# Anthropic Claude 3.7 Sonnet Anthropic Claude 3.7 Sonnet was last priced at $3.00 per million input tokens and $15.00 per million output tokens, as of October 22, 2026. None of the 6 coding benchmarks behind the index has measured it, so it has no coding index, but 64 benchmarks outside the index have a result below. Page: https://llmbenchmark.ai/models/claude-3-7-sonnet Data from October 22, 2026. Every figure below names the board it was read from and the day. - Maker: Anthropic - Released: February 24, 2025 - Price per million input tokens: $3.00 - Price per million output tokens: $15.00 - Context window: 200K tokens - Status: retired. No longer sold through the API. Retired on February 19, 2026; last list price shown. Benchmark results (64 of 195): - Aider polyglot: 60.4% (source: Aider polyglot leaderboard, read October 22, 2026) - SWE-bench Verified: 66.4% (source: SWE-bench (swebench.com), read October 22, 2026) - SWE-bench Lite: 48.0% (source: SWE-bench (swebench.com), read October 22, 2026) - SWE-bench (full test set): 33.8% (source: SWE-bench (swebench.com), read October 22, 2026) - SWE-bench Multimodal: 31.3% (source: SWE-bench (swebench.com), read October 22, 2026) - Design Arena: websites: 1193 Elo (source: Design Arena, read October 22, 2026) - Design Arena: UI components: 1148 Elo (source: Design Arena, read October 22, 2026) - Design Arena: game dev: 1138 Elo (source: Design Arena, read October 22, 2026) - Design Arena: data viz: 1196 Elo (source: Design Arena, read October 22, 2026) - Design Arena: 3D: 1093 Elo (source: Design Arena, read October 22, 2026) - Design Arena: all code categories: 1176 Elo (source: Design Arena, read October 22, 2026) - Design Arena: SVG: 1087 Elo (source: Design Arena, read October 22, 2026) - GSO-Bench: 3.8% (source: Epoch AI benchmarking hub, read October 22, 2026) - METR time horizons: 60.0% (source: Epoch AI benchmarking hub, read October 22, 2026) - DeepResearch Bench: 43.6% (source: Epoch AI benchmarking hub, read October 22, 2026) - GPQA Diamond (Epoch AI run): 79.7% (source: Epoch AI benchmarking hub, read October 22, 2026) - ARC-AGI: 28.6% (source: Epoch AI benchmarking hub, read October 22, 2026) - ARC-AGI-2: 0.9% (source: Epoch AI benchmarking hub, read October 22, 2026) - SimpleBench: 46.4% (source: Epoch AI benchmarking hub, read October 22, 2026) - OTIS Mock AIME: 57.8% (source: Epoch AI benchmarking hub, read October 22, 2026) - MATH level 5: 91.2% (source: Epoch AI benchmarking hub, read October 22, 2026) - GeoBench: 68.0% (source: Epoch AI benchmarking hub, read October 22, 2026) - Fiction.LiveBench: 83.3% (source: Epoch AI benchmarking hub, read October 22, 2026) - Creative writing (Lech Mazur): 81.1% (source: Epoch AI benchmarking hub, read October 22, 2026) - Cybench: 20.0% (source: Epoch AI benchmarking hub, read October 22, 2026) - TheAgentCompany: 30.9% (source: Epoch AI benchmarking hub, read October 22, 2026) - OSWorld: 35.8% (source: Epoch AI benchmarking hub, read October 22, 2026) - VPCT: 39.0% (source: Epoch AI benchmarking hub, read October 22, 2026) - Epoch Capabilities Index: 141.0 (source: Epoch AI benchmarking hub, read October 22, 2026) - LMArena Text: 1299 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Text: coding: 1339 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Text: hard prompts: 1315 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Text: math: 1319 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Text: instruction following: 1325 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Text: creative writing: 1317 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Vision: 1151 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Text: English: 1310 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Text: non-English: 1286 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Text: Chinese: 1297 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Text: German: 1281 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Text: Japanese: 1260 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Text: Korean: 1239 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Text: French: 1303 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Text: Spanish: 1290 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Text: Russian: 1310 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Text: Polish: 1279 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Text: multi-turn: 1339 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Text: longer queries: 1355 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Text: expert: 1301 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Text: hard prompts in English: 1320 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Text: software and IT: 1314 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Text: mathematical work: 1314 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Text: science: 1285 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Text: medicine and healthcare: 1258 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Text: legal and government: 1300 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Text: business and finance: 1273 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Text: writing and language: 1324 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Text: entertainment and media: 1300 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Vision: English: 1141 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Vision: Chinese: 1174 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Vision: reading text: 1157 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Vision: diagrams: 1153 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - LMArena Vision: homework: 1206 Elo (source: LMArena (Hugging Face dataset), read October 22, 2026) - SciCode: 4.6% (source: Kaggle Benchmarks, read October 22, 2026)