TeleCom-Bench - Tool Invocation: leaderboard
Metric: Exact match (%; tool-invocation workflow generation from a fixed tool library). Source: arxiv.org. Saturation forecast: Estimated already saturated. 8 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | DeepSeek V3.2 (Thinking) | 94.06 |
| 2 | Qwen 3 32B (Thinking) | 84.71 |
| 3 | GLM-4.7 (Thinking) | 56.5 |
| 4 | Qwen 3 235B A22B (Thinking) | 45.54 |
Interactive version: theaggregate.ai/benchmark?slug=telecom-bench-tool-invocation · How It Works · Data refreshed daily, snapshot 2026-09-25.