List your company

Language Understanding on MMLU v1 (test)

72.4AccuracyGLM-4-9B
54.30459.00263.768.398Sep 18, 2023Nov 7, 2023Dec 27, 2023Feb 15, 2024Apr 5, 2024May 25, 2024Jul 15, 2024

Evaluation results

MethodLinks
GLM-4-9BInstruction-tuned=true2024.0772.4
Qwen2-7BInstruction-tuned=true2024.0770.5
Yi-1.5-9BInstruction-tuned=true2024.0769.5
Llama-3-8BInstruction-tuned=true2024.0768.4
LLaVA-70BMultimodal-Language Data Mix=true2023.0965.1
LLaMA-2-70B-Chat2023.0963.1
LLaVA-65BMultimodal-Language Data Mix=false2023.0962.6
Vicuna-65B2023.0962.5
LLaVA-65BMultimodal-Language Data Mix=true2023.0962.2
Qwen1.5-7BInstruction-tuned=true2024.0759.5
Vicuna-33B2023.0959
LLaVA-33BMultimodal-Language Data Mix=true2023.0958.6
LLaVA-33BMultimodal-Language Data Mix=false2023.0956.1
Vicuna-13B2023.0955.8
LLaVA-13BMultimodal-Language Data Mix=false2023.0955