500AI
← People

Evan Mays

Website ↗GitHub ↗LinkedIn ↗Institution ↗
  • Information retrieval
  • Evaluation

Selected work

5
  1. MLE-bench: Evaluating Machine Learning Agents on Machine Learning EngineeringContributor · 2024↗
  2. SWE-bench VerifiedContributor · 2024↗
  3. PaperBench: Evaluating AI's Ability to Replicate AI ResearchContributor · 2025↗
  4. GPT-4o System CardAuthor · 2024↗
  5. OpenAI o1 System CardAuthor · 2024↗

Source-linked involvement

1
  1. OpenAI GPT-5 System CardAuthor · 2025↗
Suggest an edit
About & privacy