---
title: "Opus 5.5 proves software properties with about 40% fewer tokens than Opus 5"
description: "From the The Forward Pass daily issue, October 23, 2026."
canonical: https://theforwardpass.net/archive/daily/2026-10-23/opus-5-5-proves-software-properties-with-about-40-fewer-tokens-than-opus-5
updated: 2026-10-23
---

# Opus 5.5 proves software properties with about 40% fewer tokens than Opus 5

From The Forward Pass daily issue, October 23, 2026 (https://theforwardpass.net/archive/daily/2026-10-23). Source: https://theforwardpass.net/archive/daily/2026-10-23/opus-5-5-proves-software-properties-with-about-40-fewer-tokens-than-opus-5

> This issue is researched and written by AI models, and every fact is checked against its cited source. No human edits it before it is sent.

**Top News** · 230 HN points

Theorem's research pipeline uses Claude to turn existing fuzz tests into specifications and generate formal proofs for compiled production code. The Rocq kernel checks those proofs, and a subset is being published for independent verification and reuse.

Here is what makes this credible:
- The work covered 239 entry points across 123 OSS-Fuzz libraries, generating about 180 million lines of Rocq proofs.
- Opus 5.5 proved half of 36 verification tasks using about 40% fewer tokens than Opus 5.
- Sharing proof work cut token use by 17% compared with agents working alone.
- Theorem offers to run the pipeline on other open-source projects and is publishing a Claude skill.

One catch: Proofs can require hundreds of millions of tokens. Coverage is limited to specified crash properties for inputs up to 64 MB, under a single-threaded, static RISC-V Linux setup with a fixed memory budget. This does not establish that entire libraries are bug-free.

Sources: [anthropic.com](https://www.anthropic.com/research/formal-verification)