Agent Metrics

Which AI coding agent is fastest?

Turn times and usage for 15 AI coding agents, from 6.5M+ turns in Zed. Updated weekly.

Last updated: November 16th, 2026

Key Findings

  • GitHub Copilot had the fastest median turn time among the 10 most-used agents, at 30.9 seconds.
  • External agents accounted for 57% of sessions, led by Claude Agent (268K) and Codex CLI (100K).
  • Local models ranked fourth among models used with Zed Agent, with 22K sessions.

Fastest AI Coding Agents by Turn Time

Median (p50) turn time for the selected agents over the last 30 days, fastest first. p10 and p90 show the spread.

Explore Full Methodology

Agent

GitHub Copilot

Claude Agent

Cursor

Pi

Codex CLI

Mistral Vibe

Zed Agent

OpenCode

Kilo

Google Antigravity

Turn Time

The time it takes for an agent or model to respond in seconds. Excludes user think time and measures responsiveness only.

Request Timestamp → Completion Timestamp
p10
p50
p90
0s388s775s
6.2s
30.9s
291.6s
0s388s775s
7.5s
39.4s
420.5s
0s388s775s
8.7s
40.3s
278.2s
0s388s775s
8.0s
50.0s
437.0s
0s388s775s
7.0s
51.8s
570.3s
0s388s775s
5.2s
54.3s
508.7s
0s388s775s
7.1s
57.6s
598.2s
0s388s775s
6.6s
58.3s
604.9s
0s388s775s
5.5s
64.5s
668.7s
0s388s775s
9.6s
85.2s
773.9s
Explore Full Methodology

Total Sessions

813.2K

Total Turns

6.6M
1348,402
2267,917
399,991
445,074
517,373
612,105
712,017
86,582
92,050
101,646

Local Models in the Mix

Local models run entirely on your device, as opposed to cloud-hosted ones.

Learn More

Local Sessions

12.4K

Local Turns

58K

Cross-ecosystem by design

Developers can bring any AI agent they want to Zed (we think of ourselves as the "Switzerland" of editors). Many agents connect through ACP, the Agent Client Protocol, a shared open standard for agent-editor communication.

This means we see agent usage across the ecosystem, not just our own. We can offer a more comprehensive view of how AI agents are actually used than most editors can — or would.

Frequently Asked Questions






Methodology

The metrics on this page are derived from anonymized, aggregated telemetry collected from Zed users who interact with AI agents. No individual session data, user identifiers, or proprietary code is exposed, and all data is aggregated before display.

  • What we collect: When you use an AI agent in Zed, we record metadata about the interaction: which agent was used, how long it took to respond, whether you accepted or rejected the suggested edits, and how many lines of code were involved. For Zed's own agent, we also capture which underlying model powered the response. We do not collect the content of your prompts, the code you're working on, or any personally identifiable information.

  • What we exclude: To ensure the data reflects real-world usage, we exclude all interactions from Zed staff accounts and from Zed Nightly builds (which may contain experimental or unstable behavior). We also apply minimum thresholds: agents and models with very low usage volumes are not displayed to avoid misleading statistics from small sample sizes.

  • How we calculate metrics: Turn time is measured from request initiation to response completion in milliseconds. Error rate is the percentage of turns that resulted in a failure status.

  • When we update: Data is refreshed every week. This cadence allows newly released models and agents to accumulate enough usage for statistically meaningful comparisons while keeping the data reasonably current.

  • Known limitations: Model-level breakdowns are only available for Zed's own agent. External agents like Claude Agent and Codex don't reliably expose which model they're using in their telemetry. We also cannot detect user subscription tiers (e.g., whether someone is using Gemini's free or paid tier), which may affect performance characteristics.