τ-bench
Benchmarks & Leaderboards · Free + paid
Benchmarking AI agents in collaborative real-world scenarios
At a glance
- Made by
- Sierra
- Korean
- None (English and a few others only)
- Available on
- Web
What is τ-bench?
τ-bench evaluates, in enterprise domains and in both text and voice, an agent's ability to converse with users, call tools, retrieve knowledge, and follow policies. The original version had agents converse with simulated users in the retail and airline domains and was graded on verifiable database outcomes, and τ²-bench added the telecom domain and dual control, where the user also takes actions. τ³-bench added a banking domain that uses a knowledge base of about 700 documents, along with real-time voice evaluation. The new τ^τ-bench evaluates whether a coding agent can build a customer service agent.
- τ³-Banking (knowledge retrieval) leaderboard
- τ³-Voice (real-time voice) evaluation
- τ²-bench retail, airline, and telecom
- pass^k reliability metric
- Visualizer
- Submit results
Who uses τ-bench and for what
- Customer service agent developers compare model reliability
Pricing
Free (public benchmark/leaderboard)
Mostly free leaderboards/datasets released for academic and community purposes
Estimate based on AI knowledge - please verify on the official site
AI tools similar to τ-bench (alternatives)
τ-bench vs. alternatives at a glance
| AI | Pricing | Combos on the map | Connected tools | Free | Cheapest monthly | Korean |
|---|---|---|---|---|---|---|
| τ-bench | Free + paid | 0 | 5 | — | — | No |
| APEX-Agents | Free + paid | 0 | 11 | — | — | No |
| ARC-AGI-2 | Free + paid | 0 | 11 | — | — | No |
| Context-Bench | Free + paid | 0 | 11 | — | — | No |
| MCP Atlas | Free + paid | 0 | 11 | — | — | No |
0 of these 5 tools have a free plan.
Combo and connection counts are based on the relationships recorded on AI Galaxy Map (2026-10-26); they are not a quality ranking.
τ-bench on AI Galaxy Map
- One of 27 AI tools in the Benchmarks & Leaderboards field.
- Connected to 5 other tools — #11 in its field.
Frequently asked questions
Can I use τ-bench for free?
Free (public benchmark/leaderboard). Prices can change, so check the official site before paying.
What AI can I use instead of τ-bench?
Tools that do the same job, such as APEX-Agents, ARC-AGI-2, Context-Bench, MCP Atlas, are connected to it on the map.
Can I use τ-bench in Korean?
None (English and a few others only)
Sources (official pages)
Checked on the official pages on 2026-10-14. Prices and features can change, so check the official site again before paying.