GSMA Open-Telco - TeleLogs: leaderboard
The "TeleLogs" 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 | Gemini 3 Pro (Preview) | 86 | #66 |
| 2 | Gemini 3.1 Pro (Preview) | 82 | #58 |
| 3 | GPT-5 | 78 | #98 |
| 4 | Grok 4 Fast | 75 | #254 |
| 5 | O1 | 73 | #183 |
| 6 | O3 | 72 | #124 |
| 7 | Grok 4.1 Fast | 71 | #217 |
| 8 | Claude Opus 4.6 | 70 | #63 |
| 9 | Claude Opus 4 | 65 | #163 |
| 10 | Grok Code Fast 1 | 61 | #337 |
| 11 | Qwen 3 235B A22B 2507 | 61 | #260 |
| 12 | Kimi K2.5 | 60 | #144 |
| 13 | Claude Sonnet 4.5 | 59 | #142 |
| 14 | Claude 3.7 Sonnet | 59 | #249 |
| 15 | Claude Opus 4.1 | 59 | #140 |
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-telelogs · How It Works · Data refreshed daily, snapshot 2026-10-20.