Benchmark
S3Gym Benchmark
What is S3Gym?
Interactive benchmark for evaluating LLM self-improvement via self-testing, self-judging, and self-improvement in text-based games.
- Released
- 2026-08-31
- Evaluates
- General AI, Language & Knowledge, Self-Evolution
- Openness
- unknown
- Importer
- Claire Radar
- Review status
- ai-name-audit-deferred
- Reported scores
- 0
Source provenance
- Original evidence https://arxiv.org/abs/2608.31100
S3Gym paper
No reported scores are on record for this benchmark yet.