AI article
Breaking 0.669 to Reach Top 5 in Kaggle's "Name That LLM": The Decoy Trap, Dual-SVC & Sequence Encoders
Community description: How we de-camouflaged public SOTA notebooks, added DeBERTa-v3 sequence classification, recalibrated soft Sinkhorn balancing, and applied deterministic typography invariants to push beyond 0.672 into Top 5.
Dev.to | Nov 7, 2026 | Jun Matsui
Automated excerpt
Anthropic: Claude Fable 5, Opus 4.6, Opus 4.8, Opus 5, Sonnet 5 Google: Gemini 3.1 Pro Preview, 3.6 Flash, 3.7 Flash, 3.8 Flash OpenAI: GPT-5.5, GPT-5.6 Luna, GPT-5.6 Sol, GPT-5.6 Terra, GPT-6 Astra The metric is Balanced Accuracy Score (macro-average recall per class). Spaced Em-Dash (—): Produced only by Claude Opus 4.6, Opus 5, GLM-5.3, and GLM-5.3 Flash. Standard Em-Dash (—): Absent from Gemini 3.1 Pro, 3.6 Flash, and 3.8 Flash.
Selected automatically from source text; not independently written or fact-checked. Read the original for full context.