GPT-5.2 vs o3 Mini
GPT-5.2 leads o3 Mini on the Artificial Analysis Intelligence Index, 30.4 to 12.5, and o3 Mini costs 3.2x less per output token ($4.40 vs $14.00 per million). Updated October 22, 2026; 62 benchmarks have a result for both.
GPT-5.2 or o3 Mini: which to pick
Only GPT-5.2 has a coding score, 55.9 on the Vibe Coding Index; o3 Mini has none, so the two cannot be ranked on coding.
Pick o3 Mini for output tokens 3.2x cheaper ($4.40 vs $14.00 per million) and work measured by MedQA (Vals AI), where it leads.
- Shared results
- 62
- GPT-5.2 only
- 52
- o3 Mini only
- 9
- 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-5.2 has a coding score, so no call is made.
One side not measured
Intelligence
AA Intelligence Index
GPT-5.2
GPT-5.2 leads, 30.4 against 12.5.
Same board, both measured
Reasoning
GPQA Diamond
GPT-5.2
GPT-5.2 leads, 91.7% against 75.5%.
Same board, both measured
Math
AIME
GPT-5.2
GPT-5.2 leads, 96.9% against 86.5%.
Same board, both measured
Knowledge
MMLU Pro
GPT-5.2
GPT-5.2 leads, 86.2% against 78.7%.
Same board, both measured
Web design
Design Arena: websites
No call
Only GPT-5.2 has a Design Arena: websites result, 1195.
Directional only
Long documents
Listed context window
GPT-5.2
GPT-5.2 takes 400K tokens against 200K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
o3 Mini
GPT-5.2 $0.0088, o3 Mini $0.0033 per turn.
List prices
Cost per solved task
One SWE-bench Verified task, solved
No call
Only GPT-5.2 has the number, $1.91.
Directional only
At a glance
- Coding index
- GPT-5.2 55.9 from 3 benchmarks, o3 Mini not benchmarked.
- Widest category
- Agentic work, 53.5 points apart on average over 1 shared benchmark.
- Widest single gap
- τ²-Bench Telecom: GPT-5.2 84.8% against o3 Mini 31.3%, 53.5 points apart on a 0 to 100 scale.
- Output price
- GPT-5.2 $14.00 against o3 Mini $4.40 per million output tokens, 3.2x apart.
- Context window
- GPT-5.2 takes 400K 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-5.2 | Bars | o3 Mini | Ties |
|---|---|---|---|---|
| Coding | 8 | 0 | ||
| Intelligence | 2 | 0 | ||
| Agentic work | 1 | 0 | ||
| Reasoning | 12 | 0 | ||
| Math | 7 | 0 | ||
| Knowledge | 10 | 1 | ||
| General | 21 | 0 | ||
| All shared boards | 61 | 1 |
CodingLike-for-likeSix of these boards feed the Vibe Coding Index80
| Benchmark | GPT-5.2 | o3 Mini | Leader |
|---|---|---|---|
| Aider polyglot | Not measured | 60.4% | Only o3 Mini measured |
| SWE-bench Verified | 72.8% | 42.4% | GPT-5.2 |
| SWE-bench Lite | Not measured | 32.3% | Only o3 Mini measured |
| SWE-bench Multilingual | 66.7% | Not measured | Only GPT-5.2 measured |
| LMArena WebDev | 1417 | Not measured | Only GPT-5.2 measured |
| LiveCodeBench (Vals AI) | 85.4% | 71.5% | GPT-5.2 |
| SWE-bench Verified (Vals AI) | 75.8% | Not measured | Only GPT-5.2 measured |
| Vibe Code Bench (Vals AI) | 53.5% | Not measured | Only GPT-5.2 measured |
| LiveCodeBench (Artificial Analysis run) | 89.4% | 73.4% | GPT-5.2 |
| SciCode | Not measured | 42.8% | Only o3 Mini measured |
| Terminal-Bench Hard (Artificial Analysis run) | 47.0% | 6.8% | GPT-5.2 |
| Terminal-Bench | 64.9% | Not measured | Only GPT-5.2 measured |
| GSO-Bench | 27.5% | 1.3% | GPT-5.2 |
| WeirdML | 72.2% | 43.7% | GPT-5.2 |
| Cybench | Not measured | 22.5% | Only o3 Mini measured |
| ALE-Bench | 1293.5 | Not measured | Only GPT-5.2 measured |
| LMArena Text: coding | 1442 | 1378 | GPT-5.2 |
| LMArena Text: software and IT | 1434 | 1364 | GPT-5.2 |
| LMArena WebDev: HTML | 1427 | Not measured | Only GPT-5.2 measured |
| SciCode | Not measured | 7.7% | Only o3 Mini measured |
| Neither model has a result on the other 19 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index20
| Benchmark | GPT-5.2 | o3 Mini | Leader |
|---|---|---|---|
| AA Intelligence Index | 30.4 | 12.5 | GPT-5.2 |
| Epoch Capabilities Index | 153.7 | 140.2 | GPT-5.2 |
Agentic workLike-for-likePublic boards, shown as published, kept out of the index10
| Benchmark | GPT-5.2 | o3 Mini | Leader |
|---|---|---|---|
| Design Arena: agents building web apps | 1086 | Not measured | Only GPT-5.2 measured |
| Design Arena: agents building full-stack apps | 1043 | Not measured | Only GPT-5.2 measured |
| Design Arena: agents building mobile apps | 1093 | Not measured | Only GPT-5.2 measured |
| Design Arena: agents building Android apps | 1059 | Not measured | Only GPT-5.2 measured |
| Design Arena: agents building Godot games | 1142 | Not measured | Only GPT-5.2 measured |
| τ²-Bench Telecom | 84.8% | 31.3% | GPT-5.2 |
| METR time horizons | 75.3% | Not measured | Only GPT-5.2 measured |
| Remote Labor Index | 2.5% | Not measured | Only GPT-5.2 measured |
| GDPval | 49.7% | Not measured | Only GPT-5.2 measured |
| DeepResearch Bench | 41.1% | Not measured | Only GPT-5.2 measured |
| Vending-Bench 2 | $3,591 | Not measured | Only GPT-5.2 measured |
| Berkeley Function Calling Leaderboard (BFCL) | 55.9% | Not measured | Only GPT-5.2 measured |
| Neither model has a result on the other 29 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index120
| Benchmark | GPT-5.2 | o3 Mini | Leader |
|---|---|---|---|
| GPQA Diamond | 91.7% | 75.5% | GPT-5.2 |
| MMMU Pro (Vals AI) | 86.7% | Not measured | Only GPT-5.2 measured |
| GPQA Diamond (Artificial Analysis run) | 90.3% | 77.3% | GPT-5.2 |
| Humanity's Last Exam (Artificial Analysis run) | 37.7% | 12.0% | GPT-5.2 |
| GPQA Diamond (Epoch AI run) | 91.4% | 77.0% | GPT-5.2 |
| ARC-AGI | 86.2% | 34.5% | GPT-5.2 |
| ARC-AGI-2 | 52.9% | 3.0% | GPT-5.2 |
| SimpleBench | 45.8% | 22.8% | GPT-5.2 |
| Chess puzzles | 48.0% | 15.0% | GPT-5.2 |
| Mystery game puzzles | 23.0% | 7.0% | GPT-5.2 |
| EBR-bench | 23.0% | Not measured | Only GPT-5.2 measured |
| VPCT | 84.0% | Not measured | Only GPT-5.2 measured |
| LMArena Text: hard prompts | 1428 | 1365 | GPT-5.2 |
| LMArena Text: expert | 1445 | 1364 | GPT-5.2 |
| LMArena Text: hard prompts in English | 1431 | 1375 | GPT-5.2 |
| LMArena Vision: diagrams | 1265 | Not measured | Only GPT-5.2 measured |
| LMArena Vision: homework | 1276 | Not measured | Only GPT-5.2 measured |
| Kagi LLM Benchmark | 73.3% | Not measured | Only GPT-5.2 measured |
| Neither model has a result on the other 4 boards here | |||
MathLike-for-likePublic boards, shown as published, kept out of the index70
| Benchmark | GPT-5.2 | o3 Mini | Leader |
|---|---|---|---|
| AIME | 96.9% | 86.5% | GPT-5.2 |
| MATH 500 (Vals AI) | Not measured | 91.8% | Only o3 Mini measured |
| MGSM (Vals AI) | 94.0% | 91.3% | GPT-5.2 |
| AA Math Index | 99.0 | Not measured | Only GPT-5.2 measured |
| AIME 2025 (Artificial Analysis run) | 99.0% | Not measured | Only GPT-5.2 measured |
| OTIS Mock AIME | 96.1% | 76.9% | GPT-5.2 |
| FrontierMath, tiers 1 to 3 | 67.4% | 18.6% | GPT-5.2 |
| FrontierMath, tier 4 | 31.7% | 0.0% | GPT-5.2 |
| ProofBench | 15.0% | Not measured | Only GPT-5.2 measured |
| MATH level 5 | Not measured | 96.5% | Only o3 Mini measured |
| LMArena Text: math | 1440 | 1396 | GPT-5.2 |
| LMArena Text: mathematical work | 1442 | 1399 | GPT-5.2 |
| Neither model has a result on the other 1 board here | |||
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index101
| Benchmark | GPT-5.2 | o3 Mini | Leader |
|---|---|---|---|
| MMLU Pro | 86.2% | 78.7% | GPT-5.2 |
| LegalBench (Vals AI) | 82.8% | 71.5% | GPT-5.2 |
| CaseLaw (Vals AI) | 66.0% | Not measured | Only GPT-5.2 measured |
| CorpFin (Vals AI) | 65.9% | 45.3% | GPT-5.2 |
| TaxEval (Vals AI) | 75.8% | 69.4% | GPT-5.2 |
| MortgageTax (Vals AI) | 67.1% | Not measured | Only GPT-5.2 measured |
| MedQA (Vals AI) | 94.1% | 94.8% | o3 Mini |
| MedCode (Vals AI) | 49.8% | Not measured | Only GPT-5.2 measured |
| MMLU Pro (Artificial Analysis run) | 87.4% | 80.2% | GPT-5.2 |
| SimpleQA Verified | 37.1% | 15.3% | GPT-5.2 |
| LMArena Text: science | 1425 | 1339 | GPT-5.2 |
| LMArena Text: medicine and healthcare | 1425 | 1330 | GPT-5.2 |
| LMArena Text: legal and government | 1427 | 1328 | GPT-5.2 |
| LMArena Text: business and finance | 1414 | 1313 | GPT-5.2 |
| FACTS Benchmark Suite | 48.5% | Not measured | Only GPT-5.2 measured |
| Neither model has a result on the other 3 boards here | |||
Web designDirectional onlyPublic boards, shown as published, kept out of the index8 boards, none shared
| Benchmark | GPT-5.2 | o3 Mini | Leader |
|---|---|---|---|
| Design Arena: websites | 1195 | Not measured | Only GPT-5.2 measured |
| Design Arena: UI components | 1190 | Not measured | Only GPT-5.2 measured |
| Design Arena: game dev | 1195 | Not measured | Only GPT-5.2 measured |
| Design Arena: data viz | 1202 | Not measured | Only GPT-5.2 measured |
| Design Arena: 3D | 1079 | Not measured | Only GPT-5.2 measured |
| Design Arena: all code categories | 1170 | Not measured | Only GPT-5.2 measured |
| Design Arena: SVG | 1139 | Not measured | Only GPT-5.2 measured |
| Design Arena: ASCII art | 1152 | Not measured | Only GPT-5.2 measured |
| Neither model has a result on the other 1 board here | |||
GeneralLike-for-likePublic boards, shown as published, kept out of the index210
| Benchmark | GPT-5.2 | o3 Mini | Leader |
|---|---|---|---|
| SAGE (Vals AI) | 49.3% | Not measured | Only GPT-5.2 measured |
| MedScribe (Vals AI) | 84.4% | Not measured | Only GPT-5.2 measured |
| IFBench | 75.4% | 67.1% | GPT-5.2 |
| Long context reasoning (AA-LCR) | 82.7% | 43.0% | GPT-5.2 |
| DTBench | 90.9% | 68.8% | GPT-5.2 |
| LMCA | 43.9% | 19.0% | GPT-5.2 |
| Fiction.LiveBench | Not measured | 50.0% | Only o3 Mini measured |
| Creative writing (Lech Mazur) | Not measured | 61.7% | Only o3 Mini measured |
| CL-bench | 18.2% | Not measured | Only GPT-5.2 measured |
| Furniture assembly | 38.3% | Not measured | Only GPT-5.2 measured |
| LMArena Text | 1416 | 1337 | GPT-5.2 |
| LMArena Text: instruction following | 1409 | 1337 | GPT-5.2 |
| LMArena Text: creative writing | 1376 | 1286 | GPT-5.2 |
| LMArena Vision | 1246 | Not measured | Only GPT-5.2 measured |
| LMArena Text: English | 1422 | 1351 | GPT-5.2 |
| LMArena Text: non-English | 1405 | 1319 | GPT-5.2 |
| LMArena Text: Chinese | 1447 | 1379 | GPT-5.2 |
| LMArena Text: German | 1444 | 1303 | GPT-5.2 |
| LMArena Text: Japanese | 1420 | 1286 | GPT-5.2 |
| LMArena Text: Korean | 1374 | 1313 | GPT-5.2 |
| LMArena Text: French | 1454 | 1334 | GPT-5.2 |
| LMArena Text: Spanish | 1413 | 1321 | GPT-5.2 |
| LMArena Text: Russian | 1415 | 1304 | GPT-5.2 |
| LMArena Text: Polish | 1426 | 1294 | GPT-5.2 |
| LMArena Text: multi-turn | 1419 | 1320 | GPT-5.2 |
| LMArena Text: longer queries | 1413 | 1343 | GPT-5.2 |
| LMArena Text: writing and language | 1392 | 1313 | GPT-5.2 |
| LMArena Text: entertainment and media | 1378 | 1283 | GPT-5.2 |
| LMArena Vision: English | 1243 | Not measured | Only GPT-5.2 measured |
| LMArena Vision: Chinese | 1305 | Not measured | Only GPT-5.2 measured |
| LMArena Vision: reading text | 1257 | Not measured | Only GPT-5.2 measured |
| LMArena Vision: humor | 1227 | Not measured | Only GPT-5.2 measured |
| LMArena Vision: captioning | 1267 | Not measured | Only GPT-5.2 measured |
| LMArena Vision: recognizing things | 1232 | Not measured | Only GPT-5.2 measured |
| LMArena Vision: creative writing | 1225 | Not measured | Only GPT-5.2 measured |
| LMArena Document | 1405 | Not measured | Only GPT-5.2 measured |
| Neither model has a result on the other 10 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | GPT-5.2 | 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-5.2 | OpenAI o3 Mini |
|---|---|---|
| Maker | OpenAI | OpenAI |
| Weights | No public weights listed | No public weights listed |
| Released | December 10, 2025 | January 31, 2025 |
| Context window | 400K | 200K |
| Input $/Mtok | $1.75 | $1.10 |
| Output $/Mtok | $14.00 | $4.40 |
| Coding index | 55.9 | Not benchmarked |
| Independent measurements behind it | 3 | 0 |
| Cost per solved task | $1.91 | Not computable |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is GPT-5.2 better than o3 Mini for coding?
Only GPT-5.2 has a coding score, 55.9 on the Vibe Coding Index; o3 Mini has none, so the two cannot be ranked on coding. Pick o3 Mini for output tokens 3.2x cheaper ($4.40 vs $14.00 per million) and work measured by MedQA (Vals AI), where it leads.
Which is cheaper, GPT-5.2 or o3 Mini?
GPT-5.2 costs $1.75 per million input tokens and $14.00 per million output tokens; o3 Mini costs $1.10 and $4.40. Cost per solved task is known for GPT-5.2 only.
Which has the bigger context window, GPT-5.2 or o3 Mini?
GPT-5.2, with 400K tokens against 200K.
How many benchmarks is the GPT-5.2 vs o3 Mini comparison based on?
62 benchmarks have a result for both models as of October 22, 2026. GPT-5.2's coding index rests on 3 independent benchmarks and o3 Mini's on 0. Where only one model has a result, the page says so instead of naming a winner.