TAEF (Text Analytics Evaluation Framework) — leaderboard
Metric: F1 (self-reported). Source: benchmarklist.com. 11 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | Qwen 3.5 397B A17B | 79.5 |
| 2 | Grok 4.1 Fast | 77.3 |
| 3 | Qwen 3.5 122B A10B | 72.2 |
| 4 | Gemini 3.1 Flash Lite | 70.3 |
| 5 | GPT-5.4 Mini | 68.7 |
| 6 | Llama 3.3 70B Instruct | 66.5 |
| 7 | Llama 3.1 8B Instruct | 65.5 |
| 8 | Llama 3.2 3B Instruct | 38.5 |
| 9 | Qwen 3 4B Instruct | 33.7 |
Interactive version: theaggregate.ai/benchmark?slug=taef-text-analytics-evaluation-framework · How the rankings work · Data refreshed daily, snapshot 2026-07-22.