#129
AN
Claude Haiku 3
Anthropic
34.1 LLMBoard
Anthropic model product
Claude Sonnet 4.5 is the best coding model in the world. It's the strongest model for building complex agents. It’s the best model at using computers. And it shows substantial gains in reasoning and math. Highest intelligence across most tasks with exceptional agent and coding capabilities.
Updated Aug 10, 2026. Default version: Claude Sonnet 4.5
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.
| text factuality | korean | 18 | 1403.1 | 545 | N/A | |
| text factuality | spanish | 21 | 1453.5 | 1,264 | N/A | |
| document | overall | 22 | 1446.2 | 28,634 | N/A | |
| text factuality | longer query | 22 | 1486.3 | 18,206 | N/A | |
| text | longer query | 24 | 1476.2 | 24,698 | N/A | |
| text factuality | coding | 24 | 1522.1 | 12,868 | N/A | |
| text factuality | german | 25 | 1407.1 | 577 | N/A | |
| text style control | creative writing | 25 | 1453.0 | 11,896 | N/A | |
| document style control | overall | 27 | 1446.4 | 28,634 | N/A | |
| text factuality | hard prompts english | 28 | 1496.2 | 16,141 | N/A | |
| text factuality | instruction following | 28 | 1466.7 | 16,226 | N/A | |
| text style control | longer query | 28 | 1483.1 | 24,698 | N/A | |
| text | instruction following | 30 | 1458.5 | 23,108 | N/A | |
| text factuality | creative writing | 30 | 1445.3 | 7,288 | N/A | |
| text style control | spanish | 30 | 1465.2 | 2,159 | N/A | |
| text | coding | 31 | 1485.4 | 19,024 | N/A | |
| text | multi turn | 32 | 1464.8 | 14,082 | N/A | |
| text factuality | multi turn | 32 | 1473.2 | 8,821 | N/A | |
| text | creative writing | 33 | 1440.6 | 11,896 | N/A | |
| text factuality | industry entertainment and sports and media | 33 | 1437.3 | 9,755 | N/A | |
| text factuality | industry writing and literature and language | 33 | 1449.7 | 11,780 | N/A | |
| text | spanish | 34 | 1455.7 | 2,159 | N/A | |
| text factuality | french | 34 | 1474.5 | 1,194 | N/A | |
| text | hard prompts english | 35 | 1470.5 | 23,149 | N/A | |
| text factuality | expert | 35 | 1488.0 | 3,411 | N/A | |
| text style control | industry entertainment and sports and media | 35 | 1442.3 | 15,151 | N/A | |
| text style control | industry writing and literature and language | 35 | 1453.7 | 18,215 | N/A | |
| text factuality | industry software and it services | 36 | 1496.8 | 23,081 | N/A | |
| text style control | coding | 36 | 1513.3 | 19,024 | N/A | |
| text style control | instruction following | 36 | 1462.6 | 23,108 | N/A | |
| text style control | multi turn | 36 | 1478.6 | 14,082 | N/A | |
| text | industry entertainment and sports and media | 37 | 1426.7 | 15,151 | N/A | |
| text style control | hard prompts english | 37 | 1490.1 | 23,149 | N/A | |
| text factuality | industry mathematical | 38 | 1446.8 | 2,503 | N/A | |
| text | industry writing and literature and language | 39 | 1441.3 | 18,215 | N/A | |
| text factuality | hard prompts | 39 | 1480.3 | 43,052 | N/A | |
| text factuality | industry business and management and financial operations | 39 | 1459.5 | 9,453 | N/A | |
| text factuality | polish | 39 | 1403.8 | 1,276 | N/A | |
| text | expert | 40 | 1472.4 | 5,542 | N/A | |
| text | hard prompts | 40 | 1461.8 | 46,202 | N/A | |
| text | industry software and it services | 41 | 1472.1 | 29,528 | N/A | |
| text style control | industry business and management and financial operations | 43 | 1460.6 | 15,291 | N/A | |
| text | industry business and management and financial operations | 44 | 1439.3 | 15,291 | N/A | |
| text factuality | russian | 44 | 1458.4 | 4,693 | N/A | |
| text style control | industry software and it services | 44 | 1497.8 | 29,528 | N/A | |
| text factuality | industry legal and government | 45 | 1466.0 | 3,356 | N/A | |
| text style control | hard prompts | 45 | 1483.4 | 46,202 | N/A | |
| text style control | english | 47 | 1467.8 | 38,268 | N/A | |
| text style control | expert | 47 | 1484.5 | 5,542 | N/A | |
| text factuality | english | 48 | 1462.2 | 34,946 | N/A | |
| text factuality | chinese | 49 | 1485.0 | 2,464 | N/A | |
| text style control | french | 49 | 1476.7 | 1,818 | N/A | |
| text style control | korean | 50 | 1413.6 | 1,252 | N/A | |
| text | english | 51 | 1451.0 | 38,268 | N/A | |
| text | industry legal and government | 54 | 1448.9 | 5,726 | N/A | |
| text style control | exclude ties | 54 | 1458.4 | 58,728 | N/A | |
| text style control | industry legal and government | 54 | 1463.4 | 5,726 | N/A | |
| text | french | 55 | 1457.0 | 1,818 | N/A | |
| text factuality | overall | 55 | 1447.9 | 75,135 | N/A | |
| text style control | overall | 55 | 1454.9 | 80,284 | N/A | |
| text style control | russian | 55 | 1452.7 | 7,853 | N/A | |
| text factuality | industry life and physical and social science | 57 | 1466.1 | 7,905 | N/A | |
| text factuality | industry medicine and healthcare | 57 | 1469.5 | 3,120 | N/A | |
| text style control | industry life and physical and social science | 57 | 1472.2 | 13,002 | N/A | |
| text style control | non english | 57 | 1439.3 | 41,966 | N/A | |
| text | korean | 58 | 1394.9 | 1,252 | N/A | |
| text factuality | exclude ties | 58 | 1447.6 | 54,745 | N/A | |
| text | russian | 59 | 1435.1 | 7,853 | N/A | |
| text style control | industry medicine and healthcare | 59 | 1472.8 | 5,104 | N/A | |
| text style control | german | 60 | 1445.3 | 1,297 | N/A | |
| text | industry mathematical | 61 | 1445.1 | 3,953 | N/A | |
| text style control | japanese | 61 | 1410.7 | 683 | N/A | |
| text | exclude ties | 62 | 1432.7 | 58,728 | N/A | |
| text | overall | 63 | 1437.7 | 80,284 | N/A | |
| webdev | webdev-react | 63 | 1383.5 | 4,935 | N/A | |
| text style control | industry mathematical | 64 | 1451.8 | 3,953 | N/A | |
| text factuality | math | 65 | 1425.6 | 2,852 | N/A | |
| text | japanese | 67 | 1390.4 | 683 | N/A | |
| text | industry life and physical and social science | 68 | 1447.1 | 13,002 | N/A | |
| text factuality | non english | 69 | 1432.2 | 38,900 | N/A | |
| text style control | polish | 69 | 1438.7 | 2,197 | N/A | |
| webdev | overall | 69 | 1385.0 | 15,081 | N/A | |
| webdev | webdev | 69 | 1385.0 | 15,081 | N/A | |
| webdev | webdev-html | 69 | 1389.9 | 10,126 | N/A | |
| text | non english | 70 | 1422.6 | 41,966 | N/A | |
| text | german | 74 | 1423.7 | 1,297 | N/A | |
| text style control | chinese | 77 | 1480.4 | 3,835 | N/A | |
| text | industry medicine and healthcare | 80 | 1441.2 | 5,104 | N/A | |
| text | polish | 82 | 1414.7 | 2,197 | N/A | |
| text | chinese | 85 | 1464.4 | 3,835 | N/A | |
| text style control | math | 88 | 1427.7 | 4,877 | N/A | |
| text | math | 99 | 1421.7 | 4,877 | 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.
| QiHang | claude-sonnet-4-5-20250929 | global | $0.43 | $2.14 | 200K | |
| Jiekou.AI | claude-sonnet-4-5-20250929 | global | $2.7 | $13.5 | 200K | |
| NanoGPT | claude-sonnet-4-5-20250929 | global | $3 | $15 | 1M | |
| LLM Gateway | claude-sonnet-4-5-20250929 | global | $3 | $15 | 200K | |
| 302.AI | claude-sonnet-4-5-20250929 | global | $3 | $15 | 200K | |
| Helicone | claude-sonnet-4-5-20250929 | global | $3 | $15 | 200K | |
| Abacus | claude-sonnet-4-5-20250929 | global | $3 | $15 | 200K | |
| Anthropic | claude-sonnet-4-5-20250929 | global | $3 | $15 | 1M |
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 Sonnet 4.5 | N/A | N/A | 200K | 64K | No | Proprietary |
A concise description based on the published model registry.
Claude Sonnet 4.5 is the best coding model in the world. It's the strongest model for building complex agents. It’s the best model at using computers. And it shows substantial gains in reasoning and math. Highest intelligence across most tasks with exceptional agent and coding 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 Sonnet 4.5.
Claude Sonnet 4.5's default version was released on Sep 29, 2025.
Claude Sonnet 4.5's official API price is $3 per million input tokens and $15 per million output tokens via Anthropic. The lowest tracked third-party offer starts at $0.43 input and $2.14 output via QiHang.
Claude Sonnet 4.5 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.
8 published provider offerings are linked to the default version.
No nearby ranked alternatives are currently available.