reasoning benchmark
Tau2 Telecom Leaderboard
Tau2 Telecom evaluates conversational agents in shared telecommunications troubleshooting scenarios modeled as a Dec-POMDP.
Updated Oct 23, 2026
Models37
Model coverage37
MetricScore
EvidenceB
Tau2 Telecom Ranking
Higher score ranks better on this benchmark.
Sort by
Rank | Model | Score | Percentile | Participants | Evidence | Evaluated |
|---|
| Rank01 | ModelAN | Score99.30% | Percentile100.00% | Participants37 | EvidenceC | Evaluated |
| Rank02 | ModelME | Score99.30% | Percentile97.22% | Participants37 | EvidenceC | Evaluated |
| Rank03 | ModelOP | Score98.90% | Percentile94.44% | Participants37 | EvidenceC | Evaluated |
| Rank04 | ModelOP | Score98.70% | Percentile91.67% | Participants37 | EvidenceC | Evaluated |
| Rank05 | ModelAN | Score98.20% | Percentile88.89% | Participants37 | EvidenceC | Evaluated |
| Rank06 | ModelOP | Score98.00% | Percentile86.11% | Participants37 | EvidenceC | Evaluated |
| Rank07 | ModelAN | Score97.90% | Percentile83.33% | Participants37 | EvidenceC | Evaluated |
| Rank08 | ModelXI | Score96.80% | Percentile80.56% | Participants37 | EvidenceC | Evaluated |
| Rank09 | ModelOP | Score96.70% | Percentile77.78% | Participants37 | EvidenceC | Evaluated |
| Rank10 | ModelOP | Score95.60% | Percentile75.00% | Participants37 | EvidenceC | Evaluated |
| Rank11 | ModelOP | Score95.60% | Percentile72.22% | Participants37 | EvidenceC | Evaluated |
| Rank12 | ModelOP | Score95.60% | Percentile69.44% | Participants37 | EvidenceC | Evaluated |
| Rank13 | ModelME | Score94.10% | Percentile66.67% | Participants37 | EvidenceC | Evaluated |
| Rank14 | ModelOP | Score93.40% | Percentile63.89% | Participants37 | EvidenceC | Evaluated |
| Rank15 | ModelAM Nova 2 ProAmazon | Score92.70% | Percentile61.11% | Participants37 | EvidenceC | Evaluated |
| Rank16 | ModelOP | Score92.50% | Percentile58.33% | Participants37 | EvidenceC | Evaluated |
| Rank17 | ModelME | Score91.50% | Percentile55.56% | Participants37 | EvidenceC | Evaluated |
| Rank18 | ModelMI | Score87.00% | Percentile52.78% | Participants37 | EvidenceC | Evaluated |
| Rank19 | ModelMI | Score87.00% | Percentile50.00% | Participants37 | EvidenceC | Evaluated |
| Rank20 | ModelCO | Score85.00% | Percentile47.22% | Participants37 | EvidenceC | Evaluated |
| Rank21 | ModelME | Score83.10% | Percentile44.44% | Participants37 | EvidenceC | Evaluated |
| Rank22 | ModelAN | Score83.00% | Percentile41.67% | Participants37 | EvidenceC | Evaluated |
| Rank23 | ModelAMNova 2 OmniAmazon | Score80.00% | Percentile38.89% | Participants37 | EvidenceC | Evaluated |
| Rank24 | ModelAMNova 2 LiteAmazon | Score76.00% | Percentile36.11% | Participants37 | EvidenceC | Evaluated |
| Rank25 | ModelME | Score73.68% | Percentile33.33% | Participants37 | EvidenceC | Evaluated |
| Rank26 | ModelLA | Score73.00% | Percentile30.56% | Participants37 | EvidenceC | Evaluated |
| Rank27 | ModelME | Score72.80% | Percentile27.78% | Participants37 | EvidenceC | Evaluated |
| Rank28 | ModelMI | Score71.70% | Percentile25.00% | Participants37 | EvidenceC | Evaluated |
| Rank29 | ModelMA | Score65.80% | Percentile22.22% | Participants37 | EvidenceC | Evaluated |
| Rank30 | ModelMA | Score65.80% | Percentile19.44% | Participants37 | EvidenceC | Evaluated |
Tau2 Telecom Highlights
The leading models and scores on this benchmark.
Tau2 Telecom Score Distribution
A closer view of the leading scores on this benchmark.
The Top AI Models for Tau2 Telecom
The first five results on this benchmark, with official price and output speed added where the model identity can be matched.
What is Tau2 Telecom?
What Tau2 Telecom measures and how its scores work.
Tau2 Telecom is a telecom-domain benchmark in which agents and users use tools in a dual-control environment.
It measures Score as a ratio, testing coordination and communication capabilities.
Scores are shown in ratio. This benchmark is not independently verified and has an evidence level of B.
- Family
- Tau2 Telecom
- 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 Tau2 Telecom.
Which model scores highest on Tau2 Telecom?
Claude Opus 4.6 is currently ranked first with 99.30%.
What are the top three models on Tau2 Telecom?
The current leaders are Claude Opus 4.6 (99.30%), LongCat-Flash-Thinking-2601 (99.30%), and GPT-5.4 (98.90%).
Which Tau2 Telecom model has the lowest official input price?
GPT-5.4 nano has the lowest matched official input price at $0.20 input / $1.3 output per 1M tokens.
Which models are fastest among Tau2 Telecom results?
The fastest matched records are GPT-4o (132.00 tok/s via OpenAI), GPT-5.2 (100.00 tok/s via OpenAI), and GPT-5 (100.00 tok/s via OpenAI).
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.