AA TAU-2 Bench — leaderboard
Artificial Analysis independent evaluation of TAU-2 Bench: dual-control conversational AI in telecom support scenarios (114 tasks).
Metric: Accuracy (%). Source: artificialanalysis.ai. Status: saturated. 439 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GLM-5.2 (Max) | 99.12 |
| 2 | JT-35B-Flash | 99.12 |
| 3 | GLM-5-Turbo | 98.54 |
| 4 | Step 3.7 Flash | 98.54 |
| 5 | GLM-5 (Thinking) | 98.25 |
| 6 | Qwen 3.6 Plus | 97.66 |
| 7 | GLM-5.1 (Thinking) | 97.66 |
| 8 | Grok 4.3 (High) | 97.66 |
| 9 | GLM-5 (Non-reasoning) | 97.37 |
| 10 | GLM-5.1 (Non-reasoning) | 97.08 |
| 11 | Grok 4.20 0309 (Reasoning) | 96.49 |
| 12 | DeepSeek V4 Pro (Reasoning, Max Effort) | 96.2 |
| 13 | Kimi K2.6 | 95.91 |
| 14 | Qwen 3.6 Max Preview | 95.91 |
| 15 | Kimi K2.5 (Thinking) | 95.91 |
Interactive version: theaggregate.ai/benchmark?slug=aa-tau-2-bench · How the rankings work · Data refreshed daily, snapshot 2026-07-22.