OpenAI model product
The latest GPT-3.5 Turbo model with higher accuracy at responding in requested formats and a fix for a bug which caused a text encoding issue for non-English language function calls.
Updated Aug 10, 2026. Default version: GPT-3.5 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.
| text style control | polish | 210 | 1226.1 | 144 | N/A | |
| text | polish | 213 | 1120.0 | 144 | N/A | |
| text style control | japanese | 221 | 1142.0 | 965 | N/A | |
| text | japanese | 227 | 1043.8 | 965 | N/A | |
| text style control | korean | 237 | 1153.2 | 1,184 | N/A | |
| text style control | spanish | 237 | 1227.3 | 895 | N/A | |
| text style control | french | 240 | 1230.2 | 1,284 | N/A | |
| text | korean | 244 | 1018.9 | 1,184 | N/A | |
| text | french | 247 | 1116.5 | 1,284 | N/A | |
| text | spanish | 250 | 1119.8 | 895 | N/A | |
| text style control | german | 254 | 1196.8 | 1,885 | N/A | |
| text | german | 262 | 1090.3 | 1,885 | N/A | |
| text style control | industry writing and literature and language | 293 | 1224.4 | 16,149 | N/A | |
| text style control | industry entertainment and sports and media | 294 | 1196.4 | 9,653 | N/A | |
| text style control | coding | 295 | 1274.4 | 11,130 | N/A | |
| text style control | russian | 295 | 1218.3 | 5,447 | N/A | |
| text style control | industry legal and government | 297 | 1248.7 | 3,573 | N/A | |
| text style control | industry medicine and healthcare | 297 | 1227.1 | 3,837 | N/A | |
| text style control | non english | 297 | 1207.5 | 26,251 | N/A | |
| text style control | instruction following | 298 | 1214.0 | 23,523 | N/A | |
| text style control | multi turn | 300 | 1200.1 | 10,274 | N/A | |
| text style control | chinese | 301 | 1209.4 | 7,558 | N/A | |
| text style control | expert | 301 | 1194.8 | 3,207 | N/A | |
| text style control | math | 301 | 1200.5 | 8,626 | N/A | |
| text | russian | 302 | 1122.4 | 5,447 | N/A | |
| text style control | overall | 304 | 1224.6 | 66,207 | N/A | |
| text style control | creative writing | 304 | 1189.6 | 9,694 | N/A | |
| text style control | industry mathematical | 305 | 1197.4 | 7,493 | N/A | |
| text style control | industry software and it services | 305 | 1245.3 | 18,975 | N/A | |
| text style control | longer query | 305 | 1220.5 | 6,707 | N/A | |
| text style control | exclude ties | 306 | 1110.5 | 44,422 | N/A | |
| text style control | hard prompts | 307 | 1228.0 | 18,544 | N/A | |
| text | expert | 309 | 1064.7 | 3,207 | N/A | |
| text style control | hard prompts english | 309 | 1239.8 | 12,416 | N/A | |
| text style control | industry business and management and financial operations | 310 | 1198.9 | 6,898 | N/A | |
| text | math | 311 | 1141.8 | 8,626 | N/A | |
| text | non english | 311 | 1107.5 | 26,251 | N/A | |
| text style control | industry life and physical and social science | 311 | 1223.1 | 11,407 | N/A | |
| text | industry legal and government | 312 | 1118.0 | 3,573 | N/A | |
| text | industry medicine and healthcare | 312 | 1073.5 | 3,837 | N/A | |
| text | instruction following | 312 | 1119.0 | 23,523 | N/A | |
| text | industry writing and literature and language | 313 | 1139.0 | 16,149 | N/A | |
| text style control | english | 313 | 1236.9 | 39,956 | N/A | |
| text | chinese | 314 | 1074.4 | 7,558 | N/A | |
| text | coding | 314 | 1136.9 | 11,130 | N/A | |
| text | industry mathematical | 314 | 1126.8 | 7,493 | N/A | |
| text | multi turn | 314 | 1116.8 | 10,274 | N/A | |
| text | longer query | 316 | 1121.1 | 6,707 | N/A | |
| text | exclude ties | 322 | 967.8 | 44,422 | N/A | |
| text | hard prompts | 322 | 1108.2 | 18,544 | N/A | |
| text | industry entertainment and sports and media | 322 | 1089.1 | 9,653 | N/A | |
| text | overall | 323 | 1125.1 | 66,207 | N/A | |
| text | industry software and it services | 323 | 1116.3 | 18,975 | N/A | |
| text | hard prompts english | 324 | 1123.7 | 12,416 | N/A | |
| text | industry business and management and financial operations | 327 | 1075.9 | 6,898 | N/A | |
| text | creative writing | 331 | 1092.7 | 9,694 | N/A | |
| text | english | 331 | 1139.4 | 39,956 | N/A | |
| text | industry life and physical and social science | 333 | 1087.4 | 11,407 | 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.
| Azure Cognitive Services | gpt-3.5-turbo-0125 | global | $0.50 | $1.5 | 16.4K | |
| Azure | gpt-3.5-turbo-0125 | global | $0.50 | $1.5 | 16.4K | |
| OpenAI | gpt-3.5-turbo | global | $0.50 | $1.5 | 16.4K |
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-3.5 Turbo | 12.5 | N/A | 16.4K | 4.1K | No | Proprietary |
A concise description based on the published model registry.
The latest GPT-3.5 Turbo model with higher accuracy at responding in requested formats and a fix for a bug which caused a text encoding issue for non-English language function calls.
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-3.5-Turbo.
GPT-3.5-Turbo's default version was released on Mar 21, 2023.
GPT-3.5-Turbo's official API price is $0.50 per million input tokens and $1.5 per million output tokens via OpenAI. The lowest tracked third-party offer starts at $0.50 input and $1.5 output via Azure Cognitive Services.
GPT-3.5-Turbo is published under OpenAI in the model registry.
The default version has a 16.4K token context window.
No. The default version is not marked as having publicly available weights.
3 published provider offerings are linked to the default version.
Nearby ranked alternatives include Qwen2 7B, Gemma 4 E2B, Qwen3 VL 8B.