OpenAI model product
A smaller variant of O3, expected to offer enhanced multimodal capabilities, improved reasoning, and more efficient resource utilization compared to previous models while maintaining strong performance on core tasks.
Updated Aug 10, 2026. Default version: o3-mini
Structured fields from the published default version.
This profile uses the latest version under this unique model that has a calculated LLMBoard score. Arena and price are excluded.
Published benchmark records for the scored version o3-mini.
| LiveBench | 0.8 | 1 | 38 | 100.0% | C | |
| MATH | 1.0 | 1 | 71 | 100.0% | C | |
| Multilingual MMLU | 0.8 | 1 | 5 | 100.0% | C | |
| COLLIE | 1.0 | 2 | 10 | 88.9% | C | |
| MGSM | 0.9 | 2 | 31 | 96.7% | C | |
| Multi-IF | 0.8 | 2 | 20 | 94.7% | C | |
| Aider-Polyglot Edit | 0.6 | 3 | 10 | 77.8% | C | |
| Internal API instruction following (hard) | 0.5 | 3 | 7 | 66.7% | C | |
| SWE-Lancer | 0.2 | 4 | 4 | 0.0% | C | |
| IFEval | 0.9 | 5 | 65 | 93.8% | C | |
| ComplexFuncBench | 0.2 | 6 | 7 | 16.7% | C | |
| SWE-Lancer (IC-Diamond subset) | 0.1 | 6 | 6 | 0.0% | C | |
| Aider-Polyglot | 0.7 | 9 | 22 | 61.9% | C | |
| OpenAI-MRCR: 2 needle 128k | 0.2 | 9 | 9 | 0.0% | C | |
| Graphwalks parents <128k | 0.6 | 10 | 18 | 47.1% | C | |
| AIME 2024 | 0.9 | 12 | 53 | 78.8% | C | |
| FrontierMath | 0.1 | 15 | 17 | 12.5% | C | |
| Graphwalks BFS <128k | 0.5 | 15 | 22 | 33.3% | C | |
| TAU-bench Airline | 0.3 | 21 | 23 | 9.1% | C | |
| TAU-bench Retail | 0.6 | 21 | 25 | 16.7% | C | |
| Multi-Challenge | 0.4 | 23 | 29 | 21.4% | C | |
| MMLU | 0.9 | 27 | 100 | 73.7% | C | |
| SimpleQA | 0.1 | 37 | 46 | 20.0% | C | |
| SWE-Bench Verified | 0.5 | 88 | 104 | 15.5% | C | |
| GPQA | 0.8 | 97 | 233 | 58.6% | C |
Preference and agent-evaluation signals from published Arena datasets.
| text style control | japanese | 144 | 1299.3 | 1,323 | N/A | |
| text style control | industry mathematical | 150 | 1391.2 | 4,379 | N/A | |
| text | japanese | 151 | 1266.4 | 1,323 | N/A | |
| text | industry mathematical | 154 | 1378.4 | 4,379 | N/A | |
| text style control | math | 159 | 1381.5 | 4,715 | N/A | |
| text style control | korean | 162 | 1292.9 | 1,070 | N/A | |
| text | math | 163 | 1373.4 | 4,715 | N/A | |
| text | korean | 169 | 1262.2 | 1,070 | N/A | |
| text style control | coding | 171 | 1416.0 | 9,450 | N/A | |
| text style control | german | 172 | 1327.1 | 1,281 | N/A | |
| text | german | 175 | 1302.9 | 1,281 | N/A | |
| text style control | french | 176 | 1355.9 | 656 | N/A | |
| text style control | polish | 176 | 1324.3 | 2,576 | N/A | |
| text | french | 177 | 1318.6 | 656 | N/A | |
| text style control | expert | 178 | 1365.2 | 2,860 | N/A | |
| text | polish | 179 | 1291.3 | 2,576 | N/A | |
| text | expert | 182 | 1330.2 | 2,860 | N/A | |
| text | spanish | 184 | 1299.9 | 836 | N/A | |
| text style control | hard prompts | 185 | 1370.4 | 20,096 | N/A | |
| text style control | industry software and it services | 185 | 1389.6 | 16,857 | N/A | |
| text style control | spanish | 185 | 1327.5 | 836 | N/A | |
| text | coding | 186 | 1362.4 | 9,450 | N/A | |
| text style control | hard prompts english | 187 | 1383.4 | 11,279 | N/A | |
| text style control | instruction following | 187 | 1343.4 | 16,948 | N/A | |
| text style control | longer query | 187 | 1358.5 | 9,217 | N/A | |
| text | instruction following | 190 | 1315.2 | 16,948 | N/A | |
| text | longer query | 191 | 1327.1 | 9,217 | N/A | |
| text style control | overall | 193 | 1347.8 | 57,283 | N/A | |
| text style control | non english | 193 | 1326.4 | 26,897 | N/A | |
| text style control | exclude ties | 195 | 1306.9 | 40,039 | N/A | |
| text | hard prompts english | 196 | 1344.6 | 11,279 | N/A | |
| text | hard prompts | 197 | 1332.6 | 20,096 | N/A | |
| text style control | industry writing and literature and language | 197 | 1324.1 | 13,426 | N/A | |
| text style control | english | 198 | 1363.1 | 30,380 | N/A | |
| text style control | multi turn | 198 | 1339.7 | 9,489 | N/A | |
| text style control | chinese | 199 | 1360.3 | 3,363 | N/A | |
| text | chinese | 200 | 1323.5 | 3,363 | N/A | |
| text | industry software and it services | 200 | 1343.8 | 16,857 | N/A | |
| text | russian | 201 | 1298.6 | 4,436 | N/A | |
| text style control | russian | 202 | 1326.6 | 4,436 | N/A | |
| text | non english | 203 | 1298.3 | 26,897 | N/A | |
| text | exclude ties | 206 | 1265.5 | 40,039 | N/A | |
| text | overall | 207 | 1319.2 | 57,283 | N/A | |
| text | multi turn | 207 | 1313.1 | 9,489 | N/A | |
| text style control | industry entertainment and sports and media | 208 | 1301.5 | 10,284 | N/A | |
| text | english | 209 | 1334.0 | 30,380 | N/A | |
| text | industry writing and literature and language | 209 | 1294.2 | 13,426 | N/A | |
| text style control | industry business and management and financial operations | 210 | 1326.6 | 7,707 | N/A | |
| text | industry entertainment and sports and media | 211 | 1272.9 | 10,284 | N/A | |
| text style control | industry life and physical and social science | 211 | 1350.0 | 9,650 | N/A | |
| text | industry legal and government | 212 | 1305.4 | 3,632 | N/A | |
| text | industry business and management and financial operations | 213 | 1288.2 | 7,707 | N/A | |
| text | industry medicine and healthcare | 213 | 1298.6 | 3,043 | N/A | |
| text style control | creative writing | 213 | 1301.0 | 8,178 | N/A | |
| text | industry life and physical and social science | 214 | 1315.5 | 9,650 | N/A | |
| text style control | industry medicine and healthcare | 214 | 1342.5 | 3,043 | N/A | |
| text style control | industry legal and government | 215 | 1340.0 | 3,632 | N/A | |
| text | creative writing | 216 | 1273.0 | 8,178 | N/A |
Official vendor API PAYG pricing is summarized first. The table then lists individual provider offerings without treating their minimum as the official price.
| LLM Gateway | o3-mini | global | $1.1 | $4.4 | 200K | |
| Helicone | o3-mini | global | $1.1 | $4.4 | 200K | |
| Abacus | o3-mini | global | $1.1 | $4.4 | 200K | |
| Azure Cognitive Services | o3-mini | global | $1.1 | $4.4 | 200K | |
| Azure | o3-mini | global | $1.1 | $4.4 | 200K | |
| Jiekou.AI | o3-mini | global | $1.1 | $4.4 | 131.1K | |
| OpenAI | o3-mini | global | $1.1 | $4.4 | 200K |
Official prices use only the vendor's configured official Provider and positive standard USD PAYG rates. Third-party offers remain explicitly labeled.
All published versions linked to this unique model. The score columns identify the version used by the current overall ranking.
| o3-mini | 61.6 | N/A | 200K | 100K | No | Proprietary |
A concise description based on the published model registry.
A smaller variant of O3, expected to offer enhanced multimodal capabilities, improved reasoning, and more efficient resource utilization compared to previous models while maintaining strong performance on core tasks.
Use the benchmark, Arena and pricing sections above as separate evidence. A missing field means the current data snapshot does not support that claim.
Data snapshot: 2026-08-07. Editorial model content is not available in the backend.
Open a comparison with the three ranked models immediately above and below this model.
Recommendations prioritize the same model type and family, then the closest published LLMBoard score.
Common questions about o3 mini.
o3 mini's default version was released on Jan 30, 2025.
o3 mini's official API price is $1.1 per million input tokens and $4.4 per million output tokens via OpenAI. The lowest tracked third-party offer starts at $1.1 input and $4.4 output via LLM Gateway.
o3 mini is published under OpenAI in the model registry.
The default version has a 200K token context window.
No. The default version is not marked as having publicly available weights.
7 published provider offerings are linked to the default version.
Nearby ranked alternatives include Llama 3.3 Nemotron Super 49B, Llama 3.1 Nemotron Ultra 253B, GLM 4.5.