ProLLM - Summarization: leaderboard
ProLLM benchmark evaluating LLMs on text summarization quality for business documents.
Metric: Score (%). Source: www.prollm.ai. Saturation forecast: Estimated already saturated. 59 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-5 Mini | 98.8 | #186 |
| 2 | GPT-5 | 98.5 | #98 |
| 3 | GPT-OSS-120B | 98.2 | #341 |
| 4 | Grok 4 | 95.9 | #181 |
| 5 | Kimi K2 | 95.9 | #243 |
| 6 | GPT-5 Nano | 93.3 | #425 |
| 7 | Command A | 91.2 | #508 |
| 8 | GPT-OSS-20B | 83.1 | #518 |
| 9 | GPT-4.1 | 78 | #248 |
| 10 | DeepSeek V3 | 77.3 | #321 |
| 11 | Grok 3 | 76.5 | #304 |
| 12 | GPT-4.1 Mini | 76.4 | #355 |
| 13 | GPT-4.5 | 76.4 | #274 |
| 14 | Gemma 3 27B (IT) | 75.2 | #523 |
| 15 | DeepSeek R1 | 75 | #251 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=prollm-summarization · How It Works · Data refreshed daily, snapshot 2026-10-20.