AlibabaResearch/abench
CLI tool
Can I trust it?
No red flags in our checks.
Stars from real accounts No data
We haven't checked its stars for fakes yet.
Active OK
Last change 4 days ago.
Licence OK
Apache-2.0: you can use it for free, also in a commercial product. Keep the licence notice.
Quick checks from public data. They help, but they are no guarantee.
What it is
A Python benchmark that replays recorded agent trajectories (DeepSWE v1.1, LMCache) or a locally generated workload in closed loop against an OpenAI-compatible inference server such as SGLang or vLLM. It reports per-turn TTFT, TPOT and E2E latency, cache behavior and throughput…
Who it's for
Engineers benchmarking LLM inference servers for agentic workloads with multi-turn coding agent trajectories
How to use it
Install
pip install agentic-benchFrom its README. Check it there before running it.
Ask your AI to set it up
Paste this into Claude, ChatGPT or your coding assistant.
Help me install and set up AlibabaResearch/abench in my project. Follow its README: https://github.com/AlibabaResearch/abench. Explain each step and check it is safe before running anything.
Star curve
Alternatives
Similar projects named in its profile. Each link searches the directory.
Get alerts for repos like this
We'll email you when something in Models & inference starts rising. Free, once a week, only what matches.
21,744 GitHub repos watched and ranked every hour. Figures as of 28 October 2026.
What arrives: one email on Mondays with the repos that match, never more. See last week's. Privacy
For maintainers
Add this badge to your README. It shows the repo's place on the radar, updates every hour and links back to this page.
[](https://repoalerts.com/repo/AlibabaResearch/abench?ref=badge)Similar repos
- apple-aiml-research/ml-rsi-inference-bench
A long-horizon benchmark for coding agents that improve the inference stack of large language models in vLLM or SGLang. Tasks cover supporting a model on day 0, optimizing it after launch, and repairi
- facebookresearch/swe-sweep
A benchmark that measures how many bugs language models and agents can find and fix in large real repositories. Agents receive no hints about bug type or location. Tasks run on Harbor and are scored b
- NineAbyss/OR-License
A benchmark of 31 operations research tasks for evaluating LLM agents. Agents query an interactive business-information simulator, write optimization programs in an isolated environment, and submit so
- aicodeking/leanrea
A single 8 KB agent skill file that gives AI coding agents routing rules and ready-to-run plain CLI commands for reverse engineering binaries, Electron apps and bundles, instead of an MCP server. It r
- stablyai/orca
A desktop, mobile and remote-runtime application for running several CLI coding agents side by side, each in its own git worktree, with terminals, diff review, notifications and usage tracking in one
- Generated-Computers/Locals
A local inference server for Apple Silicon Macs that runs many AI agents at once, with tool calls constrained to each tool's schema and prompt caching across turns. It works with coding agents such as