AIEvals

Benchmarks

CursorBench 4.0

Coding-agent work inside an IDE-driven workflow, measured on tasks the Cursor harness is built to run.

Agentic codingCursorVendor-reported onlyReported by Anthropic, Anthropic

How it is run

Reported in Anthropic's comparison tables: Opus 5.5 57.8%, Fable 5.1 51.8%, Opus 5 46.6% and GPT-5.6 Sol 41.7% with Opus 5.5, then Sonnet 5.5 55.5% and Sonnet 5 34.1% with the Sonnet 5.5 release.

What it cannot tell you

Published by the vendor whose product the harness is, and re-reported by Anthropic. No independent run of this benchmark is in the dataset, and GPT-6 Astra has no reported figure, so a column here is deliberately empty rather than zero.

Why there is no independent table

No independent suite in this dataset runs CursorBench 4.0. The numbers below are the ones model publishers report about their own models, which is a different kind of evidence: each publisher chooses its own harness and effort level, so a row is readable on its own and not against the other rows.

Read this with

Benchmarks in the same category, which usually disagree with this one on purpose.

  • FrontierCode v1.1 (Extended)Same category. Producing mergeable patches on the full 150-task FrontierCode v1.1 software-engineering evaluation.
  • Terminal-Bench 4.0Same category. Whether an agent can complete a long, realistic piece of work in a sandboxed terminal: a working service, a proof, a CAD model, a trained kernel, a forensic report.
  • Terminal-Bench 2.1Same category. The previous generation of the same idea: can an agent drive a shell to a finished result rather than produce a plausible answer.
  • ProgramBenchSame category. Whether an agent can produce a program that fully satisfies a specification, scored on complete resolution rather than partial credit.
  • Code MigrationSame category. Whether a model can reimplement a working program in another language and preserve its behaviour — the work of porting a tool to a new ecosystem or modernising legacy code, including COBOL to Java.
  • FrontierCode v1.1Same category. Whether a coding agent produces changes that are ready to merge into a real codebase, rather than a patch that merely passes a test.

As reported by each publisher

Kept separate per publisher, because the settings are not shared.

Anthropic

Claude Opus 5.5: evaluation table · 22 September 2026

RankModelScore
1Claude Opus 5.557.8%
2Claude Fable 5.151.8%
3Claude Opus 546.6%
4GPT-5.6 Sol41.7%

Ranks compare reported scores in the same published row; ties share a rank.

Anthropic runs its own harness and states that margin size is a weakening guide to real differences at this level. Two rows rely on other publishers: AutomationBench figures come from Zapier, and the GPT figures are as reported by OpenAI. The Claude Opus 5.5 row was run with production safeguards enabled, so some security, biology and frontier-development tasks were completed by a fallback model.

www.anthropic.com/news/claude-opus-5-5

Anthropic

Claude Sonnet 5.5: evaluation table · 28 September 2026

RankModelScore
2Claude Sonnet 5.555.5%
3Claude Sonnet 534.1%
1Claude Opus 5.557.8%

Ranks compare reported scores in the same published row; ties share a rank.

Anthropic publishes this table with Sonnet 5.5, the second model in its Claude 5.5 line, and states that Sonnet 5.5 at Max effort performs comparably to Opus 5.5 on several evaluations while Opus 5.5 remains stronger on open-ended work. The GPT-6 Sol column is quoted from OpenAI, not re-run, and Anthropic notes an OpenAI image-understanding bug that may not yet be reflected in third-party scores. Two rows come from other publishers: Artificial Analysis ran GDPval-AA and AA-Briefcase on a pre-release Sonnet 5.5 deployment that Anthropic later found had a structured-output bug, and Surge AI runs Chartography. Sonnet 5.5 launched with the cyber safeguards first built for Opus-class models, so some security work was completed by a fallback model.

www.anthropic.com/claude-sonnet-5-5

Sources

Every page used for this benchmark, read on 17 October 2026.