Unverified50% confidenceFactExact time
SWE-2 is a series of models trained by the Devin team for software engineering tasks, optimized for aspects such as code repository understanding, multi-file modifications, running tests and debugging.
1
Sources
50%
Confidence
Long-term
Relevance
11/12/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedSWE-type benchmarks are used to evaluate a model's ability to solve real software engineering problems, with problems usually drawn from real issues and PRs in open-source repositories, testing cross-file understanding and multi-step reasoning ability.70% similarUnverifiedTesters evaluated model programming capabilities using the SWE-Lancer benchmark in both task selection and per-task modes.70% similarUnverifiedThe SWE-bench benchmark has become the industry standard for evaluating the coding capabilities of AI agents, containing software engineering tasks extracted from real GitHub repositories.69% similarUnverifiedLong-horizon coding benchmarks (such as SWE-bench) evaluate a model's ability to handle repository-level tasks, including reading codebases, locating bugs, making cross-file modifications, and passing tests.69% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1164634API
curl https://kongchang.com/api/v1/knowledge/claims/1164634MCP
get_claim(id=1164634)