GPT-4.1 Mini vs o4 Mini
o4 Mini leads GPT-4.1 Mini on the Artificial Analysis Intelligence Index, 16.7 to 10.2, and GPT-4.1 Mini costs 2.8x less per output token ($1.60 vs $4.40 per million). Updated October 21, 2026; 85 benchmarks have a result for both.
GPT-4.1 Mini or o4 Mini: which to pick
Neither model has a coding score yet, so the two cannot be ranked on coding.
Pick GPT-4.1 Mini for output tokens 2.8x cheaper ($1.60 vs $4.40 per million) and a larger context window (1.05M against 200K tokens).
- Shared results
- 85
- GPT-4.1 Mini only
- 1
- o4 Mini only
- 13
- 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
o4 Mini
o4 Mini leads, 16.7 against 10.2.
Same board, both measured
Reasoning
GPQA Diamond
o4 Mini
o4 Mini leads, 74.5% against 67.9%.
Same board, both measured
Math
AIME
o4 Mini
o4 Mini leads, 83.7% against 49.4%.
Same board, both measured
Knowledge
MMLU Pro
o4 Mini
o4 Mini leads, 80.6% against 77.2%.
Same board, both measured
Web design
Design Arena: websites
GPT-4.1 Mini
GPT-4.1 Mini leads, 997 against 985.
Same board, both measured
Long documents
Listed context window
GPT-4.1 Mini
GPT-4.1 Mini takes 1.05M tokens against 200K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
GPT-4.1 Mini
GPT-4.1 Mini $0.0012, o4 Mini $0.0033 per turn.
List prices
Cost per solved task
One SWE-bench Verified task, solved
No call
Only GPT-4.1 Mini has the number, $1.818.
Directional only
At a glance
- Coding index
- GPT-4.1 Mini not benchmarked, o4 Mini not benchmarked.
- Widest category
- Math, 22.5 points apart on average over 10 shared benchmarks.
- Widest single gap
- ARC-AGI: GPT-4.1 Mini 3.5% against o4 Mini 58.7%, 55.2 points apart on a 0 to 100 scale.
- Output price
- GPT-4.1 Mini $1.60 against o4 Mini $4.40 per million output tokens, 2.8x apart.
- Context window
- GPT-4.1 Mini takes 1.05M tokens, o4 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 Mini | Bars | o4 Mini | Ties |
|---|---|---|---|---|
| Coding | 0 | 8 | ||
| Intelligence | 0 | 2 | ||
| Agentic work | 0 | 2 | ||
| Reasoning | 1 | 14 | ||
| Math | 0 | 10 | ||
| Knowledge | 1 | 11 | ||
| Web design | 4 | 2 | ||
| General | 7 | 23 | ||
| All shared boards | 13 | 72 |
CodingLike-for-likeSix of these boards feed the Vibe Coding Index08
| Benchmark | GPT-4.1 Mini | o4 Mini | Leader |
|---|---|---|---|
| Aider polyglot | 32.4% | 72.0% | o4 Mini |
| SWE-bench Verified | 23.9% | 64.6% | o4 Mini |
| SWE-bench Multimodal | Not measured | 33.9% | Only o4 Mini measured |
| AA Coding Index | 20.2 | Not measured | Only GPT-4.1 Mini measured |
| LiveCodeBench (Vals AI) | 58.2% | 82.2% | o4 Mini |
| LiveCodeBench (Artificial Analysis run) | 48.3% | 85.9% | o4 Mini |
| Terminal-Bench Hard (Artificial Analysis run) | 7.6% | 15.2% | o4 Mini |
| GSO-Bench | Not measured | 3.6% | Only o4 Mini measured |
| WeirdML | 37.6% | 52.6% | o4 Mini |
| LMArena Text: coding | 1367 | 1368 | o4 Mini |
| LMArena Text: software and IT | 1360 | 1367 | o4 Mini |
| SciCode | Not measured | 10.8% | Only o4 Mini measured |
| 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 Mini | o4 Mini | Leader |
|---|---|---|---|
| AA Intelligence Index | 10.2 | 16.7 | o4 Mini |
| Epoch Capabilities Index | 134.9 | 145.5 | o4 Mini |
Agentic workLike-for-likePublic boards, shown as published, kept out of the index02
| Benchmark | GPT-4.1 Mini | o4 Mini | Leader |
|---|---|---|---|
| τ²-Bench Telecom | 52.9% | 55.6% | o4 Mini |
| METR time horizons | Not measured | 63.9% | Only o4 Mini measured |
| Berkeley Function Calling Leaderboard (BFCL) | 50.4% | 53.2% | o4 Mini |
| Neither model has a result on the other 38 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index114
| Benchmark | GPT-4.1 Mini | o4 Mini | Leader |
|---|---|---|---|
| GPQA Diamond | 67.9% | 74.5% | o4 Mini |
| MMMU Pro (Vals AI) | 70.5% | 79.7% | o4 Mini |
| GPQA Diamond (Artificial Analysis run) | 66.4% | 78.4% | o4 Mini |
| Humanity's Last Exam (Artificial Analysis run) | 5.0% | 16.5% | o4 Mini |
| GPQA Diamond (Epoch AI run) | 65.8% | 79.6% | o4 Mini |
| ARC-AGI | 3.5% | 58.7% | o4 Mini |
| ARC-AGI-2 | 0.0% | 6.1% | o4 Mini |
| SimpleBench | Not measured | 38.7% | Only o4 Mini measured |
| Chess puzzles | 1.0% | 22.0% | o4 Mini |
| Mystery game puzzles | 7.0% | 5.0% | GPT-4.1 Mini |
| VPCT | Not measured | 57.5% | Only o4 Mini measured |
| LMArena Text: hard prompts | 1349 | 1351 | o4 Mini |
| LMArena Text: expert | 1338 | 1343 | o4 Mini |
| LMArena Text: hard prompts in English | 1362 | 1366 | o4 Mini |
| LMArena Vision: diagrams | 1182 | 1197 | o4 Mini |
| LMArena Vision: homework | 1214 | 1234 | o4 Mini |
| Kagi LLM Benchmark | 48.6% | 67.6% | o4 Mini |
| 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 Mini | o4 Mini | Leader |
|---|---|---|---|
| AIME | 49.4% | 83.7% | o4 Mini |
| MATH 500 (Vals AI) | 88.0% | 94.2% | o4 Mini |
| MGSM (Vals AI) | 87.8% | 93.4% | o4 Mini |
| AA Math Index | 46.3 | 90.7 | o4 Mini |
| AIME 2025 (Artificial Analysis run) | 46.3% | 90.7% | o4 Mini |
| OTIS Mock AIME | 44.7% | 81.7% | o4 Mini |
| FrontierMath, tiers 1 to 3 | 6.7% | 36.1% | o4 Mini |
| FrontierMath, tier 4 | Not measured | 4.9% | Only o4 Mini measured |
| MATH level 5 | 87.3% | 97.8% | o4 Mini |
| LMArena Text: math | 1343 | 1389 | o4 Mini |
| LMArena Text: mathematical work | 1347 | 1379 | o4 Mini |
| Neither model has a result on the other 2 boards here | |||
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index111
| Benchmark | GPT-4.1 Mini | o4 Mini | Leader |
|---|---|---|---|
| MMLU Pro | 77.2% | 80.6% | o4 Mini |
| LegalBench (Vals AI) | 78.0% | 79.2% | o4 Mini |
| CorpFin (Vals AI) | 57.9% | 59.0% | o4 Mini |
| TaxEval (Vals AI) | 71.9% | 74.8% | o4 Mini |
| MortgageTax (Vals AI) | 65.5% | 64.8% | GPT-4.1 Mini |
| MedQA (Vals AI) | 84.6% | 96.0% | o4 Mini |
| MedCode (Vals AI) | Not measured | 33.8% | Only o4 Mini measured |
| MMLU Pro (Artificial Analysis run) | 78.1% | 83.2% | o4 Mini |
| SimpleQA Verified | 12.7% | 19.6% | o4 Mini |
| GeoBench | Not measured | 64.0% | Only o4 Mini measured |
| LMArena Text: science | 1328 | 1354 | o4 Mini |
| LMArena Text: medicine and healthcare | 1324 | 1361 | o4 Mini |
| LMArena Text: legal and government | 1343 | 1350 | o4 Mini |
| LMArena Text: business and finance | 1322 | 1325 | o4 Mini |
| FACTS Benchmark Suite | Not measured | 28.1% | Only o4 Mini measured |
| Neither model has a result on the other 3 boards here | |||
Web designLike-for-likePublic boards, shown as published, kept out of the index42
| Benchmark | GPT-4.1 Mini | o4 Mini | Leader |
|---|---|---|---|
| Design Arena: websites | 997 | 985 | GPT-4.1 Mini |
| Design Arena: UI components | 961 | 983 | o4 Mini |
| Design Arena: game dev | 1071 | 1003 | GPT-4.1 Mini |
| Design Arena: data viz | 1034 | 990 | GPT-4.1 Mini |
| Design Arena: 3D | 837 | 854 | o4 Mini |
| Design Arena: all code categories | 994 | 976 | GPT-4.1 Mini |
| Neither model has a result on the other 3 boards here | |||
GeneralLike-for-likePublic boards, shown as published, kept out of the index723
| Benchmark | GPT-4.1 Mini | o4 Mini | Leader |
|---|---|---|---|
| SAGE (Vals AI) | Not measured | 41.1% | Only o4 Mini measured |
| MedScribe (Vals AI) | Not measured | 69.1% | Only o4 Mini measured |
| IFBench | 38.3% | 68.7% | o4 Mini |
| Long context reasoning (AA-LCR) | 44.0% | 61.0% | o4 Mini |
| DTBench | 68.8% | 77.6% | o4 Mini |
| LMCA | 21.1% | 26.5% | o4 Mini |
| Fiction.LiveBench | 44.4% | 77.8% | o4 Mini |
| Creative writing (Lech Mazur) | Not measured | 75.0% | Only o4 Mini measured |
| LMArena Text | 1341 | 1353 | o4 Mini |
| LMArena Text: instruction following | 1333 | 1320 | GPT-4.1 Mini |
| LMArena Text: creative writing | 1299 | 1294 | GPT-4.1 Mini |
| LMArena Vision | 1181 | 1194 | o4 Mini |
| LMArena Text: English | 1356 | 1367 | o4 Mini |
| LMArena Text: non-English | 1318 | 1337 | o4 Mini |
| LMArena Text: Chinese | 1329 | 1354 | o4 Mini |
| LMArena Text: German | 1350 | 1336 | GPT-4.1 Mini |
| LMArena Text: Japanese | 1290 | 1308 | o4 Mini |
| LMArena Text: Korean | 1298 | 1312 | o4 Mini |
| LMArena Text: French | 1358 | 1364 | o4 Mini |
| LMArena Text: Spanish | 1319 | 1346 | o4 Mini |
| LMArena Text: Russian | 1324 | 1334 | o4 Mini |
| LMArena Text: Polish | 1326 | 1358 | o4 Mini |
| LMArena Text: multi-turn | 1354 | 1350 | GPT-4.1 Mini |
| LMArena Text: longer queries | 1344 | 1315 | GPT-4.1 Mini |
| LMArena Text: writing and language | 1319 | 1316 | GPT-4.1 Mini |
| LMArena Text: entertainment and media | 1300 | 1308 | o4 Mini |
| LMArena Vision: English | 1191 | 1200 | o4 Mini |
| LMArena Vision: Chinese | 1186 | 1218 | o4 Mini |
| LMArena Vision: reading text | 1188 | 1197 | o4 Mini |
| LMArena Vision: humor | 1182 | 1199 | o4 Mini |
| LMArena Vision: captioning | 1174 | 1204 | o4 Mini |
| LMArena Vision: recognizing things | 1187 | 1218 | o4 Mini |
| LMArena Vision: creative writing | 1182 | 1166 | GPT-4.1 Mini |
| Neither model has a result on the other 13 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | GPT-4.1 Mini | o4 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-4.1 Mini costs less
Repository review
50K input + 3K output tokens
GPT-4.1 Mini costs less
Agent loop
200K input + 10K output tokens
GPT-4.1 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 Mini | OpenAI o4 Mini |
|---|---|---|
| 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 | $0.40 | $1.10 |
| Output $/Mtok | $1.60 | $4.40 |
| Coding index | Not benchmarked | Not benchmarked |
| Independent measurements behind it | 0 | 0 |
| Cost per solved task | $1.818 | Not computable |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is GPT-4.1 Mini better than o4 Mini for coding?
Neither model has a coding score yet, so the two cannot be ranked on coding. Pick GPT-4.1 Mini for output tokens 2.8x cheaper ($1.60 vs $4.40 per million) and a larger context window (1.05M against 200K tokens).
Which is cheaper, GPT-4.1 Mini or o4 Mini?
GPT-4.1 Mini costs $0.40 per million input tokens and $1.60 per million output tokens; o4 Mini costs $1.10 and $4.40. Cost per solved task is known for GPT-4.1 Mini only.
Which has the bigger context window, GPT-4.1 Mini or o4 Mini?
GPT-4.1 Mini, with 1.05M tokens against 200K.
How many benchmarks is the GPT-4.1 Mini vs o4 Mini comparison based on?
85 benchmarks have a result for both models as of October 21, 2026. GPT-4.1 Mini's coding index rests on 0 independent benchmarks and o4 Mini's on 0. Where only one model has a result, the page says so instead of naming a winner.