The AI arena is free today

Open Superagent
AI OrganizationMaintains 12 benchmarks

Sierra: AI benchmarks & research

Conversational AI agent company. Maintains the tau-bench family of tool-agent-user benchmarks.

Maintained by Sierra

12 benchmarks

In one line

Sierra maintains t2-bench (counts toward the LLM Stats Score, 23 models scored), Tau2 Airline (counts toward the LLM Stats Score, 26 models scored), Tau2 Retail (counts toward the LLM Stats Score, 28 models scored), Tau2 Telecom (counts toward the LLM Stats Score, 37 models scored), Tau3 Airline (counts toward the LLM Stats Score, 1 model scored), Tau3 Banking (counts toward the LLM Stats Score, 21 models scored), TAU3-Bench (counts toward the LLM Stats Score, 10 models scored), Tau3 Retail (counts toward the LLM Stats Score, 1 model scored), Tau3 Telecom (counts toward the LLM Stats Score, 1 model scored), Tau-bench (counts toward the LLM Stats Score, 6 models scored), TAU-bench Airline (counts toward the LLM Stats Score, 23 models scored) and TAU-bench Retail (counts toward the LLM Stats Score, 25 models scored). It ships no models of its own on LLM Stats.

FAQ

Common questions about Sierra.

What is Sierra?

Conversational AI agent company. Maintains the tau-bench family of tool-agent-user benchmarks. On LLM Stats it maintains 12 benchmarks, led by Tau2 Telecom, Tau2 Retail and Tau2 Airline. It ships no models of its own; each score on its benchmarks carries its own provenance label on the model page.

Which Sierra benchmarks count toward the LLM Stats Score?

Tau2 Telecom, Tau2 Retail, Tau2 Airline, TAU-bench Retail, t2-bench, TAU-bench Airline and 6 more count toward the LLM Stats Score. Only benchmarks admitted to the core set move the main leaderboard; the rest are shown for transparency.

Which models lead Sierra's benchmarks?

Claude Opus 4.6 leads Tau2 Telecom at 99.3% (37 models scored), Claude Opus 4.6 leads Tau2 Retail at 91.9% (28 models scored) and Muse Glimmer-30B leads Tau2 Airline at 78.0% (26 models scored). Each benchmark page lists the full ranking and how the results were produced.

Where are Sierra's official benchmark results?

Sierra's official site is https://sierra.ai. Each benchmark page on LLM Stats links to that benchmark's own paper or leaderboard, and shows the scores next to every other benchmark so models can be compared on one page.