GPT-4.1 vs o3 Mini
Updated October 21, 2026. 63 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 Mini for coding: it scores 52.1 on the Vibe Coding Index against 46.5 for GPT-4.1.
Pick GPT-4.1 when the context window is larger, 1.05M against 200K tokens, or when what matters is Terminal-Bench Hard (Artificial Analysis run) or LMArena Text: coding, where it leads.
- Shared results
- 63
- GPT-4.1 only
- 24
- o3 Mini only
- 7
- Like-for-like categories
- 7 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 Mini
o3 Mini scores 52.1 against 46.5.
2 benchmarks behind each score
Intelligence
AA Intelligence Index
GPT-4.1
GPT-4.1 leads, 12.7 against 12.5.
Same board, both measured
Reasoning
GPQA Diamond
o3 Mini
o3 Mini leads, 75.5% against 65.4%.
Same board, both measured
Math
AIME
o3 Mini
o3 Mini leads, 86.5% against 39.6%.
Same board, both measured
Knowledge
MMLU Pro
GPT-4.1
GPT-4.1 leads, 80.5% against 78.7%.
Same board, both measured
Web design
Design Arena: websites
No call
Only GPT-4.1 has a Design Arena: websites result, 1039.
Directional only
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
o3 Mini
GPT-4.1 $0.0060, o3 Mini $0.0033 per turn.
List prices
Cost per solved task
One SWE-bench Verified task, solved
No call
Only GPT-4.1 has the number, $0.37.
Directional only
At a glance
- Coding index
- GPT-4.1 46.5 from 2 benchmarks, o3 Mini 52.1 from 2 benchmarks.
- Widest category
- Math, 16.3 points apart on average over 8 shared benchmarks.
- Widest single gap
- AIME: GPT-4.1 39.6% against o3 Mini 86.5%, 46.9 points apart on a 0 to 100 scale.
- Output price
- GPT-4.1 $8.00 against o3 Mini $4.40 per million output tokens, 1.8x apart.
- Context window
- GPT-4.1 takes 1.05M 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-4.1 | Bars | o3 Mini | Ties |
|---|---|---|---|---|
| Coding | 3 | 5 | ||
| Intelligence | 1 | 1 | ||
| Agentic work | 1 | 0 | ||
| Reasoning | 3 | 8 | ||
| Math | 0 | 8 | ||
| Knowledge | 10 | 1 | ||
| General | 20 | 2 | ||
| All shared boards | 38 | 25 |
CodingLike-for-likeFour of these boards feed the Vibe Coding Index35
| Benchmark | GPT-4.1 | o3 Mini | Leader |
|---|---|---|---|
| Aider polyglot | 52.4% | 60.4% | o3 Mini |
| SWE-bench Verified | 39.6% | 42.4% | o3 Mini |
| SWE-bench Lite | Not measured | 32.3% | Only o3 Mini measured |
| SWE-bench Multimodal | 31.1% | Not measured | Only GPT-4.1 measured |
| LiveCodeBench (Vals AI) | 54.7% | 71.5% | o3 Mini |
| LiveCodeBench (Artificial Analysis run) | 45.7% | 73.4% | o3 Mini |
| SciCode | Not measured | 42.8% | Only o3 Mini measured |
| Terminal-Bench Hard (Artificial Analysis run) | 13.6% | 6.8% | GPT-4.1 |
| GSO-Bench | Not measured | 1.3% | Only o3 Mini measured |
| WeirdML | 39.0% | 43.7% | o3 Mini |
| Cybench | Not measured | 22.5% | Only o3 Mini measured |
| ALE-Bench | 558.1 | Not measured | Only GPT-4.1 measured |
| LMArena Text: coding | 1390 | 1378 | GPT-4.1 |
| LMArena Text: software and IT | 1391 | 1364 | GPT-4.1 |
| Neither model has a result on the other 24 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index11
| Benchmark | GPT-4.1 | o3 Mini | Leader |
|---|---|---|---|
| AA Intelligence Index | 12.7 | 12.5 | GPT-4.1 |
| Epoch Capabilities Index | 136.7 | 140.2 | o3 Mini |
Agentic workLike-for-likePublic boards, shown as published, kept out of the index10
| Benchmark | GPT-4.1 | o3 Mini | Leader |
|---|---|---|---|
| τ²-Bench Telecom | 47.1% | 31.3% | GPT-4.1 |
| Neither model has a result on the other 38 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index38
| Benchmark | GPT-4.1 | o3 Mini | Leader |
|---|---|---|---|
| GPQA Diamond | 65.4% | 75.5% | o3 Mini |
| MMMU Pro (Vals AI) | 72.4% | Not measured | Only GPT-4.1 measured |
| GPQA Diamond (Artificial Analysis run) | 66.6% | 77.3% | o3 Mini |
| Humanity's Last Exam (Artificial Analysis run) | 4.2% | 12.0% | o3 Mini |
| GPQA Diamond (Epoch AI run) | 66.9% | 77.0% | o3 Mini |
| ARC-AGI | 5.5% | 34.5% | o3 Mini |
| ARC-AGI-2 | 0.4% | 3.0% | o3 Mini |
| SimpleBench | 27.0% | 22.8% | GPT-4.1 |
| Chess puzzles | 3.0% | 15.0% | o3 Mini |
| Mystery game puzzles | Not measured | 7.0% | Only o3 Mini measured |
| LMArena Text: hard prompts | 1384 | 1365 | GPT-4.1 |
| LMArena Text: expert | 1364 | 1364 | o3 Mini |
| LMArena Text: hard prompts in English | 1393 | 1375 | GPT-4.1 |
| LMArena Vision: diagrams | 1215 | Not measured | Only GPT-4.1 measured |
| LMArena Vision: homework | 1248 | Not measured | Only GPT-4.1 measured |
| Neither model has a result on the other 6 boards here | |||
MathLike-for-likePublic boards, shown as published, kept out of the index08
| Benchmark | GPT-4.1 | o3 Mini | Leader |
|---|---|---|---|
| AIME | 39.6% | 86.5% | o3 Mini |
| MATH 500 (Vals AI) | 87.2% | 91.8% | o3 Mini |
| MGSM (Vals AI) | 87.7% | 91.3% | o3 Mini |
| AA Math Index | 34.7 | Not measured | Only GPT-4.1 measured |
| AIME 2025 (Artificial Analysis run) | 34.7% | Not measured | Only GPT-4.1 measured |
| OTIS Mock AIME | 38.3% | 76.9% | o3 Mini |
| FrontierMath, tiers 1 to 3 | 6.0% | 18.6% | o3 Mini |
| FrontierMath, tier 4 | Not measured | 0.0% | Only o3 Mini measured |
| MATH level 5 | 83.0% | 96.5% | o3 Mini |
| LMArena Text: math | 1369 | 1396 | o3 Mini |
| LMArena Text: mathematical work | 1360 | 1399 | o3 Mini |
| Neither model has a result on the other 2 boards here | |||
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index101
| Benchmark | GPT-4.1 | o3 Mini | Leader |
|---|---|---|---|
| MMLU Pro | 80.5% | 78.7% | GPT-4.1 |
| LegalBench (Vals AI) | 83.1% | 71.5% | GPT-4.1 |
| CaseLaw (Vals AI) | 69.9% | Not measured | Only GPT-4.1 measured |
| CorpFin (Vals AI) | 63.0% | 45.3% | GPT-4.1 |
| TaxEval (Vals AI) | 75.1% | 69.4% | GPT-4.1 |
| MortgageTax (Vals AI) | 65.9% | Not measured | Only GPT-4.1 measured |
| MedQA (Vals AI) | 91.2% | 94.8% | o3 Mini |
| MMLU Pro (Artificial Analysis run) | 80.6% | 80.2% | GPT-4.1 |
| SimpleQA Verified | 31.1% | 15.3% | GPT-4.1 |
| GeoBench | 72.0% | Not measured | Only GPT-4.1 measured |
| LMArena Text: science | 1382 | 1339 | GPT-4.1 |
| LMArena Text: medicine and healthcare | 1379 | 1330 | GPT-4.1 |
| LMArena Text: legal and government | 1399 | 1328 | GPT-4.1 |
| LMArena Text: business and finance | 1369 | 1313 | GPT-4.1 |
| 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-4.1 | o3 Mini | Leader |
|---|---|---|---|
| Design Arena: websites | 1039 | Not measured | Only GPT-4.1 measured |
| Design Arena: UI components | 1000 | Not measured | Only GPT-4.1 measured |
| Design Arena: game dev | 1080 | Not measured | Only GPT-4.1 measured |
| Design Arena: data viz | 1104 | Not measured | Only GPT-4.1 measured |
| Design Arena: 3D | 850 | Not measured | Only GPT-4.1 measured |
| Design Arena: all code categories | 1026 | Not measured | Only GPT-4.1 measured |
| Neither model has a result on the other 3 boards here | |||
GeneralLike-for-likePublic boards, shown as published, kept out of the index202
| Benchmark | GPT-4.1 | o3 Mini | Leader |
|---|---|---|---|
| IFBench | 43.0% | 67.1% | o3 Mini |
| Long context reasoning (AA-LCR) | 68.3% | 43.0% | GPT-4.1 |
| DTBench | 68.3% | 68.8% | o3 Mini |
| LMCA | 25.6% | 19.0% | GPT-4.1 |
| Fiction.LiveBench | 63.9% | 50.0% | GPT-4.1 |
| Creative writing (Lech Mazur) | Not measured | 61.7% | Only o3 Mini measured |
| LMArena Text | 1383 | 1337 | GPT-4.1 |
| LMArena Text: instruction following | 1367 | 1337 | GPT-4.1 |
| LMArena Text: creative writing | 1363 | 1286 | GPT-4.1 |
| LMArena Vision | 1210 | Not measured | Only GPT-4.1 measured |
| LMArena Text: English | 1392 | 1351 | GPT-4.1 |
| LMArena Text: non-English | 1370 | 1319 | GPT-4.1 |
| LMArena Text: Chinese | 1382 | 1379 | GPT-4.1 |
| LMArena Text: German | 1381 | 1303 | GPT-4.1 |
| LMArena Text: Japanese | 1319 | 1286 | GPT-4.1 |
| LMArena Text: Korean | 1338 | 1313 | GPT-4.1 |
| LMArena Text: French | 1382 | 1334 | GPT-4.1 |
| LMArena Text: Spanish | 1376 | 1321 | GPT-4.1 |
| LMArena Text: Russian | 1377 | 1304 | GPT-4.1 |
| LMArena Text: Polish | 1389 | 1294 | GPT-4.1 |
| LMArena Text: multi-turn | 1397 | 1320 | GPT-4.1 |
| LMArena Text: longer queries | 1385 | 1343 | GPT-4.1 |
| LMArena Text: writing and language | 1371 | 1313 | GPT-4.1 |
| LMArena Text: entertainment and media | 1365 | 1283 | GPT-4.1 |
| LMArena Vision: English | 1209 | Not measured | Only GPT-4.1 measured |
| LMArena Vision: Chinese | 1226 | Not measured | Only GPT-4.1 measured |
| LMArena Vision: reading text | 1218 | Not measured | Only GPT-4.1 measured |
| LMArena Vision: humor | 1196 | Not measured | Only GPT-4.1 measured |
| LMArena Vision: captioning | 1207 | Not measured | Only GPT-4.1 measured |
| LMArena Vision: recognizing things | 1208 | Not measured | Only GPT-4.1 measured |
| LMArena Vision: creative writing | 1210 | Not measured | Only GPT-4.1 measured |
| Neither model has a result on the other 15 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | GPT-4.1 | 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
o3 Mini costs less
Repository review
50K input + 3K output tokens
o3 Mini costs less
Agent loop
200K input + 10K output tokens
o3 Mini 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 | OpenAI o3 Mini |
|---|---|---|
| Maker | OpenAI | OpenAI |
| Weights | No public weights listed | No public weights listed |
| Released | April 14, 2025 | January 31, 2025 |
| Context window | 1.05M | 200K |
| Input $/Mtok | $2.00 | $1.10 |
| Output $/Mtok | $8.00 | $4.40 |
| Coding index | 46.5 | 52.1 |
| Independent measurements behind it | 2 | 2 |
| Cost per solved task | $0.37 | Not computable |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is GPT-4.1 better than o3 Mini for coding?
Pick o3 Mini for coding: it scores 52.1 on the Vibe Coding Index against 46.5 for GPT-4.1. Pick GPT-4.1 when the context window is larger, 1.05M against 200K tokens, or when what matters is Terminal-Bench Hard (Artificial Analysis run) or LMArena Text: coding, where it leads.
Which is cheaper, GPT-4.1 or o3 Mini?
GPT-4.1 costs $2.00 per million input tokens and $8.00 per million output tokens; o3 Mini costs $1.10 and $4.40. Cost per solved task is known for GPT-4.1 only.
Which has the bigger context window, GPT-4.1 or o3 Mini?
GPT-4.1, with 1.05M tokens against 200K.
How many benchmarks is the GPT-4.1 vs o3 Mini comparison based on?
63 benchmarks have a result for both models as of October 21, 2026. GPT-4.1's coding index rests on 2 independent benchmarks and o3 Mini's on 2. Where only one model has a result, the page says so instead of naming a winner.