Anthropic model product
Claude 3 Sonnet strikes the ideal balance between intelligence and speed—particularly for enterprise workloads. It delivers strong performance at a lower cost compared to its peers, and is engineered for high endurance in large-scale AI deployments.
Updated Aug 10, 2026. Default version: Claude 3 Sonnet
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 style control | chinese | 100 | 979.8 | 915 | N/A | |
| vision | chinese | 101 | 937.0 | 915 | N/A | |
| vision | overall | 132 | 984.0 | 12,314 | N/A | |
| vision style control | overall | 132 | 1017.1 | 12,314 | N/A | |
| vision style control | english | 136 | 1006.6 | 7,799 | N/A | |
| vision | english | 137 | 981.5 | 7,799 | N/A | |
| text style control | polish | 182 | 1312.8 | 284 | N/A | |
| text | polish | 192 | 1258.1 | 284 | N/A | |
| text style control | japanese | 203 | 1195.6 | 1,753 | N/A | |
| text | japanese | 211 | 1131.6 | 1,753 | N/A | |
| text style control | french | 211 | 1300.5 | 1,824 | N/A | |
| text style control | korean | 213 | 1223.0 | 2,059 | N/A | |
| text style control | german | 217 | 1273.1 | 3,097 | N/A | |
| text | french | 220 | 1227.7 | 1,824 | N/A | |
| text | spanish | 227 | 1203.6 | 1,448 | N/A | |
| text style control | spanish | 227 | 1264.5 | 1,448 | N/A | |
| text | korean | 228 | 1127.9 | 2,059 | N/A | |
| text | german | 230 | 1203.6 | 3,097 | N/A | |
| text style control | russian | 250 | 1283.7 | 10,794 | N/A | |
| text style control | expert | 255 | 1270.7 | 5,614 | N/A | |
| text style control | industry medicine and healthcare | 256 | 1297.6 | 5,941 | N/A | |
| text style control | industry legal and government | 261 | 1303.2 | 6,062 | N/A | |
| text style control | multi turn | 261 | 1277.4 | 17,062 | N/A | |
| text style control | non english | 261 | 1267.5 | 48,314 | N/A | |
| text | russian | 262 | 1225.8 | 10,794 | N/A | |
| text style control | coding | 262 | 1317.7 | 18,888 | N/A | |
| text | multi turn | 265 | 1226.9 | 17,062 | N/A | |
| text style control | industry mathematical | 265 | 1260.7 | 12,413 | N/A | |
| text style control | math | 266 | 1253.4 | 13,766 | N/A | |
| text | expert | 267 | 1171.7 | 5,614 | N/A | |
| text style control | industry software and it services | 268 | 1306.8 | 31,448 | N/A | |
| text style control | industry writing and literature and language | 268 | 1268.7 | 27,297 | N/A | |
| text style control | instruction following | 268 | 1267.2 | 38,802 | N/A | |
| text style control | chinese | 269 | 1275.7 | 15,648 | N/A | |
| text style control | longer query | 269 | 1285.9 | 11,870 | N/A | |
| text | industry mathematical | 270 | 1213.0 | 12,413 | N/A | |
| text style control | industry life and physical and social science | 270 | 1298.9 | 19,089 | N/A | |
| text style control | overall | 271 | 1280.8 | 109,284 | N/A | |
| text style control | creative writing | 271 | 1245.3 | 15,592 | N/A | |
| text style control | exclude ties | 271 | 1199.4 | 73,557 | N/A | |
| text | industry medicine and healthcare | 272 | 1187.5 | 5,941 | N/A | |
| text style control | hard prompts | 272 | 1281.8 | 30,725 | N/A | |
| text | math | 273 | 1213.4 | 13,766 | N/A | |
| text | non english | 274 | 1204.9 | 48,314 | N/A | |
| text | coding | 275 | 1223.2 | 18,888 | N/A | |
| text style control | english | 275 | 1288.3 | 60,970 | N/A | |
| text style control | hard prompts english | 275 | 1285.9 | 19,193 | N/A | |
| text style control | industry business and management and financial operations | 275 | 1261.1 | 11,853 | N/A | |
| text style control | industry entertainment and sports and media | 276 | 1239.0 | 15,961 | N/A | |
| text | industry writing and literature and language | 277 | 1217.7 | 27,297 | N/A | |
| text | chinese | 278 | 1187.7 | 15,648 | N/A | |
| text | industry software and it services | 278 | 1221.9 | 31,448 | N/A | |
| text | instruction following | 278 | 1199.8 | 38,802 | N/A | |
| text | industry legal and government | 279 | 1213.9 | 6,062 | N/A | |
| text | longer query | 279 | 1211.3 | 11,870 | N/A | |
| text | overall | 280 | 1218.2 | 109,284 | N/A | |
| text | exclude ties | 280 | 1108.8 | 73,557 | N/A | |
| text | hard prompts | 281 | 1197.4 | 30,725 | N/A | |
| text | english | 282 | 1226.3 | 60,970 | N/A | |
| text | creative writing | 284 | 1186.5 | 15,592 | N/A | |
| text | hard prompts english | 284 | 1204.3 | 19,193 | N/A | |
| text | industry entertainment and sports and media | 284 | 1171.9 | 15,961 | N/A | |
| text | industry life and physical and social science | 284 | 1209.6 | 19,089 | N/A | |
| text | industry business and management and financial operations | 287 | 1173.8 | 11,853 | 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.
The default version has no provider offering with current input or output token prices.
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.
| Claude 3 Sonnet | 40.0 | N/A | 200K | 200K | No | Proprietary |
A concise description based on the published model registry.
Claude 3 Sonnet strikes the ideal balance between intelligence and speed—particularly for enterprise workloads. It delivers strong performance at a lower cost compared to its peers, and is engineered for high endurance in large-scale AI deployments.
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 Claude Sonnet 3.
Claude Sonnet 3's default version was released on Feb 29, 2024.
No official standard PAYG price is currently available for Claude Sonnet 3.
Claude Sonnet 3 is published under Anthropic 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.
No published provider offering is currently linked to the default version.
Nearby ranked alternatives include Qwen3 VL 30B A3B Thinking, Qwen3 Max, Hermes 3 70B.