TeleCom-Bench - Core Network: leaderboard
Metric: LLM-judge score (%; open-ended core-network product-knowledge questions, three-judge vote on a 5-point scale). Source: arxiv.org. Saturation forecast: Around December 2026. 8 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | DeepSeek V3.2 (Thinking) | 62.34 |
| 2 | Qwen 3 235B A22B (Thinking) | 62.13 |
| 3 | Qwen 3 32B (Thinking) | 60.22 |
| 4 | GLM-4.7 (Thinking) | 47.68 |
Interactive version: theaggregate.ai/benchmark?slug=telecom-bench-core-network · How It Works · Data refreshed daily, snapshot 2026-09-25.