AI text detector posts 99.8% Arabic accuracy with under 1% false positives across languages
markjeffrey · x · 2026-10-28
It's AI, the detector behind Bittensor subnet 32, published multilingual benchmark results on DetectRL-X (ACL 2026), a new multilingual benchmark with 12K human and AI texts per language across 6 real-world writing domains.
Accuracy: Arabic 99.8%, German 99.5%, French 99.4%, Spanish 96.0%.
False positives on real student writing: Arabic 0.89%, German 0.48%, French 0.56%, Spanish 0.72% — under 1% in every language.
In English: 98.3% on RAID and #1 on MGTD, ahead of GPTZero and Originality AI.
More from Models
- OpenAI opens Decisions API beta: up to 10x faster decisions than GPT-6 Luna — OpenAIDevs · 2026-10-28
- Open-Weight AI Security Research Stalls as $80 Fine-Tuning Undoes Safety Interventions — Miles_Brundage · 2026-10-28
- Socher's Recursive Unveils Flint: 125+ tok/s Local Coding Model Built by Automated Research — jeffclune · 2026-10-28
- Liquid AI releases LFM3: six instances spanning text, audio, vision, omni — FinancialAd1961 · 2026-10-28
- Qwen3.8 Flash on a single DGX Spark gets up to 62.7% faster code generation in new update — EAccelerate_42 · 2026-10-28
- Arena co-founder: US still leads frontier AI, but China is winning open models and driving down cost — JaynitMakwana · 2026-10-28