#129
AN
Claude Haiku 3
Anthropic
34.1 LLMBoard
Anthropic model product
Claude Opus 4 is Anthropic's most powerful model and the world's best coding model, part of the Claude 4 family. It delivers sustained performance on complex, long-running tasks and agent workflows. Opus 4 excels at coding, advanced reasoning, and can use tools (like web search) during extended thinking. It supports parallel tool execution and has improved memory capabilities.
Updated Aug 10, 2026. Default version: Claude Opus 4
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.
No published version under this unique model currently has enough benchmark coverage to calculate a score.
Published benchmark records for the scored version currently unavailable.
No published benchmark result is linked to the scored version.
Preference and agent-evaluation signals from published Arena datasets.
| vision style control | creative writing | 8 | 1258.4 | 192 | N/A | |
| vision | creative writing | 9 | 1253.4 | 192 | N/A | |
| vision style control | homework | 64 | 1237.5 | 327 | N/A | |
| text style control | creative writing | 69 | 1416.4 | 5,469 | N/A | |
| vision | homework | 69 | 1224.1 | 327 | N/A | |
| vision style control | english | 74 | 1196.2 | 1,027 | N/A | |
| text style control | longer query | 77 | 1446.8 | 8,347 | N/A | |
| vision style control | diagram | 77 | 1203.4 | 465 | N/A | |
| vision style control | ocr | 77 | 1197.2 | 1,352 | N/A | |
| text style control | industry writing and literature and language | 78 | 1418.5 | 9,411 | N/A | |
| vision style control | overall | 79 | 1188.9 | 2,201 | N/A | |
| text style control | german | 82 | 1430.3 | 1,229 | N/A | |
| text style control | japanese | 82 | 1381.0 | 973 | N/A | |
| vision | ocr | 82 | 1179.0 | 1,352 | N/A | |
| vision | diagram | 84 | 1175.3 | 465 | N/A | |
| vision | english | 84 | 1186.7 | 1,027 | N/A | |
| vision | overall | 85 | 1175.6 | 2,201 | N/A | |
| text style control | industry entertainment and sports and media | 88 | 1399.5 | 7,574 | N/A | |
| text style control | russian | 89 | 1426.2 | 2,807 | N/A | |
| text style control | industry legal and government | 90 | 1438.0 | 2,909 | N/A | |
| text style control | industry medicine and healthcare | 93 | 1446.8 | 2,635 | N/A | |
| text style control | multi turn | 97 | 1428.3 | 7,692 | N/A | |
| text style control | polish | 100 | 1405.1 | 3,181 | N/A | |
| text style control | korean | 101 | 1362.9 | 963 | N/A | |
| text style control | instruction following | 105 | 1413.7 | 10,689 | N/A | |
| text style control | coding | 109 | 1464.4 | 7,892 | N/A | |
| text | japanese | 112 | 1330.2 | 973 | N/A | |
| text style control | expert | 113 | 1436.1 | 2,217 | N/A | |
| text style control | hard prompts | 114 | 1435.1 | 19,145 | N/A | |
| text style control | hard prompts english | 114 | 1442.8 | 9,905 | N/A | |
| text | creative writing | 118 | 1374.5 | 5,469 | N/A | |
| text style control | french | 119 | 1422.6 | 580 | N/A | |
| text style control | spanish | 119 | 1396.6 | 869 | N/A | |
| text style control | english | 120 | 1425.1 | 21,407 | N/A | |
| text | longer query | 121 | 1401.5 | 8,347 | N/A | |
| text style control | overall | 121 | 1412.6 | 44,134 | N/A | |
| text style control | chinese | 121 | 1445.4 | 2,414 | N/A | |
| text style control | exclude ties | 122 | 1400.0 | 32,006 | N/A | |
| text style control | industry life and physical and social science | 123 | 1429.7 | 7,069 | N/A | |
| text style control | non english | 123 | 1397.2 | 22,716 | N/A | |
| text | industry writing and literature and language | 124 | 1380.8 | 9,411 | N/A | |
| text style control | industry software and it services | 127 | 1441.8 | 14,838 | N/A | |
| text style control | math | 130 | 1403.8 | 2,759 | N/A | |
| text | german | 131 | 1371.8 | 1,229 | N/A | |
| text style control | industry mathematical | 133 | 1410.1 | 2,632 | N/A | |
| text style control | industry business and management and financial operations | 134 | 1402.4 | 7,175 | N/A | |
| text | russian | 136 | 1380.5 | 2,807 | N/A | |
| text | instruction following | 141 | 1372.8 | 10,689 | N/A | |
| text | coding | 144 | 1401.7 | 7,892 | N/A | |
| text | industry entertainment and sports and media | 144 | 1348.7 | 7,574 | N/A | |
| text | multi turn | 144 | 1385.8 | 7,692 | N/A | |
| text | expert | 148 | 1371.3 | 2,217 | N/A | |
| text | korean | 150 | 1302.4 | 963 | N/A | |
| text | hard prompts | 152 | 1375.8 | 19,145 | N/A | |
| text | french | 153 | 1364.2 | 580 | N/A | |
| text | hard prompts english | 155 | 1384.5 | 9,905 | N/A | |
| text | industry legal and government | 155 | 1372.8 | 2,909 | N/A | |
| text | industry mathematical | 155 | 1377.0 | 2,632 | N/A | |
| text | polish | 155 | 1341.7 | 3,181 | N/A | |
| text | spanish | 156 | 1350.4 | 869 | N/A | |
| text | chinese | 160 | 1387.2 | 2,414 | N/A | |
| text | math | 162 | 1373.8 | 2,759 | N/A | |
| text | non english | 163 | 1349.3 | 22,716 | N/A | |
| text | exclude ties | 165 | 1330.1 | 32,006 | N/A | |
| text | overall | 166 | 1364.5 | 44,134 | N/A | |
| text | english | 168 | 1376.7 | 21,407 | N/A | |
| text | industry medicine and healthcare | 168 | 1364.9 | 2,635 | N/A | |
| text | industry software and it services | 168 | 1378.7 | 14,838 | N/A | |
| text | industry life and physical and social science | 174 | 1362.5 | 7,069 | N/A | |
| text | industry business and management and financial operations | 179 | 1335.9 | 7,175 | 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.
| Jiekou.AI | claude-opus-4-20250514 | global | $13.5 | $67.5 | 200K | |
| NanoGPT | claude-opus-4-20250514 | global | $15 | $75 | 200K | |
| 302.AI | claude-opus-4-20250514 | global | $15 | $75 | 200K | |
| Abacus | claude-opus-4-20250514 | global | $15 | $75 | 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.
| Claude Opus 4 | N/A | N/A | 200K | 32K | No | Proprietary |
A concise description based on the published model registry.
Claude Opus 4 is Anthropic's most powerful model and the world's best coding model, part of the Claude 4 family. It delivers sustained performance on complex, long-running tasks and agent workflows. Opus 4 excels at coding, advanced reasoning, and can use tools (like web search) during extended thinking. It supports parallel tool execution and has improved memory 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.
Recommendations prioritize the same model type and family, then the closest published LLMBoard score.
Common questions about Claude Opus 4.
Claude Opus 4's default version was released on May 22, 2025.
No official standard PAYG price is currently available for Claude Opus 4. The lowest tracked third-party offer starts at $13.5 input and $67.5 output via Jiekou.AI.
Claude Opus 4 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.
4 published provider offerings are linked to the default version.
No nearby ranked alternatives are currently available.