ego(lite) articles

Everything you need to know about browser automation

Guides, insights, comparisons, and reviews across Playwright MCP, Browser Use, Chrome DevTools MCP, coding agents, and the browsers they drive.

Moon, botanical leaves and a celestial map collage against a starry sky for the GPT-6 Astra browser benchmark

Benchmarks

GPT-6 Astra browser use benchmark with three browser tools

GPT-6 Astra passed 23 of 28 tasks with ego-browser and playwright-cli, and 20 with agent-browser. Compare shared-task speed, calls and cost.

Nov 16, 2026 · 16 min read

Abstract paper collage on a blue background for the Grok 4.7 browser tool benchmark

Benchmarks

We benchmarked Grok 4.7 browser use with ego-browser, agent-browser and playwright-cli

Grok 4.7 passed 16 of 28 tasks with ego-browser, 12 with agent-browser and 11 with playwright-cli. Compare success, speed and cost.

Nov 13, 2026 · 13 min read

Orange paper character on pale blue paper for the Claude Fable 5.2 vs 5.1 browser agent benchmark

Benchmarks

Is Claude Fable 5.2 worth switching to for browser agents?

Fable 5.2 passed 25 of 28 browser tasks against 23 for Fable 5.1. On the 23 both passed, it averaged 418.5 seconds and $2.63 per task.

Nov 13, 2026 · 14 min read

White blossoms on a sky-blue background for the browser use and computer use benchmark

Benchmarks

Browser use or computer use? We tested three tools on everyday tasks, here is what we found out

One model, three tools, seven everyday tasks. ego-browser passed five, agent-desktop four and Cua Driver two; compare the recorded results, time and token spend.

Nov 11, 2026 · 12 min read

Watercolor flowers on a pale blue background for the GPT-6.1 Sol browser tool benchmark

Benchmarks

How GPT-6.1 Sol performed with three browser tools

GPT-6.1 Sol passed 27 of 28 tasks with ego-browser, 23 with agent-browser and 22 with playwright-cli. Compare completion, shared-task speed and recorded execution costs.

Nov 11, 2026 · 15 min read

Abstract sky-blue collage for Gemini 4 Argon vs Gemini 3.1 Pro browser task results and costs

Benchmarks

We benchmarked Gemini 4 Argon against Gemini 3.1 Pro Preview on browser tasks

We benchmarked Gemini 4 Argon and Gemini 3.1 Pro Preview on 15 shared browser tasks, comparing success rates, tool calls and token costs, including failed attempts.

Nov 10, 2026 · 14 min read

Two orange citrus forms and green leaves on a blue background for the DeepSeek V4.1 Flash vs GPT-6.1 Sol comparison

Benchmarks

DeepSeek V4.1 Flash's browser use benchmarked against GPT-6.1 Sol on 72 web tasks

Across 72 web tasks run twice per model, GPT-6.1 Sol passed 121 of 144 attempts and DeepSeek V4.1 Flash passed 82. Compare their browser workflows, speed, cost and complete results.

Nov 10, 2026 · 22 min read

DeepSeek V4.1 Flash browser benchmark cover with layered translucent leaf forms on a pale blue background

Benchmarks

DeepSeek V4.1 Flash browser automation tools compared

For DeepSeek V4.1 Flash browser automation in our tested pi setup, we'd choose ego-browser for its higher completion count.

Nov 10, 2026 · 15 min read

Three growing circles filled with clouds on a blue background for the GPT-6.1 Sol browser benchmark.

Benchmarks

GPT-6.1 Sol browser use vs GPT-6 Sol in three tools

For the pi browser-agent setup we tested, we'd choose GPT-6.1 Sol over GPT-6 Sol for more completed tasks and lower model cost, rather than a consistent speed gain.

Nov 10, 2026 · 12 min read