Side-by-side comparison of Claude Code, Codex CLI, GitHub Copilot CLI, Claude Code Desktop, OpenCode, OpenCode Go, and Gemini CLI usage from 54 developers on clawdboard. All costs are estimated from token counts and published API pricing.
As of May 17, 2026 at 5:44 PM UTC, 54 developers have tracked $184k in estimated AI coding spend and 236.1B tokens across 7 tools on clawdboard. Claude Code leads with 74.3% of total spend ($137k), followed by Codex CLI at 24.0% ($44.2k), followed by GitHub Copilot CLI at 0.9% ($1.6k), followed by Claude Code Desktop at 0.7% ($1.3k), followed by OpenCode at 0.1% ($222.78), followed by OpenCode Go at 0.0% ($30.17), and Gemini CLI at 0.0% ($2.84). Data is updated hourly from opt-in developer usage logs.Last updated: May 17, 2026 at 5:44 PM UTC · Refreshed hourly
Aggregate usage across all tracked AI coding tools.
Total Estimated Cost
$184k
across all tools
Total Tokens
236.1B
processed across all tools
Tools Tracked
7
AI coding tools
How is AI coding spend distributed across tools?
Usage, cost, and adoption metrics for each tracked tool.
Anthropic's official CLI for Claude. An agentic coding assistant that works directly in your terminal with full access to your codebase.
Estimated Cost
$137k
74.3% of total
Total Tokens
208.0B
596.8M in / 724.5M out
Developers
33
avg: $4.1k / med: $3.0k
Active Days
2,335
since April 28, 2025
Top models
OpenAI's command-line coding agent that uses GPT-4o and o-series models. Brings OpenAI's models to the terminal for code generation and editing.
Estimated Cost
$44.2k
24% of total
Total Tokens
25.8B
13.2B in / 56.1M out
Developers
15
avg: $2.9k / med: $590.10
Active Days
301
since September 23, 2025
GitHub's agentic command-line coding assistant. Multi-model support (Claude, GPT, etc.) billed in premium-request units alongside token-level metrics.
Estimated Cost
$1.6k
0.9% of total
Total Tokens
891.0M
451.9M in / 7.0M out
Developers
2
avg: $818.29 / med: $818.29
Active Days
22
since March 30, 2026
The Claude desktop app's in-app coding agent (Cowork / Dispatch). Captures usage from local-agent-mode sessions running inside the desktop app, separate from the Claude Code CLI.
Estimated Cost
$1.3k
0.7% of total
Total Tokens
1.1B
3.0M in / 208.2k out
Developers
9
avg: $141.94 / med: $24.92
Active Days
91
since January 1, 1999
An open-source terminal-based AI coding assistant that supports multiple LLM providers. Designed as a flexible alternative with provider-agnostic model support.
Estimated Cost
$222.78
0.1% of total
Total Tokens
252.6M
35.1M in / 1.3M out
Developers
7
avg: $31.83 / med: $4.33
Active Days
61
since August 8, 2025
OpenCode's Go subscription tier — a curated set of high-performance open-source models (GLM, MiMo, DeepSeek, Kimi, Qwen, MiniMax) accessed through the OpenCode TUI.
Estimated Cost
$30.17
0% of total
Total Tokens
129.1M
8.2M in / 1.0M out
Developers
1
avg: $30.17 / med: $30.17
Active Days
13
since April 28, 2026
Google's official command-line coding agent powered by the Gemini family of models. Open source, with built-in multimodal and tool-use capabilities.
Estimated Cost
$2.84
0% of total
Total Tokens
10.8M
6.1M in / 108.4k out
Developers
2
avg: $1.42 / med: $1.42
Active Days
4
since April 28, 2026
How does daily estimated spend compare across Claude Code, Codex CLI, GitHub Copilot CLI, Claude Code Desktop, OpenCode, OpenCode Go, and Gemini CLI? This chart shows the 7-day moving average to smooth out daily variance.
7-day moving average of estimated daily cost per tool
Which models do Claude Code users prefer? Cost share breakdown across all models used through Claude Code.
Total estimated cost by model across all users
Which models do Codex CLI users prefer? Cost share breakdown across all models used through Codex CLI.
Total estimated cost by model across all users
Which models do GitHub Copilot CLI users prefer? Cost share breakdown across all models used through GitHub Copilot CLI.
Total estimated cost by model across all users
Which models do Claude Code Desktop users prefer? Cost share breakdown across all models used through Claude Code Desktop.
Total estimated cost by model across all users
Which models do OpenCode users prefer? Cost share breakdown across all models used through OpenCode.
Total estimated cost by model across all users
gemini-3-pro-preview
$92.02 · 41.3% of spend · 1 user
Opus 4.5
$36.43 · 16.4% of spend · 1 user
anthropic/claude-opus-4.5
$21.94 · 9.8% of spend · 1 user
google/gemini-3-pro-preview
$21.86 · 9.8% of spend · 1 user
gpt-5.2-codex
$18.30 · 8.2% of spend · 2 users
anthropic/claude-sonnet-4.5
$8.29 · 3.7% of spend · 1 user
Which models do OpenCode Go users prefer? Cost share breakdown across all models used through OpenCode Go.
Total estimated cost by model across all users
Which models do Gemini CLI users prefer? Cost share breakdown across all models used through Gemini CLI.
Total estimated cost by model across all users
The AI coding tool ecosystem is evolving rapidly. clawdboard currently tracks 7 tools: Claude Code (Anthropic), Codex CLI (OpenAI), GitHub Copilot CLI (GitHub), Claude Code Desktop (Anthropic), OpenCode (Community), OpenCode Go (OpenCode), and Gemini CLI (Google).
By estimated cost, Claude Code currently leads at 74.3% of total spend, followed by Codex CLI (24.0%), GitHub Copilot CLI (0.9%), Claude Code Desktop (0.7%), OpenCode (0.1%), OpenCode Go (0.0%), and Gemini CLI (0.0%).
Cost share is influenced by both adoption (number of users) and model pricing (higher-tier models cost more per token). A tool with fewer users but more expensive models can have a larger cost share than a widely-adopted tool using budget models.
clawdboard is the only platform tracking real usage data across all 7 tools side by side, providing a unique view of how developers actually use AI coding assistants in practice.
Common questions about AI coding tool usage data and comparisons.
clawdboard tracks usage from 7 AI coding tools: Claude Code (Anthropic), Codex CLI (OpenAI), GitHub Copilot CLI (GitHub), Claude Code Desktop (Anthropic), OpenCode (Community), OpenCode Go (OpenCode), and Gemini CLI (Google). Each tool's usage is tracked separately, allowing side-by-side comparison of cost, token usage, and model preferences.
Based on data from 54 developers, Claude Code leads with $137k in estimated API cost (74.3% of total spend). Popularity is measured by estimated cost, which reflects total usage volume weighted by model pricing.
The clawdboard CLI reads local log files from each supported tool on a developer's machine. Claude Code, Codex CLI, GitHub Copilot CLI, Claude Code Desktop, OpenCode, OpenCode Go, and Gemini CLI all maintain local usage logs. The CLI extracts token counts and model identifiers from these logs and syncs aggregate data to clawdboard. No code, prompts, or conversation content is collected.
Yes. If you use multiple supported tools, the clawdboard CLI will detect and sync usage from all installed tools. Your profile page shows a breakdown by tool, and the leaderboard aggregates your total spend across all tools.
All costs are estimated from token counts and published API pricing for each model. Usage is priced at the respective provider's rates (Anthropic, OpenAI, etc.). These are API-equivalent estimates — most developers pay flat subscription fees.
Individual developers sync their usage every 2 hours by default. The aggregate statistics on this page are recalculated hourly. New tools are added to tracking as they gain community adoption.
Works with Claude Code, Codex CLI, GitHub Copilot CLI, Claude Code Desktop, OpenCode, OpenCode Go, and Gemini CLI. Free, open-source, takes 30 seconds.
npx clawdboard auth