Share your thoughts, 1 month free Claude Pro on usSee more

Question Answering on MMLU

88.7Accuracy

Qwen 3 VL 32B Instruct

Updated 1mo ago

Evaluation Results

Method	Links
Qwen 3 VL 32B Instruct 2025.12		88.7
GPT-4 2023.11		86.5
Qwen 3 32B 2025.12		85.8
Qwen 2.5 32B 2025.12		84.6
Qwen 3 VL 8B Inst 2025.12		83.6
Olmo 3.1 32B Instruct 2025.12		81.9
Olmo 3.1 32B Instruct 2025.12		80.9
Qwen 3 8B 2025.12		80.4
Olmo 3.1 32B Instruct 2025.12		79
Qwen 2.5 7B 2025.12		77.2
OLMo 2 32B 2025.12		77.1
Gemma 2 27B 2025.12		76.1
Gemma 3 27B 2025.12		74.6
Falcon 2023.11		70.6
Falcon-180B 2023.11		70.6
Mixtral 8x7B 2024.01		70.6
Apertus 70B 2025.12		70.2
GPT-3.5 2023.11		70
GPT-3.5 2024.01		70
LLaMA 2 70B 2024.01		69.9
PaLM 2023.11		69.3
Olmo 3 7B Instruct 2025.12		69.1
Olmo 3 7B Instruct 2025.12		69.1
LLaMA-2 2023.11		68.9
RCO 2025.06		67.74
LLaMA-3-70B-Instruct 2025.06		67.39
Olmo 3 7B Instruct 2025.12		67.1
LLaDA-8B-Instruct 2026.01		65.4
CE Only 2026.01		65.1
RCO 2025.06		64.42
CTC+CE 2026.01		64.1
Granite 3.3 8B Inst 2025.12		63.5
RCO 2025.06		63.17
Apertus 8B Inst 2025.12		62.7
LLaMA-2 2023.11		62.6
RCO 2025.06		62.48
OLMo 2 7B Inst 2025.12		61.6
DPCO 2025.06		60.46
RCO 2025.06		60.37
DPCO 2025.06		60.03
LLAMA-2-70B-Chat 2025.06		60.02
DPCO 2025.06		59.42
LLaMA-3-8B-Instruct 2025.06		59.41
DPCO 2025.06		59.21
DPCO 2025.06		58.47
LLaMA-2-13B-Chat 2025.06		57.33
UltraCM-13B 2025.06		57.19
Falcon 2023.11		57
LLaMA-2-7B-Chat 2025.06		56.96
STABLEPROMPT 2026.02		55.8
GFLOWPO 2026.02		55.6
LLaMA-2 2023.11		54.8
Self-refinement 2025.06		54.79
ProTEGI 2026.02		53.5
Auto-J-13B 2025.06		52.9
Aligner 2025.06		52.56
Initial Answer 2025.06		52.48
APE 2026.02		52.1
LLaMA-2 2023.11		45.3
OLTQA 2023.05		36.14
UnifiedQA 2023.05		28.77
Falcon 2023.11		28