List your company
ResearchFormerly WizWand

Classification on SPAM (test)

99.6AccuracyACT
60.80870.87980.9591.021Sep 30, 2025
Updated 6mo ago

Evaluation results

MethodLinks
ACTModel=Nano, d=4, k=102025.0999.699.6
ACTModel=Nano, d=2, k=102025.0999.599.5
ACTModel=Nano, d=3, k=102025.0999.599.5
ACTModel=Nano, d=5, k=102025.0999.599.5
ACTTree Depth (d)=3, Optimization Steps (k)=10, LLM Backbone=GPT-4.1 Mini2025.0999.599.5
ACTTree Depth (d)=3, Optimization Steps (k)=10, LLM Backbone=GPT-4.1 Nano2025.0999.299.2
ACTTree Depth (d)=3, Optimization Steps (k)=10, LLM Backbone=Avg2025.099999
ACTModel=Gemma, d=5, k=102025.0998.898.8
ACTTree Depth (d)=3, Optimization Steps (k)=10, LLM Backbone=Qwen3 4b2025.0998.898.8
ACTTree Depth (d)=2, Optimization Steps (k)=5, LLM Backbone=GPT-4.1 Nano2025.0998.798.6
ACTTree Depth (d)=3, Optimization Steps (k)=10, LLM Backbone=Gemma3 4b2025.0998.598.5
DSPyEvaluation Protocol=BFSR, 8 demos, LLM Backbone=GPT-4.1 Nano2025.0998.398.3
TextGradModel=Nano2025.0998.298.2
DSPyModel=Nano2025.0998.298.2
DSPyEvaluation Protocol=BFSR, 8 demos, LLM Backbone=GPT-4.1 Mini2025.0998.298.2
ACTTree Depth (d)=2, Optimization Steps (k)=5, LLM Backbone=GPT-4.1 Mini2025.0998.298.2
ACTModel=Gemma, d=4, k=102025.0997.998
ACTModel=Gemma, d=3, k=102025.0997.697.6
DSPyModel=Gemma2025.0997.497.5
ACTTree Depth (d)=2, Optimization Steps (k)=5, LLM Backbone=Avg2025.0997.497.3
TEXTGRADLLM Backbone=GPT-4.1 Nano2025.0997.397.3
TextGradModel=Gemma2025.0997.297.2
DSPyEvaluation Protocol=BFSR, 8 demos, LLM Backbone=Qwen3 4b2025.0997.297.2
DSPyEvaluation Protocol=BFSR, 8 demos, LLM Backbone=Avg2025.0997.297.2
Rule FitLLM Backbone=Avg2025.099796.9
TEXTGRADLLM Backbone=GPT-4.1 Mini2025.0996.796.6
ACTTree Depth (d)=2, Optimization Steps (k)=5, LLM Backbone=Qwen3 4b2025.0996.796.6
ACTModel=Gemma, d=2, k=102025.0996.396.4
TEXTGRADLLM Backbone=Avg2025.0996.396.2
TEXTGRADLLM Backbone=Qwen3 4b2025.099696
ACTTree Depth (d)=2, Optimization Steps (k)=5, LLM Backbone=Gemma3 4b2025.0995.895.8
CoTEvaluation Protocol=0-shot, LLM Backbone=GPT-4.1 Mini2025.0995.795.5
CoTModel=Nano2025.0995.695.5
CoTEvaluation Protocol=0-shot, LLM Backbone=GPT-4.1 Nano2025.0995.595.3
DSPyEvaluation Protocol=BFSR, 8 demos, LLM Backbone=Gemma3 4b2025.099595.2
TEXTGRADLLM Backbone=Gemma3 4b2025.099594.7
TF-IDF + CARTd=102025.0994.995.2
CoTEvaluation Protocol=0-shot, LLM Backbone=Qwen3 4b2025.0993.293.6
TF-IDF + CARTTree Depth (d)=5, LLM Backbone=Avg2025.0992.793.1
CoTEvaluation Protocol=0-shot, LLM Backbone=Avg2025.0989.490.8
Con. tag.LLM Backbone=Gemma3 4b2025.0983.285.5
Con. tag.LLM Backbone=GPT-4.1 Mini2025.0982.385
CoTModel=Gemma2025.097580.1
CoTEvaluation Protocol=0-shot, LLM Backbone=Gemma3 4b2025.0973.378.6
Con. tag.LLM Backbone=Avg2025.097364
Con. tag.LLM Backbone=GPT-4.1 Nano2025.0964.245.8
Con. tag.LLM Backbone=Qwen3 4b2025.0962.339.6