internlm2.5-7B: benchmark results
Shanghai AI Lab's 7B InternLM2.5 base model with ~20% better reasoning than InternLM2 and support for up to 1M-token context (mid-2024). Provider: Shanghai AI Lab. Released 2024-06-28. Access: Open.
Unified ELO 1434 ± 1, rank #1019 of 1392 rated models, from 12 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| GSMA Open-Telco - TeleTables | 30.13 | Score (%) | 58 |
| Open PL LLM - Generative | 44.4 | Average Generative Score (%) | 43 |
| Open PL LLM Leaderboard | 39.82 | Average Score (%) | 43 |
| Open PL LLM - Multiple Choice | 33.87 | Average Multiple-Choice Score (%) | 41.3 |
| Open PL LLM - RAG | 47.24 | Average RAG Score (%) | 35 |
| GSMA Open-Telco - TeleLogs | 12.11 | Score (%) | 21.6 |
| GSMA Open-Telco - TeleQnA | 66.9 | Score (%) | 21.6 |
| GSMA Open-Telco - srsRAN-Bench | 73.81 | Score (%) | 19.3 |
| GSMA Open-Telco - ORAN-Bench | 65.47 | Score (%) | 17 |
| GSMA Open-Telco LLM Leaderboard | 40.38 | Average Score (%) | 13.6 |
| GSMA Open-Telco - 3GPP | 25.42 | Score (%) | 9.1 |
| GSMA Open-Telco - TeleMath | 8.8 | Score (%) | 9.1 |
Interactive version: theaggregate.ai/model?slug=internlm2-5-7b · How It Works · Data refreshed daily, snapshot 2026-09-05.