OpenAI model product
The latest GPT-4 model with improved performance, updated knowledge, and enhanced capabilities. It offers faster response times and more affordable pricing compared to previous versions.
Updated Aug 10, 2026. Default version: GPT-4 Turbo
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.
Preference and agent-evaluation signals from published Arena datasets.
| vision | chinese | 89 | 1039.7 | 937 | N/A | |
| vision style control | chinese | 93 | 1061.5 | 937 | N/A | |
| vision | overall | 111 | 1090.0 | 13,391 | N/A | |
| vision | english | 113 | 1097.8 | 8,417 | N/A | |
| vision style control | overall | 113 | 1112.4 | 13,391 | N/A | |
| vision style control | english | 115 | 1113.3 | 8,417 | N/A | |
| text style control | polish | 152 | 1362.1 | 178 | N/A | |
| text style control | japanese | 173 | 1251.0 | 2,112 | N/A | |
| text | polish | 175 | 1300.6 | 178 | N/A | |
| text style control | german | 185 | 1311.7 | 3,359 | N/A | |
| text style control | korean | 185 | 1263.6 | 2,668 | N/A | |
| text | japanese | 186 | 1194.3 | 2,112 | N/A | |
| text style control | creative writing | 186 | 1322.8 | 14,396 | N/A | |
| text style control | industry entertainment and sports and media | 192 | 1314.1 | 14,793 | N/A | |
| text style control | spanish | 192 | 1312.5 | 1,430 | N/A | |
| text style control | french | 194 | 1334.6 | 1,402 | N/A | |
| text style control | industry writing and literature and language | 194 | 1329.5 | 24,529 | N/A | |
| text | german | 198 | 1259.3 | 3,359 | N/A | |
| text | french | 199 | 1274.2 | 1,402 | N/A | |
| text | spanish | 205 | 1259.3 | 1,430 | N/A | |
| text | korean | 206 | 1186.8 | 2,668 | N/A | |
| text style control | russian | 214 | 1312.6 | 9,938 | N/A | |
| text style control | industry legal and government | 220 | 1336.0 | 5,381 | N/A | |
| text | industry entertainment and sports and media | 222 | 1258.7 | 14,793 | N/A | |
| text | creative writing | 224 | 1268.8 | 14,396 | N/A | |
| text style control | overall | 224 | 1324.2 | 98,114 | N/A | |
| text | industry writing and literature and language | 226 | 1278.7 | 24,529 | N/A | |
| text style control | math | 228 | 1296.3 | 13,217 | N/A | |
| text style control | english | 229 | 1341.2 | 55,116 | N/A | |
| text style control | exclude ties | 229 | 1266.8 | 65,114 | N/A | |
| text style control | chinese | 230 | 1315.8 | 10,827 | N/A | |
| text style control | instruction following | 230 | 1302.8 | 36,297 | N/A | |
| text style control | multi turn | 231 | 1312.5 | 15,255 | N/A | |
| text style control | non english | 231 | 1299.3 | 42,998 | N/A | |
| text | math | 233 | 1271.6 | 13,217 | N/A | |
| text style control | industry medicine and healthcare | 234 | 1326.2 | 5,046 | N/A | |
| text style control | expert | 235 | 1295.3 | 5,195 | N/A | |
| text style control | industry mathematical | 235 | 1299.4 | 11,796 | N/A | |
| text | russian | 236 | 1258.6 | 9,938 | N/A | |
| text | industry mathematical | 239 | 1267.9 | 11,796 | N/A | |
| text | chinese | 242 | 1241.3 | 10,827 | N/A | |
| text | expert | 242 | 1222.5 | 5,195 | N/A | |
| text style control | industry life and physical and social science | 242 | 1326.7 | 16,354 | N/A | |
| text style control | longer query | 242 | 1316.8 | 11,559 | N/A | |
| text style control | coding | 243 | 1347.2 | 17,104 | N/A | |
| text style control | hard prompts english | 243 | 1329.5 | 17,922 | N/A | |
| text | instruction following | 244 | 1249.8 | 36,297 | N/A | |
| text | english | 245 | 1291.3 | 55,116 | N/A | |
| text | industry medicine and healthcare | 247 | 1238.6 | 5,046 | N/A | |
| text | multi turn | 247 | 1267.0 | 15,255 | N/A | |
| text style control | hard prompts | 247 | 1316.0 | 28,310 | N/A | |
| text style control | industry software and it services | 247 | 1336.6 | 27,573 | N/A | |
| text | overall | 248 | 1271.9 | 98,114 | N/A | |
| text | exclude ties | 249 | 1190.7 | 65,114 | N/A | |
| text | industry legal and government | 250 | 1265.0 | 5,381 | N/A | |
| text | non english | 250 | 1244.9 | 42,998 | N/A | |
| text style control | industry business and management and financial operations | 252 | 1292.7 | 10,807 | N/A | |
| text | coding | 253 | 1268.8 | 17,104 | N/A | |
| text | hard prompts english | 253 | 1267.9 | 17,922 | N/A | |
| text | longer query | 254 | 1254.1 | 11,559 | N/A | |
| text | hard prompts | 255 | 1251.3 | 28,310 | N/A | |
| text | industry software and it services | 256 | 1268.1 | 27,573 | N/A | |
| text | industry life and physical and social science | 257 | 1256.1 | 16,354 | N/A | |
| text | industry business and management and financial operations | 261 | 1222.1 | 10,807 | 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 | gpt-4-turbo | global | $10 | $30 | 128K |
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.
| GPT-4 Turbo | 51.1 | N/A | 128K | 4.1K | No | Proprietary |
A concise description based on the published model registry.
The latest GPT-4 model with improved performance, updated knowledge, and enhanced capabilities. It offers faster response times and more affordable pricing compared to previous versions.
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 GPT-4-Turbo.
GPT-4-Turbo's default version was released on Apr 9, 2024.
GPT-4-Turbo's official API price is $10 per million input tokens and $30 per million output tokens via OpenAI.
GPT-4-Turbo is published under OpenAI in the model registry.
The default version has a 128K 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 Qwen3 VL 32B Thinking, Qwen2.5 VL 32B, Kimi K2.