reasoning benchmark
TAU3-Bench Leaderboard
TAU3-Bench evaluates general-purpose agent capabilities through multi-turn interactions with simulated user models, retrieval, and complex decision-making scenarios.
Updated Sep 5, 2026
Models8
Model coverage8
MetricScore
EvidenceB
TAU3-Bench Ranking
Higher score ranks better on this benchmark.
Sort by
Rank | Model | Score | Percentile | Participants | Evidence | Evaluated |
|---|
| Rank01 | ModelXI | Score72.90% | Percentile100.00% | Participants8 | EvidenceC | Evaluated |
| Rank02 | ModelAC | Score70.70% | Percentile85.71% | Participants8 | EvidenceC | Evaluated |
| Rank03 | ModelZA | Score70.60% | Percentile71.43% | Participants8 | EvidenceC | Evaluated |
| Rank04 | ModelAC | Score67.20% | Percentile57.14% | Participants8 | EvidenceC | Evaluated |
| Rank05 | ModelIB | Score62.00% | Percentile42.86% | Participants8 | EvidenceC | Evaluated |
| Rank06 | ModelIB | Score58.06% | Percentile28.57% | Participants8 | EvidenceC | Evaluated |
| Rank07 | ModelIB | Score45.78% | Percentile14.29% | Participants8 | EvidenceC | Evaluated |
| Rank08 | ModelNV | Score22.60% | Percentile0.00% | Participants8 | EvidenceC | Evaluated |
TAU3-Bench Highlights
The leading models and scores on this benchmark.
TAU3-Bench Score Distribution
A closer view of the leading scores on this benchmark.
The Top AI Models for TAU3-Bench
The first five results on this benchmark, with official price and output speed added where the model identity can be matched.
What is TAU3-Bench?
What TAU3-Bench measures and how its scores work.
TAU3-Bench is a benchmark for evaluating general-purpose agent capabilities.
It measures performance in multi-turn interactions with simulated user models, retrieval, and complex decision-making scenarios, using the Score metric expressed as a ratio.
Scores are shown in ratio. This benchmark is not independently verified and has an evidence level of B.
- Family
- TAU3-Bench
- 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-Bench.
Which model scores highest on TAU3-Bench?
MiMo-V2.5-Pro is currently ranked first with 72.90%.
What are the top three models on TAU3-Bench?
The current leaders are MiMo-V2.5-Pro (72.90%), Qwen3.6 Plus (70.70%), and GLM-5.1 (70.60%).
Which TAU3-Bench model has the lowest official input price?
Qwen3.6-35B-A3B has the lowest matched official input price at $0.25 input / $1.5 output per 1M tokens.
Which models are fastest among TAU3-Bench results?
The fastest matched records are MiMo-V2.5-Pro (5.27 tok/s via DeepInfra).
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.