6G-Bench - Network Slicing and Resource Management: leaderboard
Metric: Accuracy (%) on the network slicing and resource management tasks (T4-T8, T13, T14, T16, T29) 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), group score is the unweighted mean of its task accuracies; higher is better. Source: arxiv.org. Saturation forecast: Estimated already saturated. 28 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Llama 4 Maverick | 80.5 | #451 |
| 2 | Qwen3 Coder Next | 78.6 | #321 |
| 3 | Qwen 3 235B A22B 2507 Instruct | 76.9 | #291 |
| 4 | DeepSeek V3.2 | 76.1 | #198 |
| 5 | GPT-5.2 Instant | 76 | #205 |
| 6 | Ministral 3 14B | 75.9 | #636 |
| 7 | GPT-4o Mini | 75.7 | #588 |
| 8 | GPT-5.2 Codex | 75.4 | #89 |
| 9 | Olmo 3.1 32B Instruct | 75.3 | #754 |
| 10 | Ministral 3 8B | 74.9 | #676 |
| 11 | DeepSeek V3.2 Exp | 74.5 | #227 |
| 12 | Claude Haiku 4.5 | 74.2 | #271 |
| 13 | Qwen 3 VL 32B Instruct | 72.8 | #276 |
| 14 | Phi-4 | 72.5 | #701 |
| 15 | GPT-5 Mini | 71.5 | #176 |
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-network-slicing-and-resource-management · How It Works · Data refreshed daily, snapshot 2026-10-11.