reasoning-gym Evaluation

We store evaluation results of reasoning-gym datasets (including llm outputs) in this repository.

Progress and LLM accuracy metrics are tracked on our main Google Spreadsheet.

Team

• Joe Sharratt (joesharratt1229)
• Abdulhakeem Adefioye (Adefioye)
• Zafir Stojanovski (zafstojano)
• Rich Jones (Miserlou)
• Andreas Koepf (andreaskoepf)

Contact / Contributing / Sponsoring

• You can reach the eval-team in the #reasoning-gym channel of the GPU-Mode discord server.
• We would be very happy about donations in the form of OpenRouter API keys (or other inference API providers)!