Model comparison
o3-mini vs o3-pro
o3-pro is the stronger model overall, scoring 42.9 to 36.7 on the Noometry Index. o3-mini costs 18× less per token, which makes it the better buy when o3-pro's lead doesn't matter for your workload.
Last verified . 10 shared benchmarks.
Summary
- They share 10 benchmarks with published results for both. o3-mini scores higher in 1 category and o3-pro in 4 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in long context, where o3-pro leads 72.2 to 33.8.
- The biggest single-benchmark swing is Fiction.LiveBench: 50% for o3-mini and 97.2% for o3-pro.
- o3-mini is cheaper at $1.10 / $4.40 per million input/output tokens, against $20 / $80 for o3-pro.
Side by side
| o3-mini | o3-pro | |
|---|---|---|
| Provider | OpenAI | OpenAI |
| Noometry Index | 36.7 | 42.9 |
| Released | 2024-12-20 | 2025-06-10 |
| Weights | Proprietary | Proprietary |
| Context window | 200K | 200K |
| Max output | 100K | 100K |
| Input $ / M tokens | $1.10 | $20 |
| Output $ / M tokens | $4.40 | $80 |
| Results tracked | 51 | 12 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding o3-pro leads
o3-mini: 40.8 (#132), o3-pro: 55.5 (#24)
| Benchmark | o3-mini | o3-pro |
|---|---|---|
| Aider Polyglot | 60.4% | 84.9% |
| WeirdML | 43.7% | 58.2% |
| SciCode | 39.8% | — |
| GSO | 1.3% | — |
| LiveBench Coding | 82.7% | — |
| LMArena Coding | 1378 | — |
| CadEval | 54% | — |
Agentic & Tool Use Not comparable
o3-mini: 29.6 (#84), o3-pro: —
| Benchmark | o3-mini | o3-pro |
|---|---|---|
| Cybench | 22.5% | — |
Reasoning o3-pro leads
o3-mini: 16.3 (#305), o3-pro: 23.8 (#171)
| Benchmark | o3-mini | o3-pro |
|---|---|---|
| ARC-AGI-2 | 3% | 4.9% |
| ARC-AGI-1 | 34.5% | 59.3% |
| DTBench | 68.8% | 86.9% |
| LMCA | 19% | 38.5% |
| Epoch Capabilities Index | 140.34 | 147.42 |
| SimpleBench | 22.8% | — |
| Kagi LLM Benchmark | — | 72.1% |
| CritPt | 0.3% | — |
| Chess Puzzles | 17% | — |
| LiveBench Reasoning | 89.6% | — |
| LMArena Hard Prompts | 1366 | — |
| Mystery Game Puzzles | 7% | — |
| LiveBench Data Analysis | 70.6% | — |
| ForecastBench | 59.6 | — |
| LiveBench | 75.9% | — |
Math Not comparable
o3-mini: 28.1 (#244), o3-pro: —
| Benchmark | o3-mini | o3-pro |
|---|---|---|
| FrontierMath (Tiers 1-3) | 18.6% | — |
| FrontierMath Tier 4 | 0% | — |
| 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% | — |
| FrontierMath Tier 4 (v1) | 4.2% | — |
Knowledge o3-mini leads
o3-mini: 38.3 (#146), o3-pro: 29.5 (#238)
| Benchmark | o3-mini | o3-pro |
|---|---|---|
| Confabulations | 17.9% | 14.2% |
| GPQA Diamond | 77% | — |
| SimpleQA Verified | 15.3% | — |
| Vectara Hallucination Rate | — | 23.3% |
| LMArena Expert | 1364 | — |
Multilingual Not comparable
o3-mini: 45.7 (#164), o3-pro: —
| Benchmark | o3-mini | o3-pro |
|---|---|---|
| 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
o3-mini: 75.1 (#72), o3-pro: —
| Benchmark | o3-mini | o3-pro |
|---|---|---|
| LiveBench Instruction Following | 84.4% | — |
| LMArena Instruction Following | 1337 | — |
Long Context o3-pro leads
o3-mini: 33.8 (#256), o3-pro: 72.2 (#1)
| Benchmark | o3-mini | o3-pro |
|---|---|---|
| Fiction.LiveBench | 50% | 97.2% |
| LMArena Longer Query | 1343 | — |
Writing & Preference o3-pro leads
o3-mini: 50.3 (#182), o3-pro: 57.1 (#133)
| Benchmark | o3-mini | o3-pro |
|---|---|---|
| Short-Story Creative Writing | 61.7% | 84.4% |
| LMArena Text | 1337 | — |
| LMArena Creative Writing | 1286 | — |
| LMArena Multi-Turn | 1320 | — |
| LiveBench Language | 50.7% | — |
Frequently asked questions
Is o3-mini better than o3-pro?
o3-pro is the stronger model overall, scoring 42.9 to 36.7 on the Noometry Index. o3-mini costs 18× less per token, which makes it the better buy when o3-pro's lead doesn't matter for your workload.
Which is cheaper, o3-mini or o3-pro?
o3-mini is cheaper. It lists at $1.10 per million input tokens and $4.40 per million output tokens; o3-pro lists at $20 and $80.
Is o3-mini or o3-pro better for coding?
o3-pro scores higher on coding benchmarks: 55.5 versus 40.8 in the Noometry coding category.
Which has the bigger context window?
Both accept 200K tokens.
How many benchmarks do o3-mini and o3-pro share?
10 benchmarks have published results for both models. o3-mini has 51 scored results on Noometry and o3-pro has 12.