SWE-Bench Pro Verified: A Reliable Benchmark for Software Engineering Agents

• URL: http://arxiv.org/abs/2609.08149v1
• Date: Tue, 08 Sep 2026 02:29:58 GMT
• Title: SWE-Bench Pro Verified: A Reliable Benchmark for Software Engineering Agents
• Abstract summary: SWE-Bench Pro has emerged as a standard benchmark for evaluating software engineering agents.<n>We present textbfSWE-Bench Pro Verified, a verified version of SWE-Bench Pro.
• Score: 8.395965809081927
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: SWE-Bench Pro has emerged as a standard benchmark for evaluating software engineering agents on challenging repository-level tasks. However, our analysis work show that its evaluation is undermined by two sources of unreliability: \textbf{reward hacking}, enabled by leakage of gold solutions or hidden evaluation information, and \textbf{task quality issues}, including misleading problem statements and improperly scoped tests. These issues can inflate benchmark performance and obscure agents' true coding ability. We present \textbf{SWE-Bench Pro Verified}, a verified version of SWE-Bench Pro that addresses both problems. Our approach combines \textbf{anti-hacking} safeguards that eliminate major leakage channels without disrupting normal agent functionality, with \textbf{task refinement} that minimally corrects inconsistencies within flawed instances. Evaluations on SWE-Bench Pro Verified reveal that some models perform substantially worse than previously reported, suggesting that existing results on SWE-Bench Pro may overestimate real software engineering capability. SWE-Bench Pro Verified offers a more trustworthy benchmark for assessing software engineering agents.

Related papers

• SWE-Gate: Passing Functional Tests Is Not Enough for Software Engineering Agents [63.65682461568621]
  We introduce SWE-Gate, a repository-level benchmark for software engineering agents that explicitly evaluates review constraint compliance alongside functional correctness.<n>SWE-Gate derives review constraints from real pull request review comments and synthesizes repository-level repair instances around these constraints.<n>Each instance provides separate functional and constraint tests, together with non-compliant and gold patches, enabling explicit separation between issue resolution capability and review constraint compliance.
  arXiv  Detail & Related papers  (2026-09-03T17:53:34Z)
• SWE-Bench ProMax: Benchmarking Agents on Large-Scale Multilingual Code Refactoring [31.684059339633013]
  SWE-Bench ProMax is an expert-curated, multilingual code benchmark of 170 instances drawn from real commits.<n>Every instance undergoes rigorous, multi-stage curation that addresses quality problems identified in prior benchmarks.<n>Experiments with frontier models under two agent scaffolds show that the best model achieves only 41.2% resolve rate.
  arXiv  Detail & Related papers  (2026-08-10T16:23:19Z)
• DeepSWE: Measuring Frontier Coding Agents on Original, Long-Horizon Engineering Tasks [1.7623000586936592]
  DeepSWE is a benchmark of 113 original, long-horizon software engineering tasks for evaluating coding agents.<n>Its tasks are written from scratch across 91 active open-source repositories and five languages and are never contributed back upstream.<n>Despite being about half the length of SWE-Bench Pro's prompts, DeepSWE's prompts describe tasks whose reference solutions touch 5.5x more code.
  arXiv  Detail & Related papers  (2026-07-08T21:45:34Z)
• ProcCtrlBench: Evaluating Process-Level Defects and Control Preservation in LLM Coding Agents [4.908588441456849]
  ProcCtrlBench is a benchmark for execution-process evaluation in LLM coding agents.<n>It organizes recurrent execution defects into a reusable ontology covering 11 defect types in 4 categories.<n>It evaluates agent trajectories through standardized process evidence rather than final outcomes alone.
  arXiv  Detail & Related papers  (2026-05-18T08:34:48Z)
• LiveFMBench: Unveiling the Power and Limits of Agentic Workflows in Specification Generation [75.05397479715576]
  Large language models (LLMs) and agents have shown promising progress, but their true capabilities and failure modes remain unclear.<n>We present the first systematic and contamination-aware study of LLM- and agent-based formal specification generation for C programs.
  arXiv  Detail & Related papers  (2026-05-02T11:31:33Z)
• ELT-Bench-Verified: Benchmark Quality Issues Underestimate AI Agent Capabilities [4.5258165293324515]
  Extract-Load-Transform pipelines are a labor-intensive data engineering task and a high-impact target for AI automation.<n>On ELT-Bench, the first benchmark for end-to-end ELT pipeline construction, AI agents initially showed low success rates.<n>We revisit these results and identify two factors causing a substantial underestimation of agent capabilities.
  arXiv  Detail & Related papers  (2026-03-31T08:02:16Z)
• SastBench: A Benchmark for Testing Agentic SAST Triage [3.1175243456844832]
  SastBench is a benchmark for evaluating SAST triage agents that combines real CVEs as true positives with filtered SAST tool findings as approximate false positives.<n>We evaluate different agents on the benchmark and present a comparative analysis of their performance.
  arXiv  Detail & Related papers  (2026-01-06T11:36:30Z)
• ImpossibleBench: Measuring LLMs' Propensity of Exploiting Test Cases [58.411135609139855]
  "Shortcuts" to complete tasks pose significant risks for reliable assessment and deployment of large language models.<n>We introduce ImpossibleBench, a benchmark framework that measures LLM agents' propensity to exploit test cases.<n>As a practical framework, ImpossibleBench is not just an evaluation but a versatile tool.
  arXiv  Detail & Related papers  (2025-10-23T06:58:32Z)
• Establishing Best Practices for Building Rigorous Agentic Benchmarks [94.69724201080155]
  We show that many agentic benchmarks have issues in task setup or reward design.<n>Such issues can lead to under- or overestimation of agents' performance by up to 100% in relative terms.<n>We introduce the Agentic Benchmark Checklist (ABC), a set of guidelines that we synthesized from our benchmark-building experience.
  arXiv  Detail & Related papers  (2025-07-03T17:35:31Z)
• Thinking Longer, Not Larger: Enhancing Software Engineering Agents via Scaling Test-Time Compute [61.00662702026523]
  We propose a unified Test-Time Compute scaling framework that leverages increased inference-time instead of larger models.<n>Our framework incorporates two complementary strategies: internal TTC and external TTC.<n>We demonstrate our textbf32B model achieves a 46% issue resolution rate, surpassing significantly larger models such as DeepSeek R1 671B and OpenAI o1.
  arXiv  Detail & Related papers  (2025-03-31T07:31:32Z)
• The Impact of SBOM Generators on Vulnerability Assessment in Python: A Comparison and a Novel Approach [56.4040698609393]
  Software Bill of Materials (SBOM) has been promoted as a tool to increase transparency and verifiability in software composition. Current SBOM generation tools often suffer from inaccuracies in identifying components and dependencies. We propose PIP-sbom, a novel pip-inspired solution that addresses their shortcomings.
  arXiv  Detail & Related papers  (2024-09-10T10:12:37Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.