AIEvals

Benchmarks

SWE-Bench Pro (version unspecified)

Resolving long-horizon repository issues requiring large, multi-file code changes.

Repository codingReported by AnthropicVendor-reported onlyReported by Anthropic

How it is run

Section 8.2 reports an average over five trials. The card names SWE-Bench Pro without identifying its version or public subset.

What it cannot tell you

The 64.8% report cannot be assigned to v1, V2 Full or V2 HARD without a stated version. Independent subset results remain on their own pages.

Why there is no independent table

No independent suite in this dataset runs SWE-Bench Pro (version unspecified). 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

Other versions of the same evaluation. Versions are not comparable: the task set changes between them.

  • SWE-Bench Pro v1Same family. Resolving software-engineering issues in existing repositories.
  • SWE-bench MultimodalSame category. Resolving software-engineering issues that include visual context such as screenshots and design mockups.
  • SWE-Bench Pro V2 FullSame category. Repository issue resolution on the full public V2 set. Models must edit an existing codebase to satisfy the issue’s verification tests.
  • SWE-Bench Pro V2 HARDSame category. Repository issue resolution on the HARD subset of the public V2 set. Models must edit an existing codebase to satisfy the issue’s verification tests.
  • SWE-bench MultilingualSame category. Resolving issues in existing software repositories across several programming languages.

As reported by each publisher

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

Anthropic

Claude Haiku 5.5: system card capability evaluations · 7 October 2026

RankModelScore
2Claude Haiku 5.564.8%
1Claude Sonnet 5.581.3%

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

SWE-Bench Pro (version unspecified). Table 8.1.A and §8.2; five trials. The card does not identify a Pro version or subset.

Section 8, pages 111–139 of the Haiku 5.5 system card, read 8 October 2026. Values come from exact prose, tables and labelled figures. Unless specified, Haiku uses adaptive thinking at max effort and five trials with evaluation-specific context up to 1M. Each row retains its subset, metric, effort and source notes; no score is assigned to an unspecified SWE-Bench Pro version. Terminal runs use safeguards without fallback and no internet egress. ProgramBench uses filtered tasks and hidden-test pass rate without a time limit. OSWorld partial and strict results use the official 82-task offline subset. CAD uses 0–1 voxel IoU. Healthcare raw and length-adjusted scores stay separate. Life-science results disable Haiku biology safeguards. Independently run figures quoted by Anthropic remain publisher reports here. Missing comparison values are not inferred from rounded charts.

www.anthropic.com/claude-haiku-5-5-system-card

Sources

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