Agentic benchmark
τ³-bench results leaderboard
τ³-Bench Tool-Agent-User Evaluation. Every model the catalog carries a published τ³-bench results value for, ranked by that value.
τ³-bench is the current evolution of Sierra's tool-agent-user framework, adding corrected task releases and newer knowledge and voice evaluation modes alongside airline, retail, and telecom.
τ³-bench results ranking
18 models with a published τ³-bench results value, ordered by that value, highest first. Models the source has not scored on this benchmark are not listed — they are unmeasured, not last.
| Rank | Model | Provider | Published domain or average success results |
|---|---|---|---|
| 1 |  Mercury 2.5 | Inception | 96.0 |
| 2 |  Mistral Medium 3.5 128B | Mistral | 91.4 |
| 3 |  MiMo-V2.5-Pro | Xiaomi | 72.9 |
| 4 |  Nemotron 3 Ultra | NVIDIA | 70.9 |
| 5 |  Qwen3.6 Plus | Alibaba | 70.7 |
| 6 |  GLM-5.1 | Z.AI | 70.6 |
| 7 |  Claude Opus 4.5 | Anthropic | 70.2 |
| 8 | Qwen3.5 397B | Alibaba | 68.4 |
| 9 | Qwen3.6-35B-A3B | Alibaba | 67.2 |
| 10 | PAPokee-Isaac 28B | Pokee AI | 66.2 |
| 11 |  Kimi K2.5 | Moonshot AI | 65.7 |
| 12 | GLM-5 | Z.AI | 65.6 |
| 13 |  Granite 4.2 30B | IBM | 62.0 |
| 14 | Granite 4.2 8B | IBM | 58.1 |
| 15 | Granite 4.2 3B | IBM | 45.8 |
| 16 |  Atria Dawn Preview | Shanghai Artificial Intelligence Laboratory | 41.2 |
| 17 | Nemotron 3.5 Lightning 30B A3B NVFP4 | NVIDIA | 9.5 |
| 18 |  LFM2.5-2.6B | LiquidAI | 5.7 |
Evidence key: Observed
Rows are ordered by the value Official τ³-bench repository and release notes published, highest first. The source does not state whether a higher value is the better result, so this page does not either: for a benchmark that measures a rate of failure, read the table from the bottom.