Real-SWE: Benchmarking AI models on private, real-world, enterprise codebases

Does this mean they ended up sharing those private codebases with OAI, Anthropic etc? Also, the ~30% number tracks with my experience. I thought I was going insane for expecting too much from the models but they are still bad, including astra. This morning it messed something pretty trivial while fixing an issue which I was shocked to see. Also2, benchmarks don't mean much these days.

We built a “code atlas” that provides the LLM with a semantically queryable map of how things connect and relate in a very large and sprawling codebase that evolved over 15 years. It tends to dramatically reduce the length of time models have to spend reading code while also making sure they are aware (within their context window) of nuances that are important that might be missed were they forced to just rely on reading the code in hundreds of repositories.

I strongly recommend trying this approach out yourself. The recipe is not rocket science. Get your coding agent to take a first cut at building the atlas itself, and then manually correct it. Once you’re happy that it got things right, put an MCP on it or a CLI or whatever. And your LLMs will know what to do from there.

My intuition is that many of the better & bigger 'private' code bases, at least in terms of claude code and codex... are not in fact private at this point.

One lesson of running botsbench.com, in a slightly different domain, is to measure for model contamination every time.

I am trying to estimate if my reaction to seeing GPT-5.6 Sol last on that list is reasonable or or mostly emotional and find that I have no way of telling.

I used a similar methodology. Code review is my most requested action, so I used blind code review results to compare the frontier AIs.

Even posted an article about it:

https://www.matheusmoreira.com/articles/code-reviewing-lone-...

Unlike TFA, the lone lisp code is public. I suppose the models could have been trained on my codebase. Still, I think it produced some interesting results.

Took months and loads and loads of tokens to do this, so I'm not gonna repeat this study as new models come out. It did anchor all of my future expectations, though. OpenAI is winning as far as I'm concerned, and their cybersecurity program is the only remaining pain point.

This is the first set of benchmarks which match my observations around gemini-3.8-flash perfectly. This model is a true hidden gem.

this is the closest benchmark to my experience using the model harness combo. Astra for as great as it is falls slightly behind Fable 5.1 for me for large feature work (although it comments code much better). in particular, Fable is able to assess priority better than Astra (meaning Astra sometimes does things that aren’t worthwhile while missing things that are clearly important, particularly on possible ballooning scenarios- fable catches “this works for x amount of data but if we run this on y way greater than x amount of data we’ll run into issues). Gemini 3.8 is under appreciated, use Google Stitch to see it in action if you haven’t used Agy yet.

The high score of Gemini 3.8 Flash vibes with my experience anecdotally. While it often goes off the rails with open-ended questions (which is a strength if taken with care), it is also a good at solving issues in a well-defined environment like an enterprise codebase.

I'd love to see these:

- DeepSeek V4.1 Flash

- Kimi K3

- GLM 5.3 (and flash)

- hy4-preview

- Grok 4.6

All of these can be acessed using a $10/mo OpenCode Go subscription.

Gemini 3.8 flash has been incredible for our agents. For us, It performs better than any other model except Fable.

These'll be part of the training set eventually.

Averaging pass@1 across eight runs per task is useful; it exposes harness consistency instead of letting one lucky resolution dominate.

what if the production code base was made by mostly by Anthropic models?

> Each task comes from a private production codebase that we licensed from a real-world company

How does that work?

A bit of a meta question: what are the most relevant benchmarks by now?

AGI 38.8%

I’ve been able to offload most tasks (coding or eles) to Codex since 5.3-codex with extra high thinking

This benchmark is shitty because it puts Gemini in 3rd position.

I tried gemini on simple code base and it invoked 210 tool calls just to update 3 lines of code.

So TL;DR benchmarking in a completely non-reproducible manner ?

"Model X performed great, but we can't possibly tell you anything about the code it was looking at apart from it was a large code base from an unknown company".

So basically pinky-promise benchmarking ?

I'm not sure I follow the value here ?

real software engineering benchmark is how much stress you can take at work. Everyone knows this, bakka.

Wake me up when September ends or when I can do this locally.

I think these benchmarks are not that useful, e.g. this suggests Fable is better than Astra, but in practice Astra is waaaaaay faster (like 5x; it's not even close), and also waaaay less annoying to talk to.

There's only two or three sane options here - you can easily try them all and pick yourself.

[flagged]

[flagged]

[flagged]

[dead]

[dead]

The fact that gemini 3.8 flash is so high up there just tells you this is an awful benchmark.

Try and use gemini 3.8 yourself for any real world work and you'll see it's terrible. It'll just go in circles reading the same file 20 times for no reason making hundreds of tool calls for a simple change.

EDIT: I was using gemini cli... it's not a harness issue lol