ts-bench
Benchmark CLI for comparing AI coding agents on TypeScript workloads. - laiso/ts-bench
ts-bench at a Glance
- Pricing
- Free
- How you use it
- CLI
- Who it's for
- People comparing AI coding agents on TypeScript workloads
- Works with
- Claude Grok Antigravity
ts-bench Key Features
- Benchmark coding agents
- Compare model results
- Run TypeScript workloads
Can't Find What You're Looking For?
We build custom AI agents tailored to your specific business needs. From ideation to deployment, TinyAI.Tools is your partner in AI innovation.
No commitment required. Let's discuss your ideas.
ts-bench Alternatives
STATE-Bench
Benchmark AI Agents on Enterprise Workflows. Contribute to microsoft/STATE-Bench development by creating an account on GitHub.
DM-Code-Agent
Local-first, auditable Python code agent. Ships its own 30-task hidden-test benchmark plus SWE-bench Verified scored by the official harness -- every number reproducible, negative results included. - hwfengcs/DM-Code-Agent
Koala
Run AI agents and other Linux workloads, each in its own lightweight virtual machine, on your Mac or on a Linux machine.
Inillucent
Inillucent is an embedded SQL database written in Rust. It speaks SQLite, is faster than SQLite on 110 of 116 benchmark workloads and 500% faster overall, has vector and keyword search built in, and ships with a command line, a shell and an MCP serve
crux
Taking the pi coding agent to Claude Code-level performance: 0.539 → 0.773 pass@1 on Terminal-Bench 2.1 with the same self-hosted 27B model, by re-engineering the agent. - alanhuangyoo/crux
ego(lite)
Always free, no set up. Claude Code or Codex runs 100+ browser automation tasks at the same time. The fastest agent browser in our open Real-World Bench.