Anthropic model product
Claude 3.5 Haiku is Anthropic's fastest model, delivering advanced coding, tool use, and reasoning capabilities at an accessible price. It excels at user-facing products, specialized sub-agent tasks, and generating personalized experiences from large data volumes. The model is particularly well-suited for code completions, interactive chatbots, data extraction, and real-time content moderation.
Updated Aug 10, 2026. Default version: Claude 3.5 Haiku
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.
Published benchmark records for the scored version Claude 3.5 Haiku.
| DROP | 0.8 | 9 | 30 | 72.4% | C | |
| MGSM | 0.9 | 15 | 31 | 53.3% | C | |
| TAU-bench Airline | 0.2 | 22 | 23 | 4.5% | C | |
| TAU-bench Retail | 0.5 | 24 | 25 | 4.2% | C | |
| HumanEval | 0.9 | 27 | 76 | 65.3% | C | |
| MATH | 0.7 | 41 | 71 | 42.9% | C | |
| SWE-Bench Verified | 0.4 | 95 | 104 | 8.7% | C | |
| MMLU-Pro | 0.7 | 100 | 129 | 22.7% | C | |
| GPQA | 0.4 | 201 | 233 | 13.8% | C |
Preference and agent-evaluation signals from published Arena datasets.
| vision style control | homework | 92 | 1150.3 | 224 | N/A | |
| vision | homework | 94 | 1120.8 | 224 | N/A | |
| vision style control | diagram | 98 | 1134.8 | 322 | N/A | |
| vision | diagram | 100 | 1078.9 | 322 | N/A | |
| vision | ocr | 100 | 1089.4 | 916 | N/A | |
| vision style control | ocr | 100 | 1129.4 | 916 | N/A | |
| vision style control | overall | 105 | 1128.4 | 1,406 | N/A | |
| vision style control | english | 108 | 1127.9 | 671 | N/A | |
| vision | overall | 110 | 1092.7 | 1,406 | N/A | |
| vision | english | 112 | 1098.3 | 671 | N/A | |
| text style control | polish | 169 | 1337.5 | 2,711 | N/A | |
| text style control | japanese | 178 | 1241.4 | 1,446 | N/A | |
| text style control | german | 180 | 1314.3 | 1,692 | N/A | |
| text style control | korean | 183 | 1269.0 | 1,184 | N/A | |
| text style control | french | 185 | 1343.4 | 777 | N/A | |
| text style control | spanish | 189 | 1322.4 | 882 | N/A | |
| text | japanese | 193 | 1175.1 | 1,446 | N/A | |
| text | polish | 196 | 1247.7 | 2,711 | N/A | |
| text style control | industry legal and government | 199 | 1351.1 | 4,268 | N/A | |
| text style control | longer query | 199 | 1344.1 | 10,962 | N/A | |
| text style control | industry entertainment and sports and media | 200 | 1304.5 | 12,455 | N/A | |
| text style control | coding | 201 | 1385.4 | 11,234 | N/A | |
| text style control | creative writing | 203 | 1304.7 | 9,908 | N/A | |
| text | french | 207 | 1262.1 | 777 | N/A | |
| text style control | russian | 208 | 1318.6 | 6,206 | N/A | |
| text style control | industry medicine and healthcare | 210 | 1344.3 | 3,665 | N/A | |
| text style control | industry software and it services | 210 | 1365.0 | 19,985 | N/A | |
| text style control | industry writing and literature and language | 210 | 1313.0 | 16,932 | N/A | |
| text style control | multi turn | 210 | 1326.8 | 11,521 | N/A | |
| text | korean | 211 | 1173.3 | 1,184 | N/A | |
| text | spanish | 212 | 1251.6 | 882 | N/A | |
| text style control | hard prompts | 212 | 1344.5 | 23,749 | N/A | |
| text style control | hard prompts english | 212 | 1357.2 | 13,421 | N/A | |
| text style control | instruction following | 216 | 1314.9 | 21,988 | N/A | |
| text | german | 217 | 1239.3 | 1,692 | N/A | |
| text style control | expert | 217 | 1313.6 | 3,506 | N/A | |
| text style control | industry life and physical and social science | 221 | 1341.8 | 11,924 | N/A | |
| text style control | non english | 221 | 1305.0 | 32,558 | N/A | |
| text style control | overall | 225 | 1324.0 | 69,899 | N/A | |
| text style control | exclude ties | 226 | 1269.7 | 49,273 | N/A | |
| text style control | industry business and management and financial operations | 226 | 1315.5 | 9,148 | N/A | |
| text style control | chinese | 229 | 1316.5 | 4,162 | N/A | |
| text style control | english | 233 | 1336.6 | 37,333 | N/A | |
| text style control | industry mathematical | 233 | 1299.6 | 5,781 | N/A | |
| text | coding | 239 | 1286.7 | 11,234 | N/A | |
| text style control | math | 240 | 1286.4 | 6,353 | N/A | |
| text | russian | 242 | 1253.0 | 6,206 | N/A | |
| text | longer query | 248 | 1260.5 | 10,962 | N/A | |
| text | multi turn | 249 | 1264.8 | 11,521 | N/A | |
| text | industry mathematical | 250 | 1249.3 | 5,781 | N/A | |
| text | industry writing and literature and language | 250 | 1256.1 | 16,932 | N/A | |
| text | industry medicine and healthcare | 252 | 1225.9 | 3,665 | N/A | |
| text | industry software and it services | 253 | 1273.2 | 19,985 | N/A | |
| text | expert | 254 | 1206.9 | 3,506 | N/A | |
| text | hard prompts english | 254 | 1267.7 | 13,421 | N/A | |
| text | industry legal and government | 254 | 1258.4 | 4,268 | N/A | |
| text | math | 254 | 1244.5 | 6,353 | N/A | |
| text | instruction following | 255 | 1240.6 | 21,988 | N/A | |
| text | non english | 255 | 1236.3 | 32,558 | N/A | |
| text | chinese | 256 | 1224.5 | 4,162 | N/A | |
| text | hard prompts | 256 | 1251.1 | 23,749 | N/A | |
| text | industry entertainment and sports and media | 256 | 1224.3 | 12,455 | N/A | |
| text | creative writing | 259 | 1232.6 | 9,908 | N/A | |
| text | industry business and management and financial operations | 260 | 1222.6 | 9,148 | N/A | |
| text | exclude ties | 261 | 1171.8 | 49,273 | N/A | |
| text | overall | 262 | 1255.5 | 69,899 | N/A | |
| text | english | 263 | 1268.9 | 37,333 | N/A | |
| text | industry life and physical and social science | 265 | 1247.1 | 11,924 | 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.
| 302.AI | claude-3-5-haiku-20241022 | global | $0.80 | $4 | 200K | |
| ZenMux | anthropic/claude-3.5-haiku | global | $0.80 | $4 | 200K | |
| DigitalOcean | anthropic-claude-3.5-haiku | global | $0.80 | $4 | 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 3.5 Haiku | 41.2 | N/A | 200K | 8.2K | No | Proprietary |
A concise description based on the published model registry.
Claude 3.5 Haiku is Anthropic's fastest model, delivering advanced coding, tool use, and reasoning capabilities at an accessible price. It excels at user-facing products, specialized sub-agent tasks, and generating personalized experiences from large data volumes. The model is particularly well-suited for code completions, interactive chatbots, data extraction, and real-time content moderation.
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 Haiku 3.5.
Claude Haiku 3.5's default version was released on Oct 22, 2024.
No official standard PAYG price is currently available for Claude Haiku 3.5. The lowest tracked third-party offer starts at $0.80 input and $4 output via 302.AI.
Claude Haiku 3.5 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.
4 published provider offerings are linked to the default version.
Nearby ranked alternatives include Phi 3.5 MoE, Qwen3 Next 80B A3B, GPT-4o-mini.