ProLLM - Entity Extraction: leaderboard
ProLLM benchmark evaluating LLMs on structured entity extraction from unstructured text. Measured by F1 score.
Metric: Score (%). Source: www.prollm.ai. Saturation forecast: Not forecast. 48 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Grok 3 | 85.5 | #304 |
| 2 | GPT-4o | 85.4 | #343 |
| 3 | Mistral Small 3 | 85.3 | #627 |
| 4 | MiniMax-Text-01 | 85.1 | #513 |
| 5 | O1 | 84.8 | #183 |
| 6 | Nova Pro | 84.5 | #569 |
| 7 | GPT-5 Nano | 84.2 | #425 |
| 8 | DeepSeek V3 | 83.9 | #321 |
| 9 | Gemma 2 9B (IT) | 83.9 | #788 |
| 10 | Gemini 2.0 Flash | 83.8 | #342 |
| 11 | GPT-4o Mini | 83.6 | #599 |
| 12 | Kimi K2 | 83.3 | #243 |
| 13 | O3 Mini (Medium) | 83.1 | #272 (O3 Mini) |
| 14 | Mistral Small 3.1 | 82.8 | #610 |
| 15 | GPT-4.1 | 82.7 | #248 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=prollm-entity-extraction · How It Works · Data refreshed daily, snapshot 2026-10-20.