Artificial Analysis · tau2-Bench Telecom
The Frontier
Best score over time · one chart, every benchmark
Full rankings
34 models tested · sorted by score
| # | Model | Score |
|---|---|---|
| 1 | 95.6 | |
| 2 | 95.3 | |
| 3 | 94.2 | |
| 4 | 93.0 | |
| 5 | 92.1 | |
| 6 | 90.1 | |
| 7 | 90.1 | |
| 8 | 88.9 | |
| 9 | 86.3 | |
| 10 | 86.0 | |
| 11 | 85.1 | |
| 12 | 84.5 | |
| 13 | 83.9 | |
| 14 | 83.3 | |
| 15 | 80.7 | |
| 16 | 80.7 | |
| 17 | 79.5 | |
| 18 | 69.0 | |
| 19 | 67.8 | |
| 20 | 65.8 | |
| 21 | 60.2 | |
| 22 | 59.9 | |
| 23 | 47.7 | |
| 24 | 43.6 | |
| 25 | 41.5 | |
| 26 | 41.2 | |
| 27 | 37.4 | |
| 28 | 21.9 | |
| 29 | N Nanbeige4.1 3B | 21.6 |
| 30 | 17.8 | |
| 31 | 15.5 | |
| 32 | 15.2 | |
| 33 | 12.6 | |
| 34 | 8.2 |
Score distribution
Where models cluster
Correlated benchmarks
Pearson r · original research
Benchmarks that track with Artificial Analysis · tau2-Bench Telecom
Pearson correlation across models scored on both benchmarks. Closer to 1 = strongly predictive.
Frequently asked
About Artificial Analysis · tau2-Bench Telecom
What does Artificial Analysis · tau2-Bench Telecom measure?
Artificial Analysis · tau2-Bench Telecom is a knowledge benchmark in the BenchGecko catalog. 34 AI models have been tested on it. Scores range from 8.2 to 95.6 out of 100.
Which model leads on Artificial Analysis · tau2-Bench Telecom?
Gemini 3.1 Pro Preview from Google DeepMind leads Artificial Analysis · tau2-Bench Telecom with a score of 95.6. The median score across 34 tested models is 74.3.
Is Artificial Analysis · tau2-Bench Telecom saturated?
Yes · the top model on Artificial Analysis · tau2-Bench Telecom has reached 95.6 out of 100, within 5% of the theoretical ceiling. This benchmark is approaching saturation and may be replaced by a harder successor.
Does Artificial Analysis · tau2-Bench Telecom predict performance on other benchmarks?
Yes · Artificial Analysis · tau2-Bench Telecom scores correlate 0.98 with ARC-AGI across 5 shared models. Models that do well on Artificial Analysis · tau2-Bench Telecom tend to do well on ARC-AGI.
How often is Artificial Analysis · tau2-Bench Telecom data refreshed?
BenchGecko pulls updates daily. New model scores on Artificial Analysis · tau2-Bench Telecom appear as soon as they are published by Epoch AI or the model provider.
- Category
- Knowledge
- Max score
- 100
- Models
- 34
- Updated
- 2026-09-22
Top on Artificial Analysis · tau2-Bench Telecom
Gemini 3.1 Pro Preview · 95.6Qwen3.6 35B A3B · 95.3Mistral Medium 3.5 · 94.2Qwen3.7 Plus · 93.0Qwen3.5 4B · 92.1More knowledge benchmarks
Same category · related evaluations