# AI passes 37% of real engineering tasks, most of us would pass none (slim)

> Xplore released RWE-bench on 27 October 2026, 20 mechanical, electrical and aerospace engineering tasks graded by a program that runs physics solvers, with no model judging. GPT-6 Astra leads at 37%. Vlad Cealicu on what the tasks are, how a person off the street would do on them, why the grading matters and what the cost per run says.

- Full: https://www.anchorterminal.com/blog/rwe-bench-engineering.md (~2,500 tokens) · this version ~1,280 tokens · JSON https://www.anchorterminal.com/blog/rwe-bench-engineering.json · canonical https://www.anchorterminal.com/blog/rwe-bench-engineering
- Index: https://www.anchorterminal.com/llms.txt · API: https://www.anchorterminal.com/api/v1/index.json · MCP: https://www.anchorterminal.com/mcp · Updated: 2026-10-27
- Licence: CC BY 4.0, credit Anchor Terminal and link this page (https://www.anchorterminal.com/terms/#data)

By Vlad Cealicu, 27 October 2026. 1,271 words, about 6 min to read.

Xplore, a startup that builds training environments for engineering work, released RWE-bench (Real World Engineering Bench) on Tuesday 27 October 2026 [[1]](#ref-1) [[2]](#ref-2).

- 37%: GPT-6 Astra's average pass rate, the best of 11 models
- 20: tasks across mechanical, electrical and aerospace engineering
- $10: a run for GPT-6.1 Sol, about a sixth of what Astra and Claude Opus 5.5 cost

RWE-bench as published on 27 October 2026. Sources [1] and [2].

## What are the tasks?

They read like a week at an engineering job, not a quiz.

An engineer on Xplore's team who works in that field wrote each task, from problems they've met in industry, along with a reference design built with the same tools the agents get [[1]](#ref-1).

## Why the grading is the interesting part

"Every run is graded automatically by a deterministic verifier, with no LLM judge and no human grading" [[1]](#ref-1).

I think this is the part that matters.

## What do the scores say?

Xplore's page puts GPT-6.1 Sol at $10 a run and says only two models score higher, GPT-6 Astra by 12 points and Claude Opus 5.5 by 4, both at almost six times the cost [[1]](#ref-1).

Six times the money buys 12 points, so spending more isn't where the next jump comes from.

## How would a person off the street do?

Xplore doesn't give a human score, so this part is my estimate, not a measurement.

A good engineering graduate who knows those tools might get a task or two in their own field.

One task, from the brief to a design that passes every check

| Who | Time | Outcome |
| --- | --- | --- |
| GPT-6 Astra | a few hours a run | passes 37% of the 20 tasks |
| A specialist, in their own field | about a week | passes the third in their field |
| An engineering graduate | a month or more | passes a task or two |
| Someone off the street | doesn't finish | passes none |

Time on a log scale.

Pass rate on RWE-bench's 20 tasks, in per cent

| Who | Pass rate |
| --- | --- |
| GPT-6 Astra | 37 |
| A specialist, strong in one field | 33 |
| An engineering graduate | 5 |
| Someone off the street | 0 |

Each series has a zero-based scale.

Against that, a model that passes 37% across mechanical, electrical and aerospace in one run is a strong result, it's a generalist doing a bit of everyone's job.

## What's next?

Xplore says harder tasks and more domains come next, biomechanical, civil and materials engineering [[1]](#ref-1), and their thesis ends with the bar going from a bearing to an engine to a spacecraft [[3]](#ref-3).

CadQuery, Gmsh and CalculiX aren't on Anchor Terminal yet, because they're libraries you run yourself and not something an agent calls over the network.

## The terms, explained

### What is RWE-bench?

Real World Engineering Bench, Xplore's benchmark of 20 mechanical, electrical and aerospace engineering tasks, released on 27 October 2026. Each model works in a sandbox with CAD and simulation tools and hands in a design that a program checks against every requirement.

### Which model scored best?

GPT-6 Astra, with a 37% average pass rate.

### How is it graded?

By a deterministic program, with no model and no person judging.

### How would a person do on RWE-bench?

Xplore doesn't publish a human score.

### What does pass@k mean?

A task counts as passed if any one of k runs at it passes.

---

More in [Opinion](https://www.anchorterminal.com/blog/opinion/index.md) · Older opinion [Slopcore will be a thing](https://www.anchorterminal.com/blog/slopcore.md) · Newer opinion [OpenAI's models say the Exponential Time Hypothesis is false](https://www.anchorterminal.com/blog/openai-three-results.md)

- Older: [Slopcore will be a thing](https://www.anchorterminal.com/blog/slopcore.md)
- Newer: [Can you run GLM-5.3-Flash locally? Yes, on one big machine](https://www.anchorterminal.com/blog/run-glm-5-3-flash-locally.md)
- All posts: https://www.anchorterminal.com/blog/index.md

## References

Read on 27 October 2026. Quotes are as published.

[1] Xplore, "RWE-bench, Real World Engineering Bench", 27 October 2026. Source for the 20 tasks and three domains, the crankshaft, DDR3L and turbine vane tasks, how tasks are written, the sandbox tools, the harness and time per attempt, the deterministic verifier and physics solvers, GPT-6.1 Sol's $10 a run, the 12 and 4 point gaps and six times the cost, "Spending more buys little", pass@k and the domains coming next.

[2] Ryan Merket, "Xplore AI launches engineering benchmark, with GPT-6 Astra at 37%", Runtime Wire, 27 October 2026. Source for the release date, 11 models and GPT-6 Astra's 37%.

[3] Xplore, "Thesis".