IntentGrasp - News: leaderboard
Metric: Instance F1 (%) on the News (N) domain of the 12,909-item All Set, mean over option-order shuffles, zero-shot at temperature 0; higher is better. Source: arxiv.org. Saturation forecast: Around January 2027. 11 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | gemma-4-E4B-it | 56.87 |
| 2 | Llama 3.3 70B Instruct [4bit] | 49.13 |
| 3 | Qwen 3 8B | 43.16 |
| 4 | Gemma 4 E2B (IT) | 36.8 |
| 5 | Qwen 3 4B | 31.18 |
| 6 | Llama 3.1 8B Instruct | 29.21 |
| 7 | OLMo 3 7B Instruct | 16.71 |
| 8 | Llama 3.2 3B Instruct | 14.67 |
Interactive version: theaggregate.ai/benchmark?slug=intentgrasp-news · How It Works · Data refreshed daily, snapshot 2026-10-07.