AI benchmarks and leaderboards are different things
Learn the difference between a benchmark, an evaluation run and a leaderboard, and use each to answer the right question.
LLM Stats
Tau3 Banking
τ³-Bench banking domain evaluates agentic models on multi-turn, tool-using customer-support scenarios in a simulated retail banking environment.
Evaluation context and evidence
- Source
- LLM Stats
- Publisher
- Not recorded
- Benchmark release
- Not recorded
- Collected
- 2026-08-17
- Modality
- text
These are source-reported observations, not independent reruns by this site. Check the task version, evaluation protocol, unit and reporting date before comparing models. Results from different setups are not a universal ranking.
Original sources
Reported results 7
Shown in source observation order, not ranked. Dates retain the precision provided by the source.
| Model | Value | Unit | Protocol | Reported date and basis | Source |
|---|---|---|---|---|---|
| Grok 4.5 | 0.33 | Not recorded | Not recorded | 2026-07-16 · model_announcement | LLM Stats |
| Muse Glimmer-30B | 0.235 | Not recorded | Not recorded | 2026-08-10 · model_announcement | LLM Stats |
| Solar Pro 4 | 0.23 | Not recorded | Not recorded | 2026-08-06 · model_announcement | LLM Stats |
| Inkling-Small | 0.155 | Not recorded | Not recorded | 2026-07-30 · model_announcement | LLM Stats |
| Mistral Medium 3.5 | 0.134 | Not recorded | Not recorded | 2026-04-29 · model_announcement | LLM Stats |
| Nemotron 3.5 Lightning (30B A3B) | 0.0928 | Not recorded | Not recorded | 2026-08-11 · model_announcement | LLM Stats |
| LFM2.5-2.6B | 0.0567 | Not recorded | Not recorded | 2026-08-04 · model_announcement | LLM Stats |