Benchspan
https://www.benchspan.comRun agent benchmarks in minutes, not hours
Benchspan is a benchmarking platform for AI agents. If you're building an agent, you need to know if it's getting better. But running benchmarks is slow, expensive, and fragile. You spend days writing glue code every time you want to run a new benchmark, runs take forever on your laptop, and when they fail halfway through you burn hundreds of dollars in tokens with nothing to show for it. Benchspan fixes all of it. Onboard your agent once, and it works with every benchmark on the platform. We onboarded Claude Code in 37 lines of code. Running a benchmark becomes a single command, executed in parallel in the cloud. Every result goes to one place your whole team can see, with full trajectories, token usage, latency, and custom metrics. When runs partially fail, rerun just the subset that errored instead of starting from scratch. Compare runs side by side to see exactly where your agent is improving and where it's regressing.
Total Open and Closed Positions
Total open positions, and positions newly closed since the previous update
Department Headcount Over Time
Open positions per department · top 6 at any point in the window
Newly Opened and Closed Positions
Position Churn Rate
Positions closed within 14 days of opening · a high rate suggests posting instability — duplicates, pulled listings, or roles filled through internal or off-market channels
Time-to-Fill Distribution
Days from open to close · closed positions only
Salary Trend Over Time
Monthly median base salary · USD · annualized · p25/p75 dashed
Salary Range by Department
Employment Type
Technical vs. Non-technical
Open positions · by department
Top Roles by Department
Seniority Mix
Derived from job title keywords
Equity Range by Department
Top Skills
Top Tech Stacks
Skills Trend
Change in share of postings · recent 3 months vs. prior 3 months
Tech Stack Evolution
Positions opened per month · top 5 technologies