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

Mathematics on MATH (Accuracy)

95.1MATH Accuracy

Qwen 3 VL 32B Instruct

Updated 6d ago

Evaluation Results

Method	Links
Qwen 3 VL 32B Instruct 2025.12		95.1
Qwen3-VL 2026.01		94.6
Olmo 3.1 32B Instruct 2025.12		93.4
POES 2026.04		92.7
POES 2026.04		92.2
Anchor 2026.04		91.9
Random 2026.04		91.7
POES 2026.04		91.5
Anchor 2026.04		91.5
Anchor 2026.04		91.3
IPOMP 2026.04		91.2
Prediction 2026.04		90.8
Prediction 2026.04		90.8
Random 2026.04		90.7
SESS 2026.04		90.7
SESS 2026.04		90.5
Ministral 3 2026.01		90.4
Random 2026.04		90.3
SESS 2026.04		90.2
IPOMP 2026.04		90.1
Qwen3-VL 2026.01		90
POES 2026.04		90
Prediction 2026.04		89.8
IPOMP 2026.04		89.4
Ministral 3 2026.01		87.6
Gemma 3 27B 2025.12		87.4
Gemma 3 27B 2026.02		87.4
Qwen3 2026.01		87
Olmo 3.1 32B Instruct 2025.12		86.6
DictaLM 3.0 24B-Think 2026.02		86.41
Gemma3 2026.01		85.4
LLaDA2.1-mini 2026.04		84.56
Qwen 3 32B 2025.12		84.3
Ministral 3 2026.01		83
LLaDA2.0-mini 2026.04		81.5
Qwen 2.5 32B 2025.12		80.2
Qwen3-VL 2026.01		78.6
SDAR-8B-Chat 2026.04		78.4
JoyAI-LLM Flash-Base 2026.04		78.1
Random 2026.04		77.5
IPOMP 2026.04		76.7
Gemma3 2026.01		75.9
Fine-tuned 2026.05		75.3
Zero-shot 2026.05		75
Qwen3-14B 2026.04		74.7
Olmo 3.1 32B Instruct 2025.12		74.4
FREE-Merging 2026.05		74.2
DiDi-Merg.-L 2026.05		74
Anchor 2026.04		73.5
XekRung-8B 2026.04		73.5
Twin-Merging 2026.05		72.1
SESS 2026.04		72
Prediction 2026.04		72
POES 2026.04		71.5
SESS 2026.04		71.3
Qwen3-8B 2026.04		71.05
Random 2026.04		70.8
POES 2026.04		70.3
Llama-3.3-70B-Instruct 2026.04		69.55
SESS 2026.04		69.5
Random 2026.04		69
Prediction 2026.04		68.8
SDAR-30B-A3B 2026.04		68.56
Anchor 2026.04		68.5
IPOMP 2026.04		68.2
Mistral Small 3.1 2026.02		67.93
IPOMP 2026.04		67.7
Qwen3.5-9B 2026.04		66.9
Anchor 2026.04		66.7
Yuan3.0-1T Base 2026.01		66.1
Prediction 2026.04		63
SKillWeave (Ours) 2026.05		62.5
SkillWeave (Delta-Come replacement) 2026.05		62.4
DeepSeek-V3-Base 2026.01		61.6
SkillWeave (ASVD replacement) 2026.05		60.5
Twin-Merging r1024 2026.05		60.4
Qwen3-30B-A3B-Base 2026.04		59.6
EMR-Merging 2026.05		59.4
Twin-Merging r512 2026.05		59.3
TALL-Mask 2026.05		58.9
FuseChat3.0 2026.05		57.2
PCB-Merge+DARE 2026.05		57
PCB-Merging 2026.05		56.7
Ties-Merging 2026.05		56.3
Fine-tuned 2026.05		56.2
Qwen3.5-35B-A3B-Base 2026.04		56
Qwen2.5-14B 2026.05		55.6
DiDi-Merg.-L 2026.05		55.3
Twin-Merging 2026.05		55.2
FREE-Merging 2026.05		55
Routed LoRA r1024 2026.05		54.6
Gemma2-27B-it 2026.05		54.4
SkillWeave (Self-Rewarding replacement) 2026.05		54.4
Jointly MTL 2026.05		53.7
FuseLLM 2026.05		52.9
Task Arithmetic 2026.05		52.4
Sequentially MTL 2026.05		52.1
Llama-3.1-8B-Instruct 2026.04		51.9
Llama3.1-8B-Instruct 2026.05		51.9
Gemma 2 27B 2025.12		51.5

Showing 100 of 136 rows