OpenAI model product
A research preview model focused on mathematical and logical reasoning capabilities, demonstrating improved performance on tasks requiring step-by-step reasoning, mathematical problem-solving, and code generation. The model shows enhanced capabilities in formal reasoning while maintaining strong general capabilities.
Updated Aug 10, 2026. Default version: o1
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 o1.
| GPQA Biology | 0.7 | 1 | 1 | 100.0% | C | |
| GPQA Chemistry | 0.6 | 1 | 1 | 100.0% | C | |
| GPQA Physics | 0.9 | 1 | 1 | 100.0% | C | |
| MATH | 1.0 | 2 | 71 | 98.6% | C | |
| MMLU | 0.9 | 2 | 100 | 99.0% | C | |
| GSM8k | 1.0 | 3 | 48 | 95.7% | C | |
| MGSM | 0.9 | 10 | 31 | 70.0% | C | |
| TAU-bench Retail | 0.7 | 10 | 25 | 62.5% | C | |
| MathVista | 0.7 | 12 | 39 | 71.0% | C | |
| TAU-bench Airline | 0.5 | 12 | 23 | 50.0% | C | |
| FrontierMath | 0.1 | 17 | 17 | 0.0% | C | |
| SimpleQA | 0.5 | 17 | 46 | 64.4% | C | |
| MMMU | 0.8 | 18 | 63 | 72.6% | C | |
| MMMLU | 0.9 | 19 | 49 | 62.5% | C | |
| HumanEval | 0.9 | 28 | 76 | 64.0% | C | |
| LiveBench | 0.7 | 33 | 38 | 13.5% | C | |
| AIME 2024 | 0.7 | 35 | 53 | 34.6% | C | |
| SWE-Bench Verified | 0.4 | 94 | 104 | 9.7% | C | |
| GPQA | 0.8 | 95 | 233 | 59.5% | C |
Preference and agent-evaluation signals from published Arena datasets.
| vision style control | chinese | 50 | 1261.9 | 99 | N/A | |
| text style control | korean | 52 | 1409.8 | 396 | N/A | |
| text | korean | 54 | 1396.6 | 396 | N/A | |
| vision | chinese | 64 | 1230.6 | 99 | N/A | |
| vision style control | overall | 76 | 1193.4 | 3,694 | N/A | |
| vision style control | english | 81 | 1187.6 | 1,943 | N/A | |
| text style control | japanese | 89 | 1375.1 | 581 | N/A | |
| vision | overall | 89 | 1168.6 | 3,694 | N/A | |
| vision | english | 95 | 1163.4 | 1,943 | N/A | |
| text | japanese | 102 | 1346.9 | 581 | N/A | |
| text style control | industry entertainment and sports and media | 105 | 1390.1 | 5,210 | N/A | |
| text style control | instruction following | 111 | 1407.0 | 10,246 | N/A | |
| text style control | industry writing and literature and language | 112 | 1397.6 | 7,663 | N/A | |
| text style control | math | 120 | 1408.9 | 2,986 | N/A | |
| text style control | creative writing | 121 | 1381.3 | 4,642 | N/A | |
| text style control | industry mathematical | 124 | 1414.1 | 2,644 | N/A | |
| text style control | longer query | 128 | 1412.0 | 3,571 | N/A | |
| text style control | spanish | 128 | 1388.6 | 142 | N/A | |
| text style control | exclude ties | 132 | 1386.3 | 19,214 | N/A | |
| text style control | non english | 132 | 1389.6 | 11,491 | N/A | |
| text | industry entertainment and sports and media | 134 | 1358.6 | 5,210 | N/A | |
| text style control | overall | 134 | 1402.2 | 27,807 | N/A | |
| text style control | industry legal and government | 135 | 1406.4 | 1,454 | N/A | |
| text style control | chinese | 136 | 1429.2 | 1,780 | N/A | |
| text style control | english | 138 | 1411.7 | 16,316 | N/A | |
| text style control | german | 140 | 1375.3 | 556 | N/A | |
| text style control | hard prompts | 140 | 1417.8 | 6,453 | N/A | |
| text style control | russian | 141 | 1386.7 | 3,078 | N/A | |
| text | instruction following | 142 | 1367.8 | 10,246 | N/A | |
| text | industry mathematical | 143 | 1389.5 | 2,644 | N/A | |
| text style control | industry life and physical and social science | 144 | 1410.7 | 4,820 | N/A | |
| text | creative writing | 145 | 1347.8 | 4,642 | N/A | |
| text | industry writing and literature and language | 147 | 1360.0 | 7,663 | N/A | |
| text | longer query | 147 | 1378.0 | 3,571 | N/A | |
| text style control | hard prompts english | 148 | 1423.0 | 4,238 | N/A | |
| text | math | 149 | 1388.4 | 2,986 | N/A | |
| text style control | expert | 151 | 1400.6 | 1,330 | N/A | |
| text | chinese | 153 | 1393.6 | 1,780 | N/A | |
| text style control | industry software and it services | 153 | 1423.0 | 6,584 | N/A | |
| text style control | coding | 154 | 1433.0 | 3,973 | N/A | |
| text | non english | 155 | 1358.5 | 11,491 | N/A | |
| text | russian | 156 | 1355.0 | 3,078 | N/A | |
| text | hard prompts | 157 | 1371.7 | 6,453 | N/A | |
| text style control | french | 157 | 1385.2 | 252 | N/A | |
| text | german | 159 | 1337.2 | 556 | N/A | |
| text style control | multi turn | 159 | 1386.0 | 4,399 | N/A | |
| text | exclude ties | 160 | 1334.1 | 19,214 | N/A | |
| text | expert | 160 | 1360.8 | 1,330 | N/A | |
| text style control | industry medicine and healthcare | 160 | 1398.4 | 1,273 | N/A | |
| text | overall | 162 | 1366.0 | 27,807 | N/A | |
| text | industry legal and government | 162 | 1368.3 | 1,454 | N/A | |
| text style control | industry business and management and financial operations | 164 | 1369.9 | 2,720 | N/A | |
| text | french | 165 | 1343.2 | 252 | N/A | |
| text | spanish | 166 | 1342.0 | 142 | N/A | |
| text | industry life and physical and social science | 168 | 1369.1 | 4,820 | N/A | |
| text | multi turn | 169 | 1354.7 | 4,399 | N/A | |
| text | hard prompts english | 172 | 1373.4 | 4,238 | N/A | |
| text | english | 176 | 1372.2 | 16,316 | N/A | |
| text | industry medicine and healthcare | 176 | 1354.2 | 1,273 | N/A | |
| text | coding | 179 | 1367.4 | 3,973 | N/A | |
| text | industry software and it services | 179 | 1367.4 | 6,584 | N/A | |
| text | industry business and management and financial operations | 183 | 1327.4 | 2,720 | 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.
| OpenAI | o1 | global | $15 | $60 | 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.
| o1 | 63.0 | N/A | 200K | 100K | No | Proprietary | |
| o1-preview | N/A | N/A | 128K | 32.8K | No | Proprietary |
A concise description based on the published model registry.
A research preview model focused on mathematical and logical reasoning capabilities, demonstrating improved performance on tasks requiring step-by-step reasoning, mathematical problem-solving, and code generation. The model shows enhanced capabilities in formal reasoning while maintaining strong general capabilities.
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 o1.
o1's default version was released on Dec 17, 2024.
o1's official API price is $15 per million input tokens and $60 per million output tokens via OpenAI.
o1 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.
1 published provider offerings are linked to the default version.
Nearby ranked alternatives include Gemini 2.5 Flash, Nova Pro, MAI Thinking 1.