# SRE-Bench leaderboard

external benchmark

> Every figure below is reproduced as its upstream source published it: nothing is modelled, estimated, interpolated or converted. `Unavailable` means no source published the value — it is never a zero. Each value carries its evidence state and the date it was observed.

Page: https://modelscale.dev/leaderboards/benchmarks/external-sre-bench

SRE-Bench binary reverse engineering. Every model the catalog carries a published SRE-Bench value for, ranked by that value.

## Benchmark record

| Field | Value |
| --- | --- |
| Category | external |
| Measure | Fully solved challenge rate (pass@1) |
| Tasks | 262 binary reverse-engineering instances |
| Difficulty | Binary reverse engineering |
| Published by | [GPT-6 Astra System Card](https://deploymentsafety.openai.com/gpt-6-astra/gpt-6-astra.pdf) |

A contamination-controlled benchmark that asks agents to reverse engineer compiled binaries without source access and satisfy six task-specific objectives per challenge.

## SRE-Bench ranking

2 models with a published SRE-Bench value, ordered by that value, highest first. Models the source has not scored on this benchmark are not listed — they are unmeasured, not last.

| Rank | Model | Provider | Fully solved challenge rate (pass@1) | Evidence |
| --- | --- | --- | --- | --- |
| 1 | [GPT-6 Cyber](https://modelscale.dev/models/gpt-6-cyber) | OpenAI | 92.8 | Observed 2026-11-21 · source benchlm:models |
| 2 | [GPT-6 Astra](https://modelscale.dev/models/gpt-6-astra) | OpenAI | 88.0 | Observed 2026-11-21 · source benchlm:models |

Rows are ordered by the value the source published, highest first. The source does not state whether a higher value is the better result, so this document does not either: for a benchmark that measures a rate of failure, read the table from the bottom.
