GPT-5.4 Mini vs o4 Mini
GPT-5.4 Mini leads o4 Mini on the Artificial Analysis Intelligence Index, 24.1 to 16.7, at about the same output price ($4.50 vs $4.40 per million). Updated October 22, 2026; 67 benchmarks have a result for both.
GPT-5.4 Mini or o4 Mini: which to pick
Only GPT-5.4 Mini has a coding score, 35.8 on the Vibe Coding Index; o4 Mini has none, so the two cannot be ranked on coding.
Pick o4 Mini for output tokens 1.0x cheaper ($4.40 vs $4.50 per million) and work measured by LiveCodeBench (Vals AI) or MMMU Pro (Vals AI), where it leads.
- Shared results
- 67
- GPT-5.4 Mini only
- 22
- o4 Mini only
- 31
- Like-for-like categories
- 7 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
Only GPT-5.4 Mini has a coding score, so no call is made.
One side not measured
Intelligence
AA Intelligence Index
GPT-5.4 Mini
GPT-5.4 Mini leads, 24.1 against 16.7.
Same board, both measured
Agentic work
AA Agentic Index
No call
Only GPT-5.4 Mini has a AA Agentic Index result, 17.9.
Directional only
Reasoning
GPQA Diamond
GPT-5.4 Mini
GPT-5.4 Mini leads, 83.1% against 74.5%.
Same board, both measured
Math
AIME
GPT-5.4 Mini
GPT-5.4 Mini leads, 95.6% against 83.7%.
Same board, both measured
Knowledge
MMLU Pro
GPT-5.4 Mini
GPT-5.4 Mini leads, 84.5% against 80.6%.
Same board, both measured
Web design
Design Arena: websites
No call
Only o4 Mini has a Design Arena: websites result, 985.
Directional only
Long documents
Listed context window
GPT-5.4 Mini
GPT-5.4 Mini takes 400K tokens against 200K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
GPT-5.4 Mini
GPT-5.4 Mini $0.0030, o4 Mini $0.0033 per turn.
List prices
Cost per solved task
One SWE-bench Verified task, solved
No call
Only GPT-5.4 Mini has the number, $0.70.
Directional only
At a glance
- Coding index
- GPT-5.4 Mini 35.8 from 5 benchmarks, o4 Mini not benchmarked.
- Widest category
- Agentic work, 27.8 points apart on average over 1 shared benchmark.
- Widest single gap
- Terminal-Bench Hard (Artificial Analysis run): GPT-5.4 Mini 52.3% against o4 Mini 15.2%, 37.1 points apart on a 0 to 100 scale.
- Output price
- GPT-5.4 Mini $4.50 against o4 Mini $4.40 per million output tokens, 1.0x apart.
- Context window
- GPT-5.4 Mini takes 400K 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-5.4 Mini | Bars | o4 Mini | Ties |
|---|---|---|---|---|
| Coding | 4 | 1 | ||
| Intelligence | 2 | 0 | ||
| Agentic work | 1 | 0 | ||
| Reasoning | 13 | 2 | ||
| Math | 6 | 0 | ||
| Knowledge | 7 | 2 | ||
| General | 29 | 0 | ||
| All shared boards | 62 | 5 |
CodingLike-for-likeSix of these boards feed the Vibe Coding Index41
| Benchmark | GPT-5.4 Mini | o4 Mini | Leader |
|---|---|---|---|
| Aider polyglot | Not measured | 72.0% | Only o4 Mini measured |
| SWE-bench Verified | Not measured | 64.6% | Only o4 Mini measured |
| SWE-bench Multimodal | Not measured | 33.9% | Only o4 Mini measured |
| LMArena WebDev | 1397 | Not measured | Only GPT-5.4 Mini measured |
| AA Coding Index | 56.1 | Not measured | Only GPT-5.4 Mini measured |
| LiveCodeBench (Vals AI) | 81.5% | 82.2% | o4 Mini |
| SWE-bench Verified (Vals AI) | 73.0% | Not measured | Only GPT-5.4 Mini measured |
| Terminal-Bench 4 (Vals AI) | 2.5% | Not measured | Only GPT-5.4 Mini measured |
| Vibe Code Bench (Vals AI) | 48.0% | Not measured | Only GPT-5.4 Mini measured |
| Code migration (Vals AI) | 12.9% | Not measured | Only GPT-5.4 Mini measured |
| ProgramBench (Vals AI) | 0.0% | Not measured | Only GPT-5.4 Mini measured |
| Terminal-Bench 2.1 (Vals AI) | 54.7% | Not measured | Only GPT-5.4 Mini measured |
| LiveCodeBench (Artificial Analysis run) | Not measured | 85.9% | Only o4 Mini measured |
| SciCode | 52.1% | Not measured | Only GPT-5.4 Mini measured |
| Terminal-Bench Hard (Artificial Analysis run) | 52.3% | 15.2% | GPT-5.4 Mini |
| FrontierCode | 27.0% | Not measured | Only GPT-5.4 Mini measured |
| GSO-Bench | Not measured | 3.6% | Only o4 Mini measured |
| WeirdML | 60.3% | 52.6% | GPT-5.4 Mini |
| ALE-Bench | 1188.6 | Not measured | Only GPT-5.4 Mini measured |
| LMArena Text: coding | 1438 | 1368 | GPT-5.4 Mini |
| LMArena Text: software and IT | 1436 | 1367 | GPT-5.4 Mini |
| LMArena WebDev: React | 1386 | Not measured | Only GPT-5.4 Mini measured |
| LMArena WebDev: HTML | 1419 | Not measured | Only GPT-5.4 Mini measured |
| SciCode | Not measured | 10.8% | Only o4 Mini measured |
| Neither model has a result on the other 15 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index20
| Benchmark | GPT-5.4 Mini | o4 Mini | Leader |
|---|---|---|---|
| AA Intelligence Index | 24.1 | 16.7 | GPT-5.4 Mini |
| Epoch Capabilities Index | 148.7 | 145.5 | GPT-5.4 Mini |
Agentic workLike-for-likePublic boards, shown as published, kept out of the index10
| Benchmark | GPT-5.4 Mini | o4 Mini | Leader |
|---|---|---|---|
| AA Agentic Index | 17.9 | Not measured | Only GPT-5.4 Mini measured |
| Finance Agent (Vals AI) | 45.4% | Not measured | Only GPT-5.4 Mini measured |
| Tax Agent Bench (Vals AI) | 8.8% | Not measured | Only GPT-5.4 Mini measured |
| Legal Research Bench (Vals AI) | 12.5% | Not measured | Only GPT-5.4 Mini measured |
| Excel Modeling Benchmark (Vals AI) | 45.4% | Not measured | Only GPT-5.4 Mini measured |
| τ²-Bench Telecom | 83.3% | 55.6% | GPT-5.4 Mini |
| METR time horizons | Not measured | 63.9% | Only o4 Mini measured |
| DeepResearch Bench | 36.3% | Not measured | Only GPT-5.4 Mini measured |
| Berkeley Function Calling Leaderboard (BFCL) | Not measured | 53.2% | Only o4 Mini measured |
| Neither model has a result on the other 32 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index132
| Benchmark | GPT-5.4 Mini | o4 Mini | Leader |
|---|---|---|---|
| GPQA Diamond | 83.1% | 74.5% | GPT-5.4 Mini |
| MMMU Pro (Vals AI) | 79.3% | 79.7% | o4 Mini |
| GPQA Diamond (Artificial Analysis run) | 87.5% | 78.4% | GPT-5.4 Mini |
| Humanity's Last Exam (Artificial Analysis run) | 28.1% | 16.5% | GPT-5.4 Mini |
| GPQA Diamond (Epoch AI run) | 86.9% | 79.6% | GPT-5.4 Mini |
| ARC-AGI | 63.7% | 58.7% | GPT-5.4 Mini |
| ARC-AGI-2 | 18.9% | 6.1% | GPT-5.4 Mini |
| SimpleBench | Not measured | 38.7% | Only o4 Mini measured |
| Chess puzzles | 23.0% | 22.0% | GPT-5.4 Mini |
| Mystery game puzzles | 11.0% | 5.0% | GPT-5.4 Mini |
| VPCT | Not measured | 57.5% | Only o4 Mini measured |
| LMArena Text: hard prompts | 1424 | 1351 | GPT-5.4 Mini |
| LMArena Text: expert | 1435 | 1343 | GPT-5.4 Mini |
| LMArena Text: hard prompts in English | 1420 | 1366 | GPT-5.4 Mini |
| LMArena Vision: diagrams | 1266 | 1197 | GPT-5.4 Mini |
| LMArena Vision: homework | 1285 | 1234 | GPT-5.4 Mini |
| Kagi LLM Benchmark | 37.9% | 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 index60
| Benchmark | GPT-5.4 Mini | o4 Mini | Leader |
|---|---|---|---|
| AIME | 95.6% | 83.7% | GPT-5.4 Mini |
| MATH 500 (Vals AI) | Not measured | 94.2% | Only o4 Mini measured |
| MGSM (Vals AI) | Not measured | 93.4% | Only o4 Mini measured |
| AA Math Index | Not measured | 90.7 | Only o4 Mini measured |
| AIME 2025 (Artificial Analysis run) | Not measured | 90.7% | Only o4 Mini measured |
| OTIS Mock AIME | 88.9% | 81.7% | GPT-5.4 Mini |
| FrontierMath, tiers 1 to 3 | 51.2% | 36.1% | GPT-5.4 Mini |
| FrontierMath, tier 4 | 9.8% | 4.9% | GPT-5.4 Mini |
| ProofBench | 21.0% | Not measured | Only GPT-5.4 Mini measured |
| MATH level 5 | Not measured | 97.8% | Only o4 Mini measured |
| LMArena Text: math | 1418 | 1389 | GPT-5.4 Mini |
| LMArena Text: mathematical work | 1429 | 1379 | GPT-5.4 Mini |
| Neither model has a result on the other 1 board here | |||
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index72
| Benchmark | GPT-5.4 Mini | o4 Mini | Leader |
|---|---|---|---|
| MMLU Pro | 84.5% | 80.6% | GPT-5.4 Mini |
| LegalBench (Vals AI) | Not measured | 79.2% | Only o4 Mini measured |
| CaseLaw (Vals AI) | 51.7% | Not measured | Only GPT-5.4 Mini measured |
| CorpFin (Vals AI) | 60.9% | 59.0% | GPT-5.4 Mini |
| TaxEval (Vals AI) | 71.2% | 74.8% | o4 Mini |
| MortgageTax (Vals AI) | 63.5% | 64.8% | o4 Mini |
| MedQA (Vals AI) | Not measured | 96.0% | Only o4 Mini measured |
| MedCode (Vals AI) | Not measured | 33.8% | Only o4 Mini measured |
| MMLU Pro (Artificial Analysis run) | Not measured | 83.2% | Only o4 Mini measured |
| SimpleQA Verified | 29.4% | 19.6% | GPT-5.4 Mini |
| GeoBench | Not measured | 64.0% | Only o4 Mini measured |
| LMArena Text: science | 1417 | 1354 | GPT-5.4 Mini |
| LMArena Text: medicine and healthcare | 1395 | 1361 | GPT-5.4 Mini |
| LMArena Text: legal and government | 1414 | 1350 | GPT-5.4 Mini |
| LMArena Text: business and finance | 1418 | 1325 | GPT-5.4 Mini |
| FACTS Benchmark Suite | Not measured | 28.1% | Only o4 Mini measured |
| Neither model has a result on the other 2 boards here | |||
Web designDirectional onlyPublic boards, shown as published, kept out of the index6 boards, none shared
| Benchmark | GPT-5.4 Mini | o4 Mini | Leader |
|---|---|---|---|
| Design Arena: websites | Not measured | 985 | Only o4 Mini measured |
| Design Arena: UI components | Not measured | 983 | Only o4 Mini measured |
| Design Arena: game dev | Not measured | 1003 | Only o4 Mini measured |
| Design Arena: data viz | Not measured | 991 | Only o4 Mini measured |
| Design Arena: 3D | Not measured | 854 | Only o4 Mini measured |
| Design Arena: all code categories | Not measured | 976 | Only o4 Mini measured |
| Neither model has a result on the other 3 boards here | |||
GeneralLike-for-likePublic boards, shown as published, kept out of the index290
| Benchmark | GPT-5.4 Mini | o4 Mini | Leader |
|---|---|---|---|
| SAGE (Vals AI) | 50.8% | 41.1% | GPT-5.4 Mini |
| MedScribe (Vals AI) | Not measured | 69.1% | Only o4 Mini measured |
| Vals Multimodal Index | 54.2% | Not measured | Only GPT-5.4 Mini measured |
| IFBench | 73.3% | 68.7% | GPT-5.4 Mini |
| Long context reasoning (AA-LCR) | 77.0% | 61.0% | GPT-5.4 Mini |
| DTBench | 80.0% | 77.6% | GPT-5.4 Mini |
| LMCA | 40.8% | 26.5% | GPT-5.4 Mini |
| Fiction.LiveBench | Not measured | 77.8% | Only o4 Mini measured |
| Creative writing (Lech Mazur) | Not measured | 75.0% | Only o4 Mini measured |
| LMArena Text | 1412 | 1353 | GPT-5.4 Mini |
| LMArena Text: instruction following | 1405 | 1320 | GPT-5.4 Mini |
| LMArena Text: creative writing | 1370 | 1294 | GPT-5.4 Mini |
| LMArena Vision | 1245 | 1194 | GPT-5.4 Mini |
| LMArena Text: English | 1412 | 1367 | GPT-5.4 Mini |
| LMArena Text: non-English | 1405 | 1337 | GPT-5.4 Mini |
| LMArena Text: Chinese | 1446 | 1354 | GPT-5.4 Mini |
| LMArena Text: German | 1408 | 1336 | GPT-5.4 Mini |
| LMArena Text: Japanese | 1375 | 1308 | GPT-5.4 Mini |
| LMArena Text: Korean | 1370 | 1312 | GPT-5.4 Mini |
| LMArena Text: French | 1441 | 1364 | GPT-5.4 Mini |
| LMArena Text: Spanish | 1405 | 1346 | GPT-5.4 Mini |
| LMArena Text: Russian | 1417 | 1334 | GPT-5.4 Mini |
| LMArena Text: Polish | 1415 | 1358 | GPT-5.4 Mini |
| LMArena Text: multi-turn | 1429 | 1350 | GPT-5.4 Mini |
| LMArena Text: longer queries | 1408 | 1315 | GPT-5.4 Mini |
| LMArena Text: writing and language | 1393 | 1316 | GPT-5.4 Mini |
| LMArena Text: entertainment and media | 1373 | 1308 | GPT-5.4 Mini |
| LMArena Vision: English | 1244 | 1200 | GPT-5.4 Mini |
| LMArena Vision: Chinese | 1286 | 1218 | GPT-5.4 Mini |
| LMArena Vision: reading text | 1253 | 1197 | GPT-5.4 Mini |
| LMArena Vision: humor | 1235 | 1199 | GPT-5.4 Mini |
| LMArena Vision: captioning | Not measured | 1204 | Only o4 Mini measured |
| LMArena Vision: recognizing things | 1218 | 1218 | GPT-5.4 Mini |
| LMArena Vision: creative writing | 1222 | 1166 | GPT-5.4 Mini |
| 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-5.4 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-5.4 Mini costs less
Repository review
50K input + 3K output tokens
GPT-5.4 Mini costs less
Agent loop
200K input + 10K output tokens
GPT-5.4 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-5.4 Mini | OpenAI o4 Mini |
|---|---|---|
| Maker | OpenAI | OpenAI |
| Weights | No public weights listed | No public weights listed |
| Released | March 17, 2026 | April 16, 2025 |
| Context window | 400K | 200K |
| Input $/Mtok | $0.75 | $1.10 |
| Output $/Mtok | $4.50 | $4.40 |
| Coding index | 35.8 | Not benchmarked |
| Independent measurements behind it | 5 | 0 |
| Cost per solved task | $0.70 | Not computable |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is GPT-5.4 Mini better than o4 Mini for coding?
Only GPT-5.4 Mini has a coding score, 35.8 on the Vibe Coding Index; o4 Mini has none, so the two cannot be ranked on coding. Pick o4 Mini for output tokens 1.0x cheaper ($4.40 vs $4.50 per million) and work measured by LiveCodeBench (Vals AI) or MMMU Pro (Vals AI), where it leads.
Which is cheaper, GPT-5.4 Mini or o4 Mini?
GPT-5.4 Mini costs $0.75 per million input tokens and $4.50 per million output tokens; o4 Mini costs $1.10 and $4.40. Cost per solved task is known for GPT-5.4 Mini only.
Which has the bigger context window, GPT-5.4 Mini or o4 Mini?
GPT-5.4 Mini, with 400K tokens against 200K.
How many benchmarks is the GPT-5.4 Mini vs o4 Mini comparison based on?
67 benchmarks have a result for both models as of October 22, 2026. GPT-5.4 Mini's coding index rests on 5 independent benchmarks and o4 Mini's on 0. Where only one model has a result, the page says so instead of naming a winner.