List your company
ResearchFormerly WizWand

Mathematical Reasoning on OlympiadBench OE_TO_maths_en_COMP

74.04AccuracyQwen3-235B-A22B
-2.493617.375737.24557.1143Dec 30, 2025
Updated 8mo ago

Evaluation results

MethodLinks
Qwen3-235B-A22BModel Category=Large Language Models, Model Scale=235B-A22B, Reasoning Strategy=Thinking2025.1274.04
FIGR2025.1272.4
Qwen3-32BModel Category=Large Language Models, Model Scale=32B, Reasoning Strategy=Thinking2025.1271.96
Text-only RLMode=Text-only, Reasoning Strategy=RL2025.1270.33
GLM-4.5VModel Category=Large Vision-Language Models, Model Scale=108B2025.1270.03
Qwen3-VL-32B-InstructModel Category=Large Vision-Language Models, Model Scale=32B, Reasoning Strategy=Instruct2025.1269.73
Qwen3-VL-8B-InstructModel Category=Large Vision-Language Models, Model Scale=8B, Reasoning Strategy=Instruct2025.1267.21
Qwen3-32BModel Category=Large Language Models, Model Scale=32B, Reasoning Strategy=Non-Thinking2025.1252.08
Bagel-7B-MoTModel Category=Unified Multimodal Models, Model Scale=7B, Reasoning Strategy=MoT2025.1226.11
DeepEyesModel Category=Tool-Augmented Vision-Language Models2025.1213.65
Bagel-Zebra-CoTModel Category=Unified Multimodal Models, Model Scale=7B, Reasoning Strategy=CoT2025.128.46
Chain-of-FocusModel Category=Tool-Augmented Vision-Language Models2025.120.45