Our new X account is live! Follow @wizwand_team for updates

Compositional Generalization on Evaluation Dataset (Full)

0.6379Score

Gemma-7B + COGLM

Updated 4d ago

Evaluation Results

Method	Links
Gemma-7B + COGLM 2026.01		0.6379
Mistral-7B + COGLM 2026.01		0.6206
LLaMA-3-8B + COGLM 2026.01		0.6075
Qwen2.5-7B + COGLM 2026.01		0.6006
Mistral-7B 2026.01		0.5963
Gemma-7B 2026.01		0.5937
Qwen2.5-7B 2026.01		0.5906
LLaMA-3-8B 2026.01		0.5668
DeepSeek-7B + COGLM 2026.01		0.4405
Claude 3.5 Sonnet + FS* 2026.01		0.4211
DeepSeek V3 2026.01		0.4016
Claude 3.5 Sonnet 2026.01		0.377
DeepSeek-7B 2026.01		0.369
GPT-4o + FS* 2026.01		0.3569
DeepSeek V3 + FS* 2026.01		0.3563
Llama 3 (70B) + FS* 2026.01		0.2982
GPT-4o 2026.01		0.2979
Llama 3 (70B) 2026.01		0.2015