aiaimodel.cards
← All benchmarks

τ-Bench Retail

Customer-service style tasks where the model uses tools and follows policies over a conversation with a simulated user.

  1. 1gpt-oss-120b · OpenAI
    67.8%
  2. 2gpt-oss-20b · OpenAI
    54.8%

How each maker reported it

  • gpt-oss-120b Figures 1, 2, 4; Table 2

    OpenAI's own pass@1 results at reasoning level high. AIME and HLE with tools; Codeforces with a terminal tool. o4-mini and o3 values read from OpenAI's charts.

  • gpt-oss-20b Figures 1, 2, 4; Table 2

    OpenAI's own pass@1 results at reasoning level high. AIME and HLE with tools; Codeforces with a terminal tool. o3-mini was run without tools on AIME, HLE and Codeforces, so those cells are left empty. Baseline values read from OpenAI's charts.

Only each model's own maker's number is shown; scores a maker reports for rival models are left out.