPT-5 Nano measured |
| CorpFin (Vals AI) | Not measured | 59.7% | Only o3 measured |
| TaxEval (Vals AI) | 67.4% | 74.6% | o3 |
| MortgageTax (Vals AI) | 53.6% | 65.7% | o3 |
| MedQA (Vals AI) | 93.3% | 96.1% | o3 |
| MedCode (Vals AI) | 30.4% | 47.3% | o3 |
| MMLU Pro (Artificial Analysis run) | 78.0% | 85.3% | o3 |
| SimpleQA Verified | 11.7% | 49.4% | o3 |
| GeoBench | Not measured | 74.0% | Only o3 measured |
| LMArena Text: science | 1318 | 1429 | o3 |
| LMArena Text: medicine and healthcare | 1335 | 1448 | o3 |
| LMArena Text: legal and government | 1298 | 1428 | o3 |
| LMArena Text: business and finance | 1311 | 1393 | o3 |
| FACTS Benchmark Suite | Not measured | 44.4% | Only o3 measured |
| Neither model has a result on the other 2 boards here | |||
Web designLike-for-likePublic boards, shown as published, kept out of the index41
| Benchmark | GPT-5 Nano | o3 | Leader |
|---|---|---|---|
| Design Arena: websites | 1101 | 1036 | GPT-5 Nano |
| Design Arena: UI components | 1064 | 1017 | GPT-5 Nano |
| Design Arena: game dev | 1044 | 1034 | GPT-5 Nano |
| Design Arena: data viz | 1056 | 1200 | o3 |
| Design Arena: 3D | 965 | Not measured | Only GPT-5 Nano measured |
| Design Arena: all code categories | 1084 | 1020 | GPT-5 Nano |
| Neither model has a result on the other 3 boards here | |||
GeneralLike-for-likePublic boards, shown as published, kept out of the index028
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | GPT-5 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-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 |
|---|---|---|
| Maker | OpenAI | OpenAI |
| Weights | No public weights listed | No public weights listed |
| Released | August 7, 2025 | April 16, 2025 |
| Context window | 400K | 200K |
| Input $/Mtok | $0.05 | $2.00 |
| Output $/Mtok | $0.40 | $8.00 |
| Coding index | Not benchmarked | Not benchmarked |
| Independent measurements behind it | 0 | 0 |
| Cost per solved task | $0.109 | $0.571 |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is GPT-5 Nano better than o3 for coding?
Neither model has a coding score yet, so the two cannot be ranked on coding. Pick GPT-5 Nano for output tokens 20.0x cheaper ($0.40 vs $8.00 per million) and a lower cost per solved task ($0.109 against $0.571).
Which is cheaper, GPT-5 Nano or o3?
GPT-5 Nano costs $0.05 per million input tokens and $0.40 per million output tokens; o3 costs $2.00 and $8.00. Per solved SWE-bench Verified task, GPT-5 Nano costs $0.109 and o3 $0.571.
Which has the bigger context window, GPT-5 Nano or o3?
GPT-5 Nano, with 400K tokens against 200K.
How many benchmarks is the GPT-5 Nano vs o3 comparison based on?
82 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's on 0. Where only one model has a result, the page says so instead of naming a winner.