Blog · Oct 19, 2026
Introducing Drex Max, a multimodal decision model for computer use
Nace.AI
Drex Max, a decision model that sees the screen
Generally available. First among decision models on the public Decision Index 0.3.2, and it reads text, images and video.
A computer-use agent spends most of its time on small decisions. Which button to click. Which field to fill. Which search result to open. Whether the page has finished loading. A single task can take thirty of them, and today each one usually means sending a screenshot to a large frontier model and waiting seconds while it writes an answer.
Today we are releasing Drex Max. It is our most capable decision model, and the first one that sees. You give it a screenshot, a screencast, a scanned document, a chart or a photo, along with a set of typed questions, and one forward pass returns a probability for every option you supplied. Drex Max is built to sit inside that loop and make each of those small decisions in milliseconds, at a fraction of what a frontier model costs.
Benchmarks
Decision models benchmark
| Benchmark | Drex Max | Drex v2.0 | Drex v1.5 | Jev 1.14 | GPT-6 Luna Decisions | GPT-6 Sol | Claude Opus 5.5 |
|---|---|---|---|---|---|---|---|
| Decision benchmarks | |||||||
| Decision Index (public) | 67.6 | 61.3 | 58.1 | 60.7 | 47.8 | – | – |
| JevBench | 92.2 | 85.7 | 84.8 | 86.7 | 91.0 | 99.1 | 100.0 |
| Decision Bench | 94.3 | 88.3 | 86.8 | 92.3 | 90.5 | 94.7 | 95.6 |
| DecideBench (item) | 98.5 | 96.5 | 90.0 | 98.0 | 97.2 | 99.2 | 98.8 |
| DecideBench (pair) | 97.0 | 93.5 | 80.5 | 96.0 | 94.5 | 98.5 | 98.5 |
| Game Bench (win %) | 64.0 | 60.3 | 58.7 | 50.0 | 57.5 | 65.0 | 63.0 |
| Knowledge | |||||||
| MMLU-Pro | 72.5 | 72.8 | 58.6 | 82.1 | 58.1 | 93.0 | 94.0 |
| HLE | 19.0 | 12.8 | 11.4 | 19.4 | 12.3 | 39.0 | 56.0 |
| CRUXEval | 85.8 | 84.6 | 76.7 | 74.7 | 66.4 | 100.0 | 95.0 |
| Reasoning | |||||||
| ARC-Challenge | 97.4 | 96.8 | 95.9 | 97.6 | 96.9 | 99.0 | 98.0 |
| ARC-Easy | 99.4 | 98.6 | 97.9 | 99.3 | 99.0 | 100.0 | 100.0 |
| HellaSwag | 97.9 | 95.9 | 92.1 | 94.3 | 91.4 | 93.0 | 96.0 |
| Agentic benchmarks | |||||||
| OSWorld-Verified (automation) | 0.780 | 0.698 | 0.676 | 0.734 | 0.747 | 0.756 | 0.790 |
| OSWorld-V2 (automation) | 0.737 | 0.636 | 0.640 | 0.687 | 0.659 | 0.744 | 0.761 |
| BFCL (tool calling) | 98.2 | 96.6 | 94.9 | 96.4 | 94.2 | 94.7 | 97.3 |
| ToolRet (tool retrieval) | 70.6 | 67.3 | 70.2 | 65.0 | 60.4 | 72.7 | 74.8 |
| When2Call | 85.2 | 86.5 | 89.7 | 81.7 | 70.2 | 78.3 | 86.7 |
| RAGTruth | 84.8 | 82.5 | 82.7 | 75.1 | 77.0 | 72.5 | 69.8 |
| Efficiency | |||||||
| Median latency | 183 ms | 151 ms | 145 ms | 196 ms | 326 ms | ~2.0 s | ~3.5 s |
| Cost (per 1k decisions) | $0.06 | $0.06 | $0.04 | $0.042 | $0.10 | $3.33 | $10.17 |
Decision Index Vision (public)
| Benchmark | Drex Max | GPT-6 Luna Decisions |
|---|---|---|
| Overall | ||
| Public Vision Index | 74.5 | 63.9 |
| Perception | ||
| CV-Bench | 86.3 | 73.8 |
| BLINK | 74.1 | 63.7 |
| RealWorldQA | 84.0 | 75.0 |
| Winoground | 93.0 | 83.8 |
| Documents & charts | ||
| CharXiv | 86.1 | 78.8 |
| InfographicVQA | 98.8 | 93.8 |
| KIE (CORD + FUNSD) | 95.5 | 97.5 |
| Agentic | ||
| Mind2Web | 88.6 | 81.2 |
| Reasoning & safety | ||
| R-Bench-M | 48.9 | 32.5 |
| MMMU-Pro vision | 53.6 | 41.2 |
| Hateful Memes (moderation) | 70.6 | 71.2 |
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.
The recordings in this post show what that adds up to: an agent that books a flight or watches a live camera, with Drex Max making each decision along the way.
Pricing and availability
Drex Max is available today through the Nace API at $0.06 per million input tokens, with a 262K-token context window. Sign up at console.nace.ai and get $25 in free credits to try it on your own screens.