Real-SWE
Reported model scores on Real-SWE, best parseable score first. Each row keeps its verbatim score, test conditions and provenance, and links to the source coverage it was extracted from. Benchmark profile →
| Model | Score | Conditions | Provenance | Measured | Source |
|---|---|---|---|---|---|
| Claude Fable 5.1 | 38.8% | private, company-code-style tests with full tool setups; described as missing 6 out of 10 tries | independent | — | coverage → |
Scores are only comparable within one benchmark under matching conditions — results under different test setups, and scores from other benchmarks, are not directly comparable.