AI - Paski.devClaude Sonnet 4.5
Anthropic llmAnthropic's coding-focused model that set a new state of the art on SWE-bench Verified at launch. The 82.0% figure reported with additional test-time compute is deliberately not recorded.
overall ⌄
54.4
30 of 93 ranked
price · $/M tokens
3 / 15
in / out, as of 2026-07-25
to run it yourself ⌄
API only
no weights to run
Benchmarks
What its maker published, and what anyone else measured. Every figure links the document it came from.
Cheaper, and at least as good
On a 1,000-in, 1,000-out call these cost less and rank no lower — a hard comparison to argue with, and a narrow one. Value covers what it misses.
| DeepSeek V4-Flash DeepSeek | $0.00042 | overall 59.3 |
| DeepSeek V4-Pro DeepSeek | $0.00130 | overall 68.3 |
| MiniMax M3 MiniMax | $0.00150 | overall 65.1 |
| Kimi K2.5 Moonshot AI | $0.00360 | overall 58.8 |
| Qwen3.5 397B A17B Alibaba | $0.00420 | overall 63.7 |
Lineage
No recorded lineage — root or standalone model.
Metadata
| org | Anthropic |
| released | 2025-09-29 |
| license | proprietary |