6G-Bench: leaderboard
Metric: Accuracy (%) on the full set of 6G-Bench's 3,722 expert-validated four-option multiple-choice questions on network-level semantic reasoning for AI-native 6G networks, deterministic single-shot answers (temperature 0, one letter in a JSON object); higher is better. Source: arxiv.org. Saturation forecast: Estimated already saturated. 22 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Llama 4 Maverick | 82.9 | #451 |
| 2 | Qwen3 Coder Next | 81.8 | #321 |
| 3 | Ministral 3 14B | 79.5 | #636 |
| 4 | GPT-5.2 Instant | 79.4 | #205 |
| 5 | GPT-5.2 Codex | 79 | #89 |
| 6 | DeepSeek V3.2 Exp | 78.9 | #227 |
| 7 | Olmo 3.1 32B Instruct | 78.3 | #754 |
| 8 | Ministral 3 8B | 78.3 | #676 |
| 9 | Claude Haiku 4.5 | 76.4 | #271 |
| 10 | Hermes 4 70B | 76.2 | #489 |
| 11 | GPT-4.1 Nano | 72.6 | #716 |
| 12 | Phi-4 | 69.3 | #701 |
| 13 | Llama 3.1 8B Instruct | 66.6 | #1018 |
| 14 | lfm-2.2-6B | 65.9 | |
| 15 | Qwen 2.5 7B Instruct | 63.2 | #846 |
No result here: #3 Claude Opus 5.5, #5 GPT-6 Astra, #8 Claude Fable 5.1.
Interactive version: theaggregate.ai/benchmark?slug=6g-bench · How It Works · Data refreshed daily, snapshot 2026-10-11.