TeleCom-Bench - Basic Theory: leaderboard
Telecom theory set of TeleCom-Bench (Xiao et al., ZTE Corporation, KDD 2026): multiple-select questions on communication fundamentals, 5G network architecture and 3GPP protocols. Scored by Macro-F1 in percent (the mean of a communication-exam set and a 3GPP set), with reasoning enabled, temperature 0.7 and a majority vote over three samples; higher is better.
Metric: Macro-F1 (%; multiple-select telecom theory questions, mean of a communication-exam set and a 3GPP-protocol set). Source: arxiv.org. Saturation forecast: Around February 2027. 8 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Qwen 3 235B A22B (Thinking) | 69.04 | #622 (Qwen 3 235B A22B) |
| 2 | DeepSeek V3.2 (Thinking) | 67.12 | #403 (DeepSeek V3.2) |
| 3 | Qwen 3 32B (Thinking) | 61.01 | #960 (Qwen 3 32B) |
| 4 | GLM-4.7 (Thinking) | 51.82 | #365 (GLM-4.7) |
No result here: #1 Claude Fable 5.2, #2 Gemini 4 Carbon, #5 Claude Opus 5.5.
Interactive version: theaggregate.ai/benchmark?slug=telecom-bench-basic-theory · How It Works · Data refreshed daily, snapshot 2026-11-12.