Detection on Algospeak Phonetic 1.0 (test) benchmark leaderboard · SOTA2 Research

Detection on Algospeak Phonetic 1.0 (test)

0.99Adjusted R2GPT-4o-m

Evaluation Results

Method	Links
GPT-4o-m2026.05		0.99	—	—	—
Qwen2026.05		0.89	—	—	—
Grok2026.05		0.35	—	—	—
Claude2026.05		0.3	—	—	—
Mistral2026.05		0.12	—	—	—
Llama2026.05		-0.25	—	—	—
GPT-4o2026.05		-4.54	—	—	—
Significance Count2026.05		—	—	—	6