
Openbenchmarks for Agents
用独立验证的数据对比和评估 SaaS API,辅助自建或购买决策。
fenilsuchak · HN
OpenBenchmarks – Helping agents discover and pick the right SaaS APIs
完整作品展
技术栈
23 projects

用独立验证的数据对比和评估 SaaS API,辅助自建或购买决策。
fenilsuchak · HN
OpenBenchmarks – Helping agents discover and pick the right SaaS APIs

与AI模型进行策略游戏,查看大语言模型在排行榜上的排名。
masterchef2209 · HN
I created a platform to check which AI models is the best gamer

分析TikTok视频在你的基线和细分市场中的表现,发现爆款内容格式。
@AnthonyCasauria · X
no human touched these — ViralVault's blog just shipped 2 more posts on autopilot. imaged, quality-checked, and published by the pipeline itself. 100-article backlog, chipping away. check it out → @viralvaultapp #buildinpublic #solofounder

对比多个LLM API提供商的延迟和吞吐量。
@QAInsights · X

跨14个维度分析Python代码,检测违规并提供详细报告。
@KSFirasa · X
Hello! I built a tool that profiles code (python only atm) across 14 dimensions detecting violations and capabilities outputting a full report. A bit more nuanced than "AI-powered insights". Free while in beta. Thank you!

提交网站获得每日速度排名和性能监控。
@thefastestweb · X
daily speed monitoring for indie sites. Submit your URL, get ranked on a public leaderboard, and know the moment your performance drops.

对版本控制系统和编码代理进行性能基准测试。
videlov · HN
I was interested in answering this question so I built a benchmark comparing git, jj and gitbutler in agentic context https://vcbench.dev/ Disclaimer - I am a co-founder of GitButler

识别阻碍你的B2B AI或SaaS初创企业发展的最大瓶颈。
@FounderUnstuck · X
If you’re building a startup and want to identify your biggest bottleneck, try the free assessment: 🔗 We’d love to hear if the results match your experience.

分析 GitHub 账户获取评分、徽章、编程语言分布和评价。
@w3ziqv · X
built GitScore — analyzes your GitHub activity and gives you a score from 0 to 1000+ based on commits, stars, impact, and global rank still early, would love brutal feedback

SpecParse 将工程PDF表格自动转换为格式化的Excel工作簿
@SpecParse · X
Convert Complex PDF Tables into Styled Excel Workbooks

汇总Google商业资料评论数据,利用AI生成周度性能简报。
@smooseo · X
For the moment only in French but soon in english : - analyse GBP’s reviews

查看LLM模型在10个基准问题上的评分和排名。
fristovic · HN
She watched me look at model rankings and asked what do the numbers mean... I literally had no good way of explaining it to her so I just came up with something that is approximately in the same ballpark as some of the benchmarks out there lol