Model comparison
o1-mini vs o3-pro
o3-pro is the stronger model overall, scoring 42.9 to 34.0 on the Noometry Index.
Last verified . 7 shared benchmarks.
Summary
- They share 7 benchmarks with published results for both. o1-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 40.1.
- The biggest single-benchmark swing is Aider Polyglot: 32.9% for o1-mini and 84.9% for o3-pro.
Side by side
| o1-mini | o3-pro | |
|---|---|---|
| Provider | OpenAI | OpenAI |
| Noometry Index | 34.0 | 42.9 |
| Released | 2024-09-12 | 2025-06-10 |
| Weights | Proprietary | Proprietary |
| Context window | — | 200K |
| Max output | — | 100K |
| Input $ / M tokens | — | $20 |
| Output $ / M tokens | — | $80 |
| Results tracked | 39 | 12 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding o3-pro leads
o1-mini: 35.5 (#224), o3-pro: 55.5 (#24)
| Benchmark | o1-mini | o3-pro |
|---|---|---|
| Aider Polyglot | 32.9% | 84.9% |
| WeirdML | 36.3% | 58.2% |
| LiveBench Coding | 48% | — |
| LMArena Coding | 1362 | — |
| HumanEval+ | 89% | — |
| MBPP+ | 78.8% | — |
Agentic & Tool Use Not comparable
o1-mini: 24.6 (#118), o3-pro: —
| Benchmark | o1-mini | o3-pro |
|---|---|---|
| Cybench | 10% | — |
Reasoning o3-pro leads
o1-mini: 8.8 (#346), o3-pro: 23.8 (#171)
| Benchmark | o1-mini | o3-pro |
|---|---|---|
| ARC-AGI-2 | 0.8% | 4.9% |
| ARC-AGI-1 | 14% | 59.3% |
| Epoch Capabilities Index | 135.82 | 147.42 |
| SimpleBench | 18.1% | — |
| Kagi LLM Benchmark | — | 72.1% |
| LiveBench Reasoning | 72.3% | — |
| LMArena Hard Prompts | 1333 | — |
| DTBench | — | 86.9% |
| LiveBench Data Analysis | 57.9% | — |
| LMCA | — | 38.5% |
| LiveBench | 57.8% | — |
Math Not comparable
o1-mini: 35.4 (#186), o3-pro: —
| Benchmark | o1-mini | o3-pro |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 46.9% | — |
| LiveBench Math | 62% | — |
| LMArena Math | 1358 | — |
| MATH Level 5 | 89.2% | — |
| FrontierMath (Feb 2025 set) | 1.7% | — |
Knowledge o1-mini leads
o1-mini: 34.9 (#192), o3-pro: 29.5 (#238)
| Benchmark | o1-mini | o3-pro |
|---|---|---|
| Confabulations | 18.6% | 14.2% |
| GPQA Diamond | 62.4% | — |
| Vectara Hallucination Rate | — | 23.3% |
| LMArena Expert | 1316 | — |
Multilingual Not comparable
o1-mini: 43.6 (#182), o3-pro: —
| Benchmark | o1-mini | o3-pro |
|---|---|---|
| LMArena Non-English | 1289 | — |
| LMArena Chinese | 1314 | — |
| LMArena French | 1293 | — |
| LMArena German | 1278 | — |
| LMArena Japanese | 1245 | — |
| LMArena Korean | 1223 | — |
| LMArena Russian | 1283 | — |
| LMArena Spanish | 1303 | — |
Instruction Following Not comparable
o1-mini: 66.7 (#206), o3-pro: —
| Benchmark | o1-mini | o3-pro |
|---|---|---|
| LiveBench Instruction Following | 65.4% | — |
| LMArena Instruction Following | 1304 | — |
Long Context o3-pro leads
o1-mini: 40.1 (#161), o3-pro: 72.2 (#1)
| Benchmark | o1-mini | o3-pro |
|---|---|---|
| Fiction.LiveBench | — | 97.2% |
| LMArena Longer Query | 1320 | — |
Writing & Preference o3-pro leads
o1-mini: 48.4 (#202), o3-pro: 57.1 (#133)
| Benchmark | o1-mini | o3-pro |
|---|---|---|
| Short-Story Creative Writing | 64.9% | 84.4% |
| LMArena Text | 1317 | — |
| LMArena Creative Writing | 1244 | — |
| LMArena Multi-Turn | 1314 | — |
| LiveBench Language | 40.9% | — |
Frequently asked questions
Is o1-mini better than o3-pro?
o3-pro is the stronger model overall, scoring 42.9 to 34.0 on the Noometry Index.
Is o1-mini or o3-pro better for coding?
o3-pro scores higher on coding benchmarks: 55.5 versus 35.5 in the Noometry coding category.
How many benchmarks do o1-mini and o3-pro share?
7 benchmarks have published results for both models. o1-mini has 39 scored results on Noometry and o3-pro has 12.