GSMA Open Telco Leaderboard: leaderboard
Telecommunications-domain model leaderboard across TeleQnA, TeleTables, ORANBench, srsRANBench, TeleMath, TeleLogs, and 3GPP pattern-matching benchmarks.
Metric: Average Score (%). Source: huggingface.co. Source: huggingface.co. 90 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemini 3.1 Pro (Preview) | 75.55 | #58 |
| 2 | Gemini 3 Pro (Preview) | 74.65 | #66 |
| 3 | Claude Opus 4.6 | 73.3 | #63 |
| 4 | GPT-5 | 71.88 | #98 |
| 5 | Gemini 3 Flash (Preview) | 70.41 | #82 |
| 6 | Claude Opus 4.5 | 69.64 | #83 |
| 7 | Kimi K2.5 | 69.42 | #144 |
| 8 | O3 | 69.39 | #124 |
| 9 | Grok 4 Fast | 68.42 | #254 |
| 10 | Claude Opus 4 | 68.25 | #163 |
| 11 | O1 | 68.08 | #183 |
| 12 | Claude Opus 4.1 | 68.04 | #140 |
| 13 | Grok 4.1 Fast | 67.14 | #217 |
| 14 | Claude Sonnet 4.5 | 66.04 | #142 |
| 15 | Claude 3.7 Sonnet | 65.56 | #249 |
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-leaderboard · How It Works · Data refreshed daily, snapshot 2026-10-20.