Skip to content
Agent Shootout

Weekly public leaderboard

Same task.
Every AI agent.
Scored on video.

Five everyday jobs, given to ten general-purpose agents. The prompt matches. The session is new. The screen is recorded. The result is a pass, a partial, or a fail — plus the interventions, the clock, and the cost.

  • Trip plan
  • Inbox triage
  • Local research
  • Grocery cart
  • Expense report
See the boardHow scoring works

Get the weekly results

One letter when the week’s films and scores are in.

The address is sent to Kit, which delivers the letter. The confirmation page says “You're in! Watch your inbox for the first shootout.” Unsubscribe in any edition.

How it works

One public comparison, repeated. The field this round is the ten agents on the board. Nothing has been scored yet.

  1. 01

    Same prompt

    The task is written once and pasted word for word. No agent gets a rewritten brief.

  2. 02

    Fresh session

    Each run starts clean. No leftover chat, no memory, no instructions carried over.

  3. 03

    On video

    The screen is recorded. One labeled run is the score. That film is the evidence.

  4. 04

    Same week

    Every agent in the table runs inside one week. The letter goes out with the scores.

Edition · Testing soon

Preview leaderboard

No filmed week has been scored. Every cell stays Testing soon until a run is on video.

Preview leaderboard of ten agents. No task has been scored yet. Every result is Testing soon.
AgentTrip planInbox triageLocal researchGrocery cartExpense reportInterventionsTimeCost
ChatGPT agentTesting soonTesting soonTesting soonTesting soonTesting soonTesting soonTesting soonTesting soon
Claude CoworkTesting soonTesting soonTesting soonTesting soonTesting soonTesting soonTesting soonTesting soon
ManusTesting soonTesting soonTesting soonTesting soonTesting soonTesting soonTesting soonTesting soon
GensparkTesting soonTesting soonTesting soonTesting soonTesting soonTesting soonTesting soonTesting soon
Perplexity CometTesting soonTesting soonTesting soonTesting soonTesting soonTesting soonTesting soonTesting soon
GeminiTesting soonTesting soonTesting soonTesting soonTesting soonTesting soonTesting soonTesting soon
GrokTesting soonTesting soonTesting soonTesting soonTesting soonTesting soonTesting soonTesting soon
LindyTesting soonTesting soonTesting soonTesting soonTesting soonTesting soonTesting soonTesting soon
Simular SaiTesting soonTesting soonTesting soonTesting soonTesting soonTesting soonTesting soonTesting soon
OpenClawTesting soonTesting soonTesting soonTesting soonTesting soonTesting soonTesting soonTesting soon

Field order for now. Once scores exist: pass rate, then fewer interventions, then lower cost.

Scoring rulesPaid slots are labeled

Scroll sideways for every task and metric.