Model comparison
GPT-5.2 Pro vs o3-mini
GPT-5.2 Pro is the stronger model overall, scoring 52.3 to 36.7 on the Noometry Index. o3-mini costs 30× less per token, which makes it the better buy when GPT-5.2 Pro's lead doesn't matter for your workload.
Last verified . 7 shared benchmarks.
Summary
- They share 7 benchmarks with published results for both. GPT-5.2 Pro scores higher in 2 categories and o3-mini in 0 categories; 2 gaps are clear of the uncertainty.
- The widest gap is in math, where GPT-5.2 Pro leads 65.3 to 28.1.
- The biggest single-benchmark swing is ARC-AGI-1: 90.5% for GPT-5.2 Pro and 34.5% for o3-mini.
- o3-mini is cheaper at $1.10 / $4.40 per million input/output tokens, against $21 / $168 for GPT-5.2 Pro.
- GPT-5.2 Pro accepts more context: 400K tokens versus 200K.
Side by side
| GPT-5.2 Pro | o3-mini | |
|---|---|---|
| Provider | OpenAI | OpenAI |
| Noometry Index | 52.3 | 36.7 |
| Released | 2025-12-11 | 2024-12-20 |
| Weights | Proprietary | Proprietary |
| Context window | 400K | 200K |
| Max output | 128K | 100K |
| Input $ / M tokens | $21 | $1.10 |
| Output $ / M tokens | $168 | $4.40 |
| Results tracked | 8 | 51 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Not comparable
GPT-5.2 Pro: —, o3-mini: 40.8 (#132)
| Benchmark | GPT-5.2 Pro | o3-mini |
|---|---|---|
| Aider Polyglot | — | 60.4% |
| SciCode | — | 39.8% |
| GSO | — | 1.3% |
| WeirdML | — | 43.7% |
| LiveBench Coding | — | 82.7% |
| LMArena Coding | — | 1378 |
| CadEval | — | 54% |
Agentic & Tool Use Not comparable
GPT-5.2 Pro: —, o3-mini: 29.6 (#84)
| Benchmark | GPT-5.2 Pro | o3-mini |
|---|---|---|
| Cybench | — | 22.5% |
Reasoning GPT-5.2 Pro leads
GPT-5.2 Pro: 51.5 (#33), o3-mini: 16.3 (#305)
| Benchmark | GPT-5.2 Pro | o3-mini |
|---|---|---|
| ARC-AGI-2 | 54.2% | 3% |
| SimpleBench | 57.4% | 22.8% |
| ARC-AGI-1 | 90.5% | 34.5% |
| Epoch Capabilities Index | 155.4 | 140.34 |
| NYT Connections (extended) | 79.3% | — |
| CritPt | — | 0.3% |
| Chess Puzzles | — | 17% |
| LiveBench Reasoning | — | 89.6% |
| LMArena Hard Prompts | — | 1366 |
| Mystery Game Puzzles | — | 7% |
| DTBench | — | 68.8% |
| LiveBench Data Analysis | — | 70.6% |
| LMCA | — | 19% |
| ForecastBench | — | 59.6 |
| LiveBench | — | 75.9% |
Math GPT-5.2 Pro leads
GPT-5.2 Pro: 65.3 (#29), o3-mini: 28.1 (#244)
| Benchmark | GPT-5.2 Pro | o3-mini |
|---|---|---|
| FrontierMath (Tiers 1-3) | 74% | 18.6% |
| FrontierMath Tier 4 | 46% | 0% |
| FrontierMath Tier 4 (v1) | 31.3% | 4.2% |
| OTIS Mock AIME 2024-2025 | — | 76.9% |
| LiveBench Math | — | 77.3% |
| LMArena Math | — | 1396 |
| MATH Level 5 | — | 96.5% |
| FrontierMath (Feb 2025 set) | — | 12.4% |
Knowledge Not comparable
GPT-5.2 Pro: —, o3-mini: 38.3 (#146)
| Benchmark | GPT-5.2 Pro | o3-mini |
|---|---|---|
| GPQA Diamond | — | 77% |
| SimpleQA Verified | — | 15.3% |
| Confabulations | — | 17.9% |
| LMArena Expert | — | 1364 |
Multilingual Not comparable
GPT-5.2 Pro: —, o3-mini: 45.7 (#164)
| Benchmark | GPT-5.2 Pro | o3-mini |
|---|---|---|
| LMArena Non-English | — | 1319 |
| LMArena Chinese | — | 1379 |
| LMArena French | — | 1334 |
| LMArena German | — | 1303 |
| LMArena Japanese | — | 1286 |
| LMArena Korean | — | 1314 |
| LMArena Russian | — | 1304 |
| LMArena Spanish | — | 1321 |
Instruction Following Not comparable
GPT-5.2 Pro: —, o3-mini: 75.1 (#72)
| Benchmark | GPT-5.2 Pro | o3-mini |
|---|---|---|
| LiveBench Instruction Following | — | 84.4% |
| LMArena Instruction Following | — | 1337 |
Long Context Not comparable
GPT-5.2 Pro: —, o3-mini: 33.8 (#256)
| Benchmark | GPT-5.2 Pro | o3-mini |
|---|---|---|
| Fiction.LiveBench | — | 50% |
| LMArena Longer Query | — | 1343 |
Writing & Preference Not comparable
GPT-5.2 Pro: —, o3-mini: 50.3 (#182)
| Benchmark | GPT-5.2 Pro | o3-mini |
|---|---|---|
| LMArena Text | — | 1337 |
| LMArena Creative Writing | — | 1286 |
| Short-Story Creative Writing | — | 61.7% |
| LMArena Multi-Turn | — | 1320 |
| LiveBench Language | — | 50.7% |
Frequently asked questions
Is GPT-5.2 Pro better than o3-mini?
GPT-5.2 Pro is the stronger model overall, scoring 52.3 to 36.7 on the Noometry Index. o3-mini costs 30× less per token, which makes it the better buy when GPT-5.2 Pro's lead doesn't matter for your workload.
Which is cheaper, GPT-5.2 Pro or o3-mini?
o3-mini is cheaper. It lists at $1.10 per million input tokens and $4.40 per million output tokens; GPT-5.2 Pro lists at $21 and $168.
Which has the bigger context window?
GPT-5.2 Pro does, with 400K tokens against 200K.
How many benchmarks do GPT-5.2 Pro and o3-mini share?
7 benchmarks have published results for both models. GPT-5.2 Pro has 8 scored results on Noometry and o3-mini has 51.