Ascending Labs Research
Benchmark checker Coding

Is FrontierCode still meaningful?

Status:New / unproven Checked against the report, 5 November 2026

Verdict

Unproven. Labs headline it, but nobody has confirmed who runs it or how.

Why new / unproven: The chapter lists it as active, but its maintainer and method are not confirmed.[1][1] Benchmark data bundle Epoch AI Primary

What “New / unproven” means

Known problems

  • Its maintainer and method are not confirmed.[1][1] Benchmark data bundle Epoch AI Primary
  • OpenAI and Anthropic both put it in their autumn 2026 launch tables.[2][2] Introducing Claude Opus 5.5 Anthropic Vendor[3][3] GPT-6 Astra benchmarks explained Vellum Secondary

What to look at instead

The report names no direct successor.

Where it appears in the report

Chapter 1, Benchmarks

Sources

Copied from the chapter source lists. Each number links back to the source in its chapter.

  1. [1]
    Benchmark data bundle, Epoch AI. Dated scores (5 Nov 2026) and ceilings for most benchmarks here. Primary epoch.ai Chapter 1, source 1
  2. [2]
    Introducing Claude Opus 5.5, Anthropic. It gives Anthropic's launch table and caveats. Vendor anthropic.com Chapter 1, source 12
  3. [3]
    GPT-6 Astra benchmarks explained, Vellum. It transcribes OpenAI's launch table and discusses its framing. Secondary vellum.ai Chapter 1, source 14
  • CursorBench Status:Still useful Yes, as one signal. Remember that a product company owns it.
  • GSO Status:Near ceiling Fading. The top score is 88.2%, and the scaffold drives results.
  • DeepSWE Status:Flawed Partly. Its fresh tasks resist contamination, but Epoch AI found issues in at least 23 of 113.
  • SWE-bench Pro Status:Flawed No. About a third of its tasks are broken, and agents have cheated on it.