Ripple-65B Preview delivers strong agentic coding results as a fully Apache 2.0 open US model
AI Digest
Ripple-65BApache 2.0TerminalBench 2.1Inkling 2 Small
Ripple-65B在编码测试中表现优异但其他测试落后，展示开源模型潜力与局限。
Ripple-65B excels in coding benchmarks but lags behind new models in others, highlighting open-source AI's strengths and gaps.
Key points
- Ripple-65B是650亿参数的Apache 2.0开源模型 Ripple-65B is a 65B-parameter Apache 2.0 open model
- 研发成本3200万美元，TerminalBench 2.1测试得分最高 Cost $32M to develop, tops TerminalBench 2.1 coding tests
- 在部分基准测试中落后于Inkling 2 Small Lags behind Inkling 2 Small in some benchmarks
- 采用全Apache 2.0协议开放源码 Fully open-sourced under Apache 2.0
Takeaway: 开源模型在编码任务中表现突出，但需更多测试验证全面能力。 / Open models excel in coding tasks but require more testing to validate overall capabilities.
Why it matters 展示开源模型在特定任务的优势，但需更多数据验证全面能力。
View original ↗ Back to hot list
This page is an aggregated digest from decoder; content and hot-score data come from public sources. Copyright belongs to the original authors. We link to originals with nofollow and never republish full text.