List your company
ResearchFormerly WizWand

Compositional Generalization on Evaluation Dataset (Full)

0.6379ScoreGemma-7B + COGLM
0.1840440.3018720.41970.537528Jan 29, 2026
Updated 8mo ago

Evaluation results

MethodLinks
Gemma-7B + COGLMFine-tuning Strategy=LoRA, Model Backbone=Gemma-7B, Method Components=COGLM2026.010.6379
Mistral-7B + COGLMFine-tuning Strategy=LoRA, Model Backbone=Mistral-7B, Method Components=COGLM2026.010.6206
LLaMA-3-8B + COGLMFine-tuning Strategy=LoRA, Model Backbone=LLaMA-3-8B, Method Components=COGLM2026.010.6075
Qwen2.5-7B + COGLMFine-tuning Strategy=LoRA, Model Backbone=Qwen2.5-7B, Method Components=COGLM2026.010.6006
Mistral-7BFine-tuning Strategy=LoRA, Model Backbone=Mistral-7B2026.010.5963
Gemma-7BFine-tuning Strategy=LoRA, Model Backbone=Gemma-7B2026.010.5937
Qwen2.5-7BFine-tuning Strategy=LoRA, Model Backbone=Qwen2.5-7B2026.010.5906
LLaMA-3-8BFine-tuning Strategy=LoRA, Model Backbone=LLaMA-3-8B2026.010.5668
DeepSeek-7B + COGLMFine-tuning Strategy=LoRA, Model Backbone=DeepSeek-7B, Method Components=COGLM2026.010.4405
Claude 3.5 Sonnet + FS*Evaluation Protocol=Few-shot, Model Backbone=Claude 3.5 Sonnet2026.010.4211
DeepSeek V3Evaluation Protocol=Zero-shot, Model Backbone=DeepSeek V32026.010.4016
Claude 3.5 SonnetEvaluation Protocol=Zero-shot, Model Backbone=Claude 3.5 Sonnet2026.010.377
DeepSeek-7BFine-tuning Strategy=LoRA, Model Backbone=DeepSeek-7B2026.010.369
GPT-4o + FS*Evaluation Protocol=Few-shot, Model Backbone=GPT-4o2026.010.3569
DeepSeek V3 + FS*Evaluation Protocol=Few-shot, Model Backbone=DeepSeek V32026.010.3563
Llama 3 (70B) + FS*Evaluation Protocol=Few-shot, Model Backbone=Llama 3 (70B)2026.010.2982
GPT-4oEvaluation Protocol=Zero-shot, Model Backbone=GPT-4o2026.010.2979
Llama 3 (70B)Evaluation Protocol=Zero-shot, Model Backbone=Llama 3 (70B)2026.010.2015