reasoning benchmark
Tau3 Banking Leaderboard
Tau3 Banking evaluates agentic models on multi-turn, tool-using customer-support scenarios in a simulated retail banking environment.
Updated Oct 23, 2026
Models16
Model coverage16
MetricScore
EvidenceB
Tau3 Banking Ranking
Higher score ranks better on this benchmark.
Sort by
Rank | Model | Score | Percentile | Participants | Evidence | Evaluated |
|---|
| Rank01 | ModelSA | Score41.20% | Percentile100.00% | Participants16 | EvidenceC | Evaluated |
| Rank02 | ModelIN | Score41.00% | Percentile93.33% | Participants16 | EvidenceC | Evaluated |
| Rank03 | ModelRA | Score36.10% | Percentile86.67% | Participants16 | EvidenceC | Evaluated |
| Rank04 | ModelXA | Score33.00% | Percentile80.00% | Participants16 | EvidenceB | Evaluated |
| Rank05 | ModelIN | Score30.24% | Percentile73.33% | Participants16 | EvidenceC | Evaluated |
| Rank06 | ModelIN | Score28.00% | Percentile66.67% | Participants16 | EvidenceC | Evaluated |
| Rank07 | ModelTM | Score23.70% | Percentile60.00% | Participants16 | EvidenceC | Evaluated |
| Rank08 | ModelME | Score23.50% | Percentile53.33% | Participants16 | EvidenceC | Evaluated |
| Rank09 | ModelUP | Score23.00% | Percentile46.67% | Participants16 | EvidenceC | Evaluated |
| Rank10 | ModelNV | Score18.88% | Percentile40.00% | Participants16 | EvidenceC | Evaluated |
| Rank11 | ModelNV | Score17.01% | Percentile33.33% | Participants16 | EvidenceC | Evaluated |
| Rank12 | ModelTM | Score15.50% | Percentile26.67% | Participants16 | EvidenceC | Evaluated |
| Rank13 | ModelMA | Score13.40% | Percentile20.00% | Participants16 | EvidenceC | Evaluated |
| Rank14 | ModelNV | Score12.89% | Percentile13.33% | Participants16 | EvidenceC | Evaluated |
| Rank15 | ModelNV | Score9.28% | Percentile6.67% | Participants16 | EvidenceC | Evaluated |
| Rank16 | ModelLA | Score5.67% | Percentile0.00% | Participants16 | EvidenceC | Evaluated |
Tau3 Banking Highlights
The leading models and scores on this benchmark.
Tau3 Banking Score Distribution
A closer view of the leading scores on this benchmark.
The Top AI Models for Tau3 Banking
The first five results on this benchmark, with official price and output speed added where the model identity can be matched.
What is Tau3 Banking?
What Tau3 Banking measures and how its scores work.
Tau3 Banking is a reasoning benchmark for evaluating agentic models in a simulated retail banking environment.
It measures performance on multi-turn, tool-using customer-support scenarios using Score, reported as a ratio.
Scores are shown in ratio. This benchmark is not independently verified and has an evidence level of B.
- Family
- Tau3 Banking
- Modality
- text
- Primary category
- reasoning
- Score direction
- higher
- LLMBoard eligible
- No
- Evaluation key
- overall
LLM Stats. Benchmark scores retain their original unit. Overall score eligibility is shown separately.
FAQ
Common questions about Tau3 Banking.
Which model scores highest on Tau3 Banking?
Atria Dawn Preview is currently ranked first with 41.20%.
What are the top three models on Tau3 Banking?
The current leaders are Atria Dawn Preview (41.20%), Ling 3.0 Flash Fin (41.00%), and Beam 1.0 (36.10%).
Which Tau3 Banking model has the lowest official input price?
Mercury 3 has the lowest matched official input price at $0.10 input / $0.35 output per 1M tokens.
Which models are fastest among Tau3 Banking results?
The fastest matched records are Mercury 3 (1,068.00 tok/s via Inception) and Grok 4.5 (80.00 tok/s via xAI).
Does the highest score result prove overall model quality?
No. This benchmark measures one defined capability or task. The overall LLMBoard score uses a separate aggregation across eligible benchmark evidence.