List your company
ResearchFormerly WizWand

Classification on DIAGNO (test)

85.5AccuracyTF-IDF + CART
48.68458.24267.877.358Sep 30, 2025
Updated 6mo ago

Evaluation results

MethodLinks
TF-IDF + CARTd=72025.0985.576.7
ACTTree Depth (d)=4, Optimization Steps (k)=20, LLM Backbone=GPT-4.1 Mini2025.0982.381.8
Rule FitLLM Backbone=Avg2025.0980.279.3
TF-IDF + CARTTree Depth (d)=3, LLM Backbone=Avg2025.0978.878.9
ACTTree Depth (d)=3, Optimization Steps (k)=10, LLM Backbone=GPT-4.1 Mini2025.0977.375.2
Con. tag.LLM Backbone=GPT-4.1 Mini2025.0975.378.6
ACTModel=Nano, d=5, k=102025.0973.754.2
ACTModel=Nano, d=8, k=102025.0973.456.1
ACTModel=Gemma, d=5, k=102025.0972.852.7
ACTTree Depth (d)=4, Optimization Steps (k)=20, LLM Backbone=Avg2025.0972.874.2
ACTModel=Nano, d=4, k=102025.0972.754.1
ACTModel=Gemma, d=4, k=102025.0972.641.5
ACTModel=Gemma, d=8, k=102025.0971.959.4
DSPyModel=Nano2025.0970.745.9
ACTTree Depth (d)=4, Optimization Steps (k)=20, LLM Backbone=GPT-4.1 Nano2025.0970.370.8
ACTTree Depth (d)=4, Optimization Steps (k)=20, LLM Backbone=Qwen3 4b2025.0970.373.5
DSPyEvaluation Protocol=BFSR, 8 demos, LLM Backbone=GPT-4.1 Nano2025.0968.761.2
CoTModel=Nano2025.0968.648.1
TextGradModel=Nano2025.0968.648.1
ACTTree Depth (d)=3, Optimization Steps (k)=10, LLM Backbone=Avg2025.0968.667.5
ACTTree Depth (d)=4, Optimization Steps (k)=20, LLM Backbone=Gemma3 4b2025.0968.370.8
TextGradModel=Gemma2025.096754.2
ACTTree Depth (d)=3, Optimization Steps (k)=10, LLM Backbone=GPT-4.1 Nano2025.0966.867
DSPyModel=Gemma2025.0966.557.9
TEXTGRADLLM Backbone=GPT-4.1 Mini2025.0965.855.5
Con. tag.LLM Backbone=Gemma3 4b2025.0965.563.9
ACTTree Depth (d)=3, Optimization Steps (k)=10, LLM Backbone=Gemma3 4b2025.0965.366.5
DSPyEvaluation Protocol=BFSR, 8 demos, LLM Backbone=Avg2025.0965.160.9
ACTTree Depth (d)=3, Optimization Steps (k)=10, LLM Backbone=Qwen3 4b2025.0964.861.3
Con. tag.LLM Backbone=Avg2025.0964.766.3
DSPyEvaluation Protocol=BFSR, 8 demos, LLM Backbone=GPT-4.1 Mini2025.0964.559.4
TEXTGRADLLM Backbone=GPT-4.1 Nano2025.0964.553
TEXTGRADLLM Backbone=Avg2025.0964.456.3
DSPyEvaluation Protocol=BFSR, 8 demos, LLM Backbone=Gemma3 4b2025.096468.2
TEXTGRADLLM Backbone=Qwen3 4b2025.096460
CoTEvaluation Protocol=0-shot, LLM Backbone=GPT-4.1 Nano2025.0963.354.7
DSPyEvaluation Protocol=BFSR, 8 demos, LLM Backbone=Qwen3 4b2025.0963.354.9
TEXTGRADLLM Backbone=Gemma3 4b2025.0963.356.7
CoTEvaluation Protocol=0-shot, LLM Backbone=Qwen3 4b2025.0963.241.7
CoTEvaluation Protocol=0-shot, LLM Backbone=Avg2025.0962.354.3
CoTEvaluation Protocol=0-shot, LLM Backbone=Gemma3 4b2025.0961.569.5
CoTEvaluation Protocol=0-shot, LLM Backbone=GPT-4.1 Mini2025.0961.251.4
Con. tag.LLM Backbone=GPT-4.1 Nano2025.0959.358.1
Con. tag.LLM Backbone=Qwen3 4b2025.0958.864.7
CoTModel=Gemma2025.0950.155