GSMA Open-Telco - srsRAN-Bench: leaderboard
The "srsRAN-Bench" subtask of GSMA Open-Telco. A task from the GSMA Open-Telco LLM Benchmark, evaluating models on telecommunications domain knowledge, standards and network engineering problems.
Metric: Score (%). Source: huggingface.co. Saturation forecast: Around January 2027. 90 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | MiMo-V2-Flash | 86.67 | #372 |
| 2 | Gemini 2.5 Pro | 84.67 | #152 |
| 3 | Gemini 3.1 Pro (Preview) | 84.67 | #58 |
| 4 | Claude Opus 4.6 | 84.67 | #63 |
| 5 | Kimi K2.5 | 84.67 | #144 |
| 6 | MiniMax-M2.5 | 84.67 | #303 |
| 7 | Gemini 2.5 Flash | 84 | #245 |
| 8 | GPT-OSS-120B | 84 | #341 |
| 9 | Claude 3.5 Sonnet | 84 | #350 |
| 10 | Grok 4 Fast | 84 | #254 |
| 11 | phi-4-14B | 83.36 | #733 |
| 12 | Gemini 3 Flash (Preview) | 83.33 | #82 |
| 13 | Phi-4 | 83.33 | #706 |
| 14 | GPT-5.2 | 82.67 | #110 |
| 15 | Claude Opus 4.5 | 82.67 | #83 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=gsma-open-telco-srsran-bench · How It Works · Data refreshed daily, snapshot 2026-10-20.