GPT-5.5 vs o3 Mini
Updated October 21, 2026. 57 benchmarks have a result for both. Coding is ranked on the Vibe Coding Index; every other board is shown as published.
vs boards won of 57 shared
Decision reading
Pick GPT-5.5 for coding: it scores 67.8 on the Vibe Coding Index against 52.1 for o3 Mini.
Pick o3 Mini when output tokens cost 6.8x less.
Model AGPT-5.5OpenAI67.8/1002 independent benchmarks$1.65 per solved taskModel Bo3 MiniOpenAI52.1/1002 independent benchmarksNo cost per solved task
- Shared results
- 57
- GPT-5.5 only
- 75
- o3 Mini only
- 13
- 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
GPT-5.5
GPT-5.5 scores 67.8 against 52.1.
2 benchmarks behind each score
Intelligence
AA Intelligence Index
GPT-5.5
GPT-5.5 leads, 38.4 against 12.5.
Same board, both measured
Agentic work
AA Agentic Index
No call
Only GPT-5.5 has a AA Agentic Index result, 36.4.
Directional only
Reasoning
GPQA Diamond
GPT-5.5
GPT-5.5 leads, 93.2% against 75.5%.
Same board, both measured
Math
AIME
No call
Only o3 Mini has a AIME result, 86.5%.
Directional only
Knowledge
MMLU Pro
GPT-5.5
GPT-5.5 leads, 88.1% against 78.7%.
Same board, both measured
Web design
Design Arena: websites
No call
Only GPT-5.5 has a Design Arena: websites result, 1256.
Directional only
Long documents
Listed context window
GPT-5.5
GPT-5.5 takes 1.05M tokens against 200K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
o3 Mini
GPT-5.5 $0.020, o3 Mini $0.0033 per turn.
List prices
Cost per solved task
One SWE-bench Verified task, solved
No call
Only GPT-5.5 has the number, $1.65.
Directional only
At a glance
- Coding index
- GPT-5.5 67.8 from 2 benchmarks, o3 Mini 52.1 from 2 benchmarks.
- Widest category
- Agentic work, 62.6 points apart on average over 1 shared benchmark.
- Widest single gap
- ARC-AGI-2: GPT-5.5 85.0% against o3 Mini 3.0%, 82.0 points apart on a 0 to 100 scale.
- Output price
- GPT-5.5 $30.00 against o3 Mini $4.40 per million output tokens, 6.8x apart.
- Context window
- GPT-5.5 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-5.5 | Bars | o3 Mini | Ties |
|---|---|---|---|---|
| Coding | 7 | 0 | ||
| Intelligence | 2 | 0 | ||
| Agentic work | 1 | 0 | ||
| Reasoning | 12 | 0 | ||
| Math | 5 | 0 | ||
| Knowledge | 9 | 0 | ||
| General | 21 | 0 | ||
| All shared boards | 57 | 0 |
CodingLike-for-likeFour of these boards feed the Vibe Coding Index70
| Benchmark | GPT-5.5 | o3 Mini | Leader |
|---|---|---|---|
| Aider polyglot | Not measured | 60.4% | Only o3 Mini measured |
| SWE-bench Verified | Not measured | 42.4% | Only o3 Mini measured |
| SWE-bench Lite | Not measured | 32.3% | Only o3 Mini measured |
| LiveBench coding | 85.1% | Not measured | Only GPT-5.5 measured |
| LMArena WebDev | 1513 | Not measured | Only GPT-5.5 measured |
| AA Coding Index | 74.9 | Not measured | Only GPT-5.5 measured |
| LiveCodeBench (Vals AI) | 85.3% | 71.5% | GPT-5.5 |
| SWE-bench Verified (Vals AI) | 82.6% | Not measured | Only GPT-5.5 measured |
| Vibe Code Bench (Vals AI) | 69.8% | Not measured | Only GPT-5.5 measured |
| Code migration (Vals AI) | 45.2% | Not measured | Only GPT-5.5 measured |
| ProgramBench (Vals AI) | 0.5% | Not measured | Only GPT-5.5 measured |
| Terminal-Bench 2.1 (Vals AI) | 76.4% | Not measured | Only GPT-5.5 measured |
| SkillsBench (Vals AI) | 62.5% | Not measured | Only GPT-5.5 measured |
| LiveCodeBench (Artificial Analysis run) | Not measured | 73.4% | Only o3 Mini measured |
| SciCode | 56.1% | 42.8% | GPT-5.5 |
| Terminal-Bench Hard (Artificial Analysis run) | 60.6% | 6.8% | GPT-5.5 |
| Terminal-Bench | 84.7% | Not measured | Only GPT-5.5 measured |
| FrontierCode | 43.0% | Not measured | Only GPT-5.5 measured |
| GSO-Bench | 40.2% | 1.3% | GPT-5.5 |
| WeirdML | 84.9% | 43.7% | GPT-5.5 |
| MirrorCode | 10.0% | Not measured | Only GPT-5.5 measured |
| Cybench | Not measured | 22.5% | Only o3 Mini measured |
| ALE-Bench | 1943.0 | Not measured | Only GPT-5.5 measured |
| LMArena Text: coding | 1494 | 1378 | GPT-5.5 |
| LMArena Text: software and IT | 1493 | 1364 | GPT-5.5 |
| LMArena WebDev: React | 1506 | Not measured | Only GPT-5.5 measured |
| LMArena WebDev: HTML | 1543 | Not measured | Only GPT-5.5 measured |
| LMArena WebDev: from an image | 1532 | Not measured | Only GPT-5.5 measured |
| Neither model has a result on the other 10 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index20
| Benchmark | GPT-5.5 | o3 Mini | Leader |
|---|---|---|---|
| AA Intelligence Index | 38.4 | 12.5 | GPT-5.5 |
| Epoch Capabilities Index | 159.7 | 140.2 | GPT-5.5 |
Agentic workLike-for-likePublic boards, shown as published, kept out of the index10
| Benchmark | GPT-5.5 | o3 Mini | Leader |
|---|---|---|---|
| AA Agentic Index | 36.4 | Not measured | Only GPT-5.5 measured |
| Design Arena: agents building web apps | 1117 | Not measured | Only GPT-5.5 measured |
| Design Arena: agents building full-stack apps | 1089 | Not measured | Only GPT-5.5 measured |
| Design Arena: agents building mobile apps | 1143 | Not measured | Only GPT-5.5 measured |
| Design Arena: agents building Android apps | 1169 | Not measured | Only GPT-5.5 measured |
| Design Arena: agents building Godot games | 1173 | Not measured | Only GPT-5.5 measured |
| Design Arena: agents building games | 1179 | Not measured | Only GPT-5.5 measured |
| Design Arena: HTML slides | 1067 | Not measured | Only GPT-5.5 measured |
| Design Arena: PowerPoint slides | 1108 | Not measured | Only GPT-5.5 measured |
| LiveBench research | 61.6% | Not measured | Only GPT-5.5 measured |
| LiveBench browser | 48.0% | Not measured | Only GPT-5.5 measured |
| LiveBench long agentic | 44.6% | Not measured | Only GPT-5.5 measured |
| SREBench (Vals AI) | 3.8% | Not measured | Only GPT-5.5 measured |
| Finance Agent (Vals AI) | 51.8% | Not measured | Only GPT-5.5 measured |
| Tax Agent Bench (Vals AI) | 21.8% | Not measured | Only GPT-5.5 measured |
| Legal Research Bench (Vals AI) | 40.4% | Not measured | Only GPT-5.5 measured |
| Excel Modeling Benchmark (Vals AI) | 64.5% | Not measured | Only GPT-5.5 measured |
| Time Horizon Index (Vals AI) | 8.3% | Not measured | Only GPT-5.5 measured |
| τ²-Bench Telecom | 93.9% | 31.3% | GPT-5.5 |
| APEX-Agents | 55.1% | Not measured | Only GPT-5.5 measured |
| Remote Labor Index | 6.3% | Not measured | Only GPT-5.5 measured |
| OSWorld 2.0 | 13.0% | Not measured | Only GPT-5.5 measured |
| DeepResearch Bench | 54.0% | Not measured | Only GPT-5.5 measured |
| PostTrainBench | 27.2% | Not measured | Only GPT-5.5 measured |
| Vending-Bench 2 | $7,524 | Not measured | Only GPT-5.5 measured |
| Neither model has a result on the other 14 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index120
| Benchmark | GPT-5.5 | o3 Mini | Leader |
|---|---|---|---|
| GPQA Diamond | 93.2% | 75.5% | GPT-5.5 |
| LiveBench reasoning | 89.7% | Not measured | Only GPT-5.5 measured |
| MMMU Pro (Vals AI) | 88.3% | Not measured | Only GPT-5.5 measured |
| GPQA Diamond (Artificial Analysis run) | 93.5% | 77.3% | GPT-5.5 |
| Humanity's Last Exam (Artificial Analysis run) | 45.8% | 12.0% | GPT-5.5 |
| GPQA Diamond (Epoch AI run) | 90.7% | 77.0% | GPT-5.5 |
| ARC-AGI | 95.0% | 34.5% | GPT-5.5 |
| ARC-AGI-2 | 85.0% | 3.0% | GPT-5.5 |
| SimpleBench | 69.0% | 22.8% | GPT-5.5 |
| Chess puzzles | 63.0% | 15.0% | GPT-5.5 |
| Mystery game puzzles | 56.0% | 7.0% | GPT-5.5 |
| EBR-bench | 34.3% | Not measured | Only GPT-5.5 measured |
| LMArena Text: hard prompts | 1489 | 1365 | GPT-5.5 |
| LMArena Text: expert | 1507 | 1364 | GPT-5.5 |
| LMArena Text: hard prompts in English | 1483 | 1375 | GPT-5.5 |
| LMArena Vision: diagrams | 1325 | Not measured | Only GPT-5.5 measured |
| LMArena Vision: homework | 1332 | Not measured | Only GPT-5.5 measured |
| Neither model has a result on the other 4 boards here | |||
MathLike-for-likePublic boards, shown as published, kept out of the index50
| Benchmark | GPT-5.5 | o3 Mini | Leader |
|---|---|---|---|
| AIME | Not measured | 86.5% | Only o3 Mini measured |
| MATH 500 (Vals AI) | Not measured | 91.8% | Only o3 Mini measured |
| MGSM (Vals AI) | Not measured | 91.3% | Only o3 Mini measured |
| OTIS Mock AIME | 84.4% | 76.9% | GPT-5.5 |
| FrontierMath, tiers 1 to 3 | 85.3% | 18.6% | GPT-5.5 |
| FrontierMath, tier 4 | 72.5% | 0.0% | GPT-5.5 |
| ProofBench | 50.0% | Not measured | Only GPT-5.5 measured |
| MATH level 5 | Not measured | 96.5% | Only o3 Mini measured |
| LMArena Text: math | 1487 | 1396 | GPT-5.5 |
| LMArena Text: mathematical work | 1496 | 1399 | GPT-5.5 |
| Neither model has a result on the other 3 boards here | |||
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index90
| Benchmark | GPT-5.5 | o3 Mini | Leader |
|---|---|---|---|
| MMLU Pro | 88.1% | 78.7% | GPT-5.5 |
| LegalBench (Vals AI) | 86.5% | 71.5% | GPT-5.5 |
| CaseLaw (Vals AI) | 66.2% | Not measured | Only GPT-5.5 measured |
| CorpFin (Vals AI) | 68.4% | 45.3% | GPT-5.5 |
| TaxEval (Vals AI) | 75.0% | 69.4% | GPT-5.5 |
| MortgageTax (Vals AI) | 68.8% | Not measured | Only GPT-5.5 measured |
| MedQA (Vals AI) | Not measured | 94.8% | Only o3 Mini measured |
| MedCode (Vals AI) | 49.1% | Not measured | Only GPT-5.5 measured |
| MMLU Pro (Artificial Analysis run) | Not measured | 80.2% | Only o3 Mini measured |
| SimpleQA Verified | 63.0% | 15.3% | GPT-5.5 |
| LMArena Text: science | 1485 | 1339 | GPT-5.5 |
| LMArena Text: medicine and healthcare | 1465 | 1330 | GPT-5.5 |
| LMArena Text: legal and government | 1491 | 1328 | GPT-5.5 |
| LMArena Text: business and finance | 1478 | 1313 | GPT-5.5 |
| Neither model has a result on the other 3 boards here | |||
Web designDirectional onlyPublic boards, shown as published, kept out of the index9 boards, none shared
| Benchmark | GPT-5.5 | o3 Mini | Leader |
|---|---|---|---|
| Design Arena: websites | 1256 | Not measured | Only GPT-5.5 measured |
| Design Arena: UI components | 1260 | Not measured | Only GPT-5.5 measured |
| Design Arena: game dev | 1294 | Not measured | Only GPT-5.5 measured |
| Design Arena: data viz | 1265 | Not measured | Only GPT-5.5 measured |
| Design Arena: 3D | 1198 | Not measured | Only GPT-5.5 measured |
| Design Arena: all code categories | 1260 | Not measured | Only GPT-5.5 measured |
| Design Arena: SVG | 1234 | Not measured | Only GPT-5.5 measured |
| Design Arena: ASCII art | 1254 | Not measured | Only GPT-5.5 measured |
| LiveBench design | 70.3% | Not measured | Only GPT-5.5 measured |
GeneralLike-for-likePublic boards, shown as published, kept out of the index210
| Benchmark | GPT-5.5 | o3 Mini | Leader |
|---|---|---|---|
| LiveBench data analysis | 81.6% | Not measured | Only GPT-5.5 measured |
| Public Benefits Bench (Vals AI) | 60.9% | Not measured | Only GPT-5.5 measured |
| SAGE (Vals AI) | 51.5% | Not measured | Only GPT-5.5 measured |
| MedScribe (Vals AI) | 86.9% | Not measured | Only GPT-5.5 measured |
| Vals Multimodal Index | 68.1% | Not measured | Only GPT-5.5 measured |
| IFBench | 75.9% | 67.1% | GPT-5.5 |
| Long context reasoning (AA-LCR) | 84.3% | 43.0% | GPT-5.5 |
| DTBench | 96.0% | 68.8% | GPT-5.5 |
| LMCA | 54.3% | 19.0% | GPT-5.5 |
| Fiction.LiveBench | Not measured | 50.0% | Only o3 Mini measured |
| Creative writing (Lech Mazur) | Not measured | 61.7% | Only o3 Mini measured |
| Surface Evolver Bench | 88.1% | Not measured | Only GPT-5.5 measured |
| Furniture assembly | 44.2% | Not measured | Only GPT-5.5 measured |
| ExploitBench | 47.4% | Not measured | Only GPT-5.5 measured |
| CL-bench Life | 22.2% | Not measured | Only GPT-5.5 measured |
| LMArena Text | 1471 | 1337 | GPT-5.5 |
| LMArena Text: instruction following | 1478 | 1337 | GPT-5.5 |
| LMArena Text: creative writing | 1455 | 1286 | GPT-5.5 |
| LMArena Vision | 1297 | Not measured | Only GPT-5.5 measured |
| LMArena Text: English | 1470 | 1351 | GPT-5.5 |
| LMArena Text: non-English | 1467 | 1319 | GPT-5.5 |
| LMArena Text: Chinese | 1534 | 1379 | GPT-5.5 |
| LMArena Text: German | 1480 | 1303 | GPT-5.5 |
| LMArena Text: Japanese | 1499 | 1286 | GPT-5.5 |
| LMArena Text: Korean | 1460 | 1313 | GPT-5.5 |
| LMArena Text: French | 1485 | 1334 | GPT-5.5 |
| LMArena Text: Spanish | 1468 | 1321 | GPT-5.5 |
| LMArena Text: Russian | 1473 | 1304 | GPT-5.5 |
| LMArena Text: Polish | 1465 | 1294 | GPT-5.5 |
| LMArena Text: multi-turn | 1476 | 1320 | GPT-5.5 |
| LMArena Text: longer queries | 1484 | 1343 | GPT-5.5 |
| LMArena Text: writing and language | 1466 | 1313 | GPT-5.5 |
| LMArena Text: entertainment and media | 1449 | 1283 | GPT-5.5 |
| LMArena Vision: English | 1292 | Not measured | Only GPT-5.5 measured |
| LMArena Vision: Chinese | 1360 | Not measured | Only GPT-5.5 measured |
| LMArena Vision: reading text | 1306 | Not measured | Only GPT-5.5 measured |
| LMArena Vision: humor | 1293 | Not measured | Only GPT-5.5 measured |
| LMArena Vision: recognizing things | 1231 | Not measured | Only GPT-5.5 measured |
| LMArena Vision: creative writing | 1301 | Not measured | Only GPT-5.5 measured |
| LMArena Document | 1486 | Not measured | Only GPT-5.5 measured |
| Neither model has a result on the other 6 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | GPT-5.5 | 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
GPT-5.5$0.020Fits in one request
o3 Mini$0.0033Fits in one request
o3 Mini costs less
Repository review
50K input + 3K output tokens
GPT-5.5$0.340Fits in one request
o3 Mini$0.068Fits in one request
o3 Mini costs less
Agent loop
200K input + 10K output tokens
GPT-5.5$1.30Fits in one request
o3 Mini$0.264Exceeds the context window
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-5.5 | OpenAI o3 Mini |
|---|---|---|
| Maker | OpenAI | OpenAI |
| Weights | No public weights listed | No public weights listed |
| Released | April 24, 2026 | January 31, 2025 |
| Context window | 1.05M | 200K |
| Input $/Mtok | $5.00 | $1.10 |
| Output $/Mtok | $30.00 | $4.40 |
| Coding index | 67.8 | 52.1 |
| Independent measurements behind it | 2 | 2 |
| Cost per solved task | $1.65 | Not computable |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is GPT-5.5 better than o3 Mini for coding?
Pick GPT-5.5 for coding: it scores 67.8 on the Vibe Coding Index against 52.1 for o3 Mini. Pick o3 Mini when output tokens cost 6.8x less.
Which is cheaper, GPT-5.5 or o3 Mini?
GPT-5.5 costs $5.00 per million input tokens and $30.00 per million output tokens; o3 Mini costs $1.10 and $4.40. Cost per solved task is known for GPT-5.5 only.
Which has the bigger context window, GPT-5.5 or o3 Mini?
GPT-5.5, with 1.05M tokens against 200K.
How many benchmarks is the GPT-5.5 vs o3 Mini comparison based on?
57 benchmarks have a result for both models as of October 21, 2026. GPT-5.5'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.