Benchmark
APEX-SWE Benchmark
What is APEX-SWE?
APEX-SWE evaluates AI agents on software engineering tasks requiring multi-step coding, debugging, and verification.
- Modality
- text
- Evaluates
- agents, code
- Openness
- unknown
- Importer
- LLM Stats
- Reported scores
- 1
Source provenance
- Original evidence https://api.zeroeval.com/leaderboard/benchmarks/apex-swe?top_n=500
APEX-SWE results and reported scores
LLM Stats
| Model | Organization | Reported value | Reported | Evidence |
|---|---|---|---|---|
| Grok 4.6 | xAI | 0.564 | 2026-08-12 | evidence |
Scores are partitioned by the source that reported them and are never merged into a single cross-source ranking, because the sources measure different things and say so.