Use casesDevelopersBrowser use
Drex for browser use.
A computer-use agent makes dozens of decisions per task, each one from a screenshot. Drex Max makes each in one pass, from screens, charts, forms, photos and video, and returns a probability for every option you give it.
- 74.5
- Decision Index Vision, vs 63.9
- 174 ms
- per screenshot, vs 253 ms
- 0.780
- OSWorld-Verified, vs 0.734
Trusted by
- Big Fouraccounting firm
One screenshot in. One probability per option out.
The agent you already run keeps its planner and its tools. Drex Max takes the small decisions in between.
- 01
Send the screen
A screenshot, a screencast frame, a chart or a photo. Drex Max accepts every size. Jev 1.14 rejects 15.9% of images by side length.
- 02
Ask typed questions
Which element to click. Whether the page has finished loading. Which result to open. Each question lists its options, and one forward pass scores them all.
- 03
Act on the confident calls
Every answer is a calibrated probability. Threshold it: click when the model is sure, hand the step to a person when it is not. Median 174 ms per decision.
Measured on screens. The public Decision Index Vision suite.
A browser agent reads charts, forms, menus and photos as often as plain text. Drex Max is scored on all of them.
Perception
- Drex Max
- 86.3
- GPT-6 Luna Decisions
- 73.8
- Drex Max
- 74.1
- GPT-6 Luna Decisions
- 63.7
- Drex Max
- 84.0
- GPT-6 Luna Decisions
- 75.0
- Drex Max
- 93.0
- GPT-6 Luna Decisions
- 83.8
Documents & charts
- Drex Max
- 86.1
- GPT-6 Luna Decisions
- 78.8
- Drex Max
- 98.8
- GPT-6 Luna Decisions
- 93.8
- Drex Max
- 95.5
- GPT-6 Luna Decisions
- 97.5
Agentic
- Drex Max
- 88.6
- GPT-6 Luna Decisions
- 81.2
Reasoning & safety
- Drex Max
- 48.9
- GPT-6 Luna Decisions
- 32.5
- Drex Max
- 53.6
- GPT-6 Luna Decisions
- 41.2
- Drex Max
- 70.6
- GPT-6 Luna Decisions
- 71.2
And the agent benchmarks
- 0.780 vs 0.734
- OSWorld-Verified · automation desktop tasks, end to end
- 0.737 vs 0.687
- OSWorld-V2 · automation desktop tasks, second edition
- 88.6 vs 81.2
- Mind2Web web tasks from natural-language instructions
Vision scores are Drex Max against GPT-6 Luna Decisions on the public Decision Index Vision suite, edition 0.3.2. OSWorld scores are Drex Max against Jev 1.14; Mind2Web is against GPT-6 Luna Decisions. Latency is the median API time per decision, one request at a time, on the same 243 screenshot questions from the same client. 11 vision benchmarks in all.
Fast and cheap enough for every step.
A generative model pays for every token it writes. Drex Max writes nothing, so a decision costs one pass over the input no matter how many options it scores.
That makes it cheap enough to call on every step of every task: before each click, after each page load, on every frame that matters.
Two ways in. One key.
Model id `drex-max`, pinned. Send the screenshot in the `images` array, up to 8 per request, with the same typed questions every Drex model takes. Priced at $0.06 per million input tokens; output is not billed.
Put a decision model where the guesswork is.
Free to try today. Tuned on your decisions and served in your environment when you are ready.