# AI's best coding agent fails 60% of the time -- and the data backs it up

DevFeed: [AI's best coding agent fails 60% of the time -- and the data backs it up](<https://devfeed.tech/articles/ai-s-best-coding-agent-fails-60-of-the-time-and-the-data-backs-it-up-21601.md>)

Original publisher: [Read original article](<https://thenewstack.io/real-swe-coding-benchmark/>)

Author: Amanda Caswell

Published: 2026-09-14T22:22:27Z

Content type: news

Language: en

Sources: [The New Stack](<https://devfeed.tech/sources/the-new-stack.md>)

Topics: [Benchmark](<https://devfeed.tech/topics/benchmark.md>), [AI-assisted coding](<https://devfeed.tech/topics/ai-assisted-coding.md>), [Fable](<https://devfeed.tech/topics/fable.md>), [Claude Code](<https://devfeed.tech/topics/claude-code.md>), [codex](<https://devfeed.tech/topics/codex.md>), [Command-line interface](<https://devfeed.tech/topics/cli.md>), [anthropic](<https://devfeed.tech/topics/anthropic.md>)

Tags: [ai](<https://devfeed.tech/tags/ai.md>), [ai-engineering](<https://devfeed.tech/tags/ai-engineering.md>), [ai-models](<https://devfeed.tech/tags/ai-models.md>), [benchmark](<https://devfeed.tech/tags/benchmark.md>), [benchmarks](<https://devfeed.tech/tags/benchmarks.md>), [claude-code](<https://devfeed.tech/tags/claude-code.md>), [cli](<https://devfeed.tech/tags/cli.md>), [codex](<https://devfeed.tech/tags/codex.md>), [coding](<https://devfeed.tech/tags/coding.md>), [fable](<https://devfeed.tech/tags/fable.md>), [performance](<https://devfeed.tech/tags/performance.md>), [software-testing](<https://devfeed.tech/tags/software-testing.md>)

## AI overview

Real-SWE evaluates coding agents on private company codebases and reports substantially lower success rates than public-repository benchmarks. Claude Fable 5.1, running through Claude Code, led the comparison with a 38.8% score, while the tested systems often failed most attempts.

## Source excerpt

Claude Fable 5.1 just won a new coding benchmark despite failing more than six out of 10 times. Its 38.8% The post AI's best coding agent fails 60% of the time -- and the data backs it up appeared first on The New Stack.