GPT-4.1 vs o3
o3 leads GPT-4.1 on the Artificial Analysis Intelligence Index, 20.2 to 12.7, at about the same output price ($8.00 vs $8.00 per million). Updated October 22, 2026; 90 benchmarks have a result for both.
GPT-4.1 or o3: which to pick
Neither model has a coding score yet, so the two cannot be ranked on coding.
Pick GPT-4.1 for a lower cost per solved task ($0.37 against $0.571) and a larger context window (1.05M against 200K tokens).
- Shared results
- 90
- GPT-4.1 only
- 2
- o3 only
- 12
- 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 12.7.
Same board, both measured
Reasoning
GPQA Diamond
o3
o3 leads, 84.1% against 65.4%.
Same board, both measured
Math
AIME
o3
o3 leads, 85.3% against 39.6%.
Same board, both measured
Knowledge
MMLU Pro
o3
o3 leads, 85.6% against 80.5%.
Same board, both measured
Web design
Design Arena: websites
GPT-4.1
GPT-4.1 leads, 1038 against 1036.
Same board, both measured
Long documents
Listed context window
GPT-4.1
GPT-4.1 takes 1.05M tokens against 200K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
No call
GPT-4.1 $0.0060, o3 $0.0060 per turn.
List prices
Cost per solved task
One SWE-bench Verified task, solved
GPT-4.1
GPT-4.1 $0.37, o3 $0.571.
Published attempt cost and pass rate
At a glance
- Coding index
- GPT-4.1 not benchmarked, o3 not benchmarked.
- Widest category
- Math, 27.3 points apart on average over 10 shared benchmarks.
- Widest single gap
- ARC-AGI: GPT-4.1 5.5% against o3 60.8%, 55.3 points apart on a 0 to 100 scale.
- Output price
- Both cost $8.00 per million output tokens.
- Context window
- GPT-4.1 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 | Bars | o3 | Ties |
|---|---|---|---|---|
| Coding | 0 | 11 | ||
| Intelligence | 0 | 2 | ||
| Agentic work | 0 | 3 | ||
| Reasoning | 1 | 14 | ||
| Math | 0 | 10 | ||
| Knowledge | 4 | 10 | ||
| Web design | 3 | 2 | ||
| General | 3 | 27 | ||
| All shared boards | 11 | 79 |
CodingLike-for-likeSix of these boards feed the Vibe Coding Index011
| Benchmark | GPT-4.1 | o3 | Leader |
|---|---|---|---|
| Aider polyglot | 52.4% | 81.3% | o3 |
| SWE-bench Verified | 39.6% | 58.4% | o3 |
| SWE-bench Multimodal | 31.1% | 36.0% | o3 |
| LiveCodeBench (Vals AI) | 54.7% | 83.9% | o3 |
| LiveCodeBench (Artificial Analysis run) | 45.7% | 80.8% | o3 |
| Terminal-Bench Hard (Artificial Analysis run) | 13.6% | 37.1% | o3 |
| GSO-Bench | Not measured | 8.8% | Only o3 measured |
| WeirdML | 39.0% | 52.4% | o3 |
| ALE-Bench | 558.1 | 933.5 | o3 |
| LMArena Text: coding | 1390 | 1407 | o3 |
| LMArena Text: software and IT | 1391 | 1415 | o3 |
| SciCode | 4.6% | 9.2% | o3 |
| Neither model has a result on the other 27 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index02
| Benchmark | GPT-4.1 | o3 | Leader |
|---|---|---|---|
| AA Intelligence Index | 12.7 | 20.2 | o3 |
| Epoch Capabilities Index | 136.7 | 146.7 | o3 |
Agentic workLike-for-likePublic boards, shown as published, kept out of the index03
| Benchmark | GPT-4.1 | o3 | Leader |
|---|---|---|---|
| τ²-Bench Telecom | 47.1% | 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) | 54.0% | 63.0% | o3 |
| BrowseComp-Plus | 36.4% | 65.9% | o3 |
| Neither model has a result on the other 34 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index114
| Benchmark | GPT-4.1 | o3 | Leader |
|---|---|---|---|
| GPQA Diamond | 65.4% | 84.1% | o3 |
| MMMU Pro (Vals AI) | 72.4% | 80.4% | o3 |
| GPQA Diamond (Artificial Analysis run) | 66.6% | 82.7% | o3 |
| Humanity's Last Exam (Artificial Analysis run) | 4.2% | 20.1% | o3 |
| GPQA Diamond (Epoch AI run) | 66.9% | 81.8% | o3 |
| ARC-AGI | 5.5% | 60.8% | o3 |
| ARC-AGI-2 | 0.4% | 6.5% | o3 |
| SimpleBench | 27.0% | 53.1% | o3 |
| Chess puzzles | 3.0% | 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 | 1384 | 1402 | o3 |
| LMArena Text: expert | 1364 | 1402 | o3 |
| LMArena Text: hard prompts in English | 1393 | 1411 | o3 |
| LMArena Vision: diagrams | 1215 | 1220 | o3 |
| LMArena Vision: homework | 1248 | 1234 | GPT-4.1 |
| Kagi LLM Benchmark | 52.3% | 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-4.1 | o3 | Leader |
|---|---|---|---|
| AIME | 39.6% | 85.3% | o3 |
| MATH 500 (Vals AI) | 87.2% | 94.6% | o3 |
| MGSM (Vals AI) | 87.7% | 91.8% | o3 |
| AA Math Index | 34.7 | 88.3 | o3 |
| AIME 2025 (Artificial Analysis run) | 34.7% | 88.3% | o3 |
| OTIS Mock AIME | 38.3% | 84.4% | o3 |
| FrontierMath, tiers 1 to 3 | 6.0% | 33.3% | o3 |
| MATH level 5 | 83.0% | 97.8% | o3 |
| LMArena Text: math | 1369 | 1426 | o3 |
| LMArena Text: mathematical work | 1360 | 1423 | o3 |
| Neither model has a result on the other 3 boards here | |||
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index410
| Benchmark | GPT-4.1 | o3 | Leader |
|---|---|---|---|
| MMLU Pro | 80.5% | 85.6% | o3 |
| LegalBench (Vals AI) | 83.1% | 83.8% | o3 |
| CaseLaw (Vals AI) | 69.9% | Not measured | Only GPT-4.1 measured |
| CorpFin (Vals AI) | 63.0% | 59.7% | GPT-4.1 |
| TaxEval (Vals AI) | 75.1% | 74.6% | GPT-4.1 |
| MortgageTax (Vals AI) | 65.9% | 65.7% | GPT-4.1 |
| MedQA (Vals AI) | 91.2% | 96.1% | o3 |
| MedCode (Vals AI) | Not measured | 47.3% | Only o3 measured |
| MMLU Pro (Artificial Analysis run) | 80.6% | 85.3% | o3 |
| SimpleQA Verified | 31.1% | 49.4% | o3 |
| GeoBench | 72.0% | 74.0% | o3 |
| LMArena Text: science | 1382 | 1429 | o3 |
| LMArena Text: medicine and healthcare | 1379 | 1448 | o3 |
| LMArena Text: legal and government | 1399 | 1428 | o3 |
| LMArena Text: business and finance | 1369 | 1393 | o3 |
| FACTS Benchmark Suite | 45.8% | 44.4% | GPT-4.1 |
| Neither model has a result on the other 2 boards here | |||
Web designLike-for-likePublic boards, shown as published, kept out of the index32
| Benchmark | GPT-4.1 | o3 | Leader |
|---|---|---|---|
| Design Arena: websites | 1038 | 1036 | GPT-4.1 |
| Design Arena: UI components | 997 | 1017 | o3 |
| Design Arena: game dev | 1079 | 1034 | GPT-4.1 |
| Design Arena: data viz | 1104 | 1200 | o3 |
| Design Arena: 3D | 849 | Not measured | Only GPT-4.1 measured |
| Design Arena: all code categories | 1025 | 1020 | GPT-4.1 |
| Neither model has a result on the other 3 boards here | |||
GeneralLike-for-likePublic boards, shown as published, kept out of the index327
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | GPT-4.1 | 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
Same cost
Repository review
50K input + 3K output tokens
Same cost
Agent loop
200K input + 10K output tokens
Same cost
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 | 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 | $2.00 | $2.00 |
| Output $/Mtok | $8.00 | $8.00 |
| Coding index | Not benchmarked | Not benchmarked |
| Independent measurements behind it | 0 | 0 |
| Cost per solved task | $0.37 | $0.571 |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is GPT-4.1 better than o3 for coding?
Neither model has a coding score yet, so the two cannot be ranked on coding. Pick GPT-4.1 for a lower cost per solved task ($0.37 against $0.571) and a larger context window (1.05M against 200K tokens).
Which is cheaper, GPT-4.1 or o3?
GPT-4.1 costs $2.00 per million input tokens and $8.00 per million output tokens; o3 costs $2.00 and $8.00. Per solved SWE-bench Verified task, GPT-4.1 costs $0.37 and o3 $0.571.
Which has the bigger context window, GPT-4.1 or o3?
GPT-4.1, with 1.05M tokens against 200K.
How many benchmarks is the GPT-4.1 vs o3 comparison based on?
90 benchmarks have a result for both models as of October 22, 2026. GPT-4.1'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.