ProLLM - Summarization — leaderboard
ProLLM benchmark evaluating LLMs on text summarization quality for business documents.
Metric: Score (%). Source: www.prollm.ai. Status: saturated. 59 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | GPT-5 Mini | 98.8 |
| 2 | GPT-5 | 98.5 |
| 3 | GPT-OSS-120B | 98.2 |
| 4 | Kimi K2 | 95.9 |
| 5 | Grok 4 | 95.9 |
| 6 | GPT-5 Nano | 93.3 |
| 7 | Command A | 91.2 |
| 8 | GPT-OSS-20B | 83.1 |
| 9 | GPT-4.1 | 78 |
| 10 | DeepSeek V3 | 77.3 |
| 11 | Grok 3 | 76.5 |
| 12 | GPT-4.1 Mini | 76.4 |
| 13 | GPT-4.5 | 76.4 |
| 14 | Gemma 3 27B (IT) | 75.2 |
| 15 | DeepSeek R1 | 75 |
Interactive version: theaggregate.ai/benchmark?slug=prollm-summarization · How the rankings work · Data refreshed daily, snapshot 2026-07-22.