Kluster Hallucination Detection - RAG Method 2 Resistance: leaderboard
The "RAG Method 2 Resistance" subtask of Kluster Hallucination Detection. A task from the Kluster Hallucination Detection benchmark, measuring how reliably a model detects unsupported or fabricated claims.
Metric: Resistance (100 - Hallucination Rate %). Source: huggingface.co. Saturation forecast: Estimated already saturated. 12 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | DeepSeek R1 0528 | 97.74 | #222 |
| 2 | Llama 4 Maverick Instruct FP8 | 96.66 | #414 |
| 3 | Gemma 3 27B (IT) | 96.29 | #523 |
| 4 | Llama 4 Scout Instruct | 95.77 | #539 |
| 5 | DeepSeek V3 (0324) | 95.34 | #340 |
| 6 | Mistral Small 3 | 95.26 | #627 |
| 7 | Qwen 3 235B A22B FP8 | 94.96 | #301 |
| 8 | Magistral Small | 91.38 | #1016 |
| 9 | Qwen 2.5 VL 7B Instruct | 90.65 | #654 |
| 10 | Mistral Nemo Instruct (2407) | 89.37 | #936 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=kluster-hallucination-detection-rag-method-2-resistance · How It Works · Data refreshed daily, snapshot 2026-10-20.