AI benchmarks and leaderboards are different things
Learn the difference between a benchmark, an evaluation run and a leaderboard, and use each to answer the right question.
OpenCompass Hub
Flames
Flames is a highly adversarial benchmark in Chinese for LLM's value alignment evaluation developed by Shanghai AI Lab and Fudan NLP Group. Flames meticulously designs a dataset of 2,251 highly adversarial, manually crafted prompts, each tailored to probe a specific value dimension (i.e., Fairness, Safety, Morality, Legality, Data protection). Currently, Flames releases 1,000 prompts for public use (Flames_1k_Chinese).
Evaluation context and evidence
- Source
- OpenCompass Hub
- Publisher
- Not recorded
- Benchmark release
- 2024-03-13
- Collected
- 2026-08-18
- Modality
- Not recorded
These are source-reported observations, not independent reruns by this site. Check the task version, evaluation protocol, unit and reporting date before comparing models. Results from different setups are not a universal ranking.
Original sources
Reported results 0
This source record has no numeric results in our collection. That does not mean a score of zero or that no public results exist. Consult the original resources above.