IntentGrasp - Customer Support: leaderboard
Metric: Instance F1 (%) on the Customer Support (CS) 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 June 2027. 11 models tracked.
Top models
| # | Model | Score |
|---|---|---|
| 1 | gemma-4-E4B-it | 25.51 |
| 2 | Llama 3.3 70B Instruct [4bit] | 19.98 |
| 3 | Qwen 3 8B | 19.96 |
| 4 | Qwen 3 4B | 19.74 |
| 5 | Gemma 4 E2B (IT) | 19.58 |
| 6 | OLMo 3 7B Instruct | 19.52 |
| 7 | Llama 3.1 8B Instruct | 13.79 |
| 8 | Llama 3.2 3B Instruct | 9.19 |
Interactive version: theaggregate.ai/benchmark?slug=intentgrasp-customer-support · How It Works · Data refreshed daily, snapshot 2026-10-07.