TeleCom-Bench - Basic Theory: leaderboard

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 December 2026. 8 models tracked.

Top models

#ModelScore
1Qwen 3 235B A22B (Thinking)69.04
2DeepSeek V3.2 (Thinking)67.12
3Qwen 3 32B (Thinking)61.01
4GLM-4.7 (Thinking)51.82

Interactive version: theaggregate.ai/benchmark?slug=telecom-bench-basic-theory · How It Works · Data refreshed daily, snapshot 2026-09-25.