List your company
ResearchFormerly WizWand

Compositional Generalization on Evaluation Dataset (Fold 1 Seen)

0.6191ScoreMistral-7B
0.1621240.2807620.39940.518038Jan 29, 2026
Updated 8mo ago

Evaluation results

MethodLinks
Mistral-7BFine-tuning Strategy=LoRA, Model Backbone=Mistral-7B2026.010.6191
Mistral-7B + COGLMFine-tuning Strategy=LoRA, Model Backbone=Mistral-7B, Method Components=COGLM2026.010.5794
Gemma-7BFine-tuning Strategy=LoRA, Model Backbone=Gemma-7B2026.010.5747
LLaMA-3-8B + COGLMFine-tuning Strategy=LoRA, Model Backbone=LLaMA-3-8B, Method Components=COGLM2026.010.5678
Gemma-7B + COGLMFine-tuning Strategy=LoRA, Model Backbone=Gemma-7B, Method Components=COGLM2026.010.5626
Qwen2.5-7B + COGLMFine-tuning Strategy=LoRA, Model Backbone=Qwen2.5-7B, Method Components=COGLM2026.010.5465
Qwen2.5-7BFine-tuning Strategy=LoRA, Model Backbone=Qwen2.5-7B2026.010.5203
LLaMA-3-8BFine-tuning Strategy=LoRA, Model Backbone=LLaMA-3-8B2026.010.5095
DeepSeek-7B + COGLMFine-tuning Strategy=LoRA, Model Backbone=DeepSeek-7B, Method Components=COGLM2026.010.4425
Claude 3.5 Sonnet + FS*Evaluation Protocol=Few-shot, Model Backbone=Claude 3.5 Sonnet2026.010.4062
GPT-4o + FS*Evaluation Protocol=Few-shot, Model Backbone=GPT-4o2026.010.3908
DeepSeek V3 + FS*Evaluation Protocol=Few-shot, Model Backbone=DeepSeek V32026.010.3885
DeepSeek V3Evaluation Protocol=Zero-shot, Model Backbone=DeepSeek V32026.010.3806
Claude 3.5 SonnetEvaluation Protocol=Zero-shot, Model Backbone=Claude 3.5 Sonnet2026.010.3671
DeepSeek-7BFine-tuning Strategy=LoRA, Model Backbone=DeepSeek-7B2026.010.3261
GPT-4oEvaluation Protocol=Zero-shot, Model Backbone=GPT-4o2026.010.3161
Llama 3 (70B) + FS*Evaluation Protocol=Few-shot, Model Backbone=Llama 3 (70B)2026.010.2503
Llama 3 (70B)Evaluation Protocol=Zero-shot, Model Backbone=Llama 3 (70B)2026.010.1797