VitaBench

ICLR'26: 66 tools, real-world apps (delivery, travel, retail); 100 cross-scenario + 300 single-scenario tasks; adopted by Qwen/Seed.

Stars

183

Adoption surface

complex

Autonomy

headless

Recovery

none

License

✅ open-source

Category

Evaluation and benchmarking harnesses

Repository ↗ Example: VitaBench paper ↗

Related in Evaluation and benchmarking harnesses

• Agent Lightning
• SWE-bench
• AgentBench
• inspect_ai
• WebArena
• ClawBench

Maintain VitaBench? Add the badge

Paste this into your README so readers can find the list and see how VitaBench compares:

[![Best of Agent Harnesses](https://img.shields.io/badge/%F0%9F%8F%86_Best_of-Agent_Harnesses-5ac4bf)](https://github.com/RyanAlberts/best-of-Agent-Harnesses)

Copy