List your company

Theory of Mind on ToMBench

81.8AccuracyGPT-o3
66.82470.71274.678.488Feb 11, 2026

Evaluation results

MethodLinks
GPT-o3Model Family=GPT Family, Reasoning Variant=Reasoning2026.0281.8
GPT-o4-miniModel Family=GPT Family, Reasoning Variant=Non-Reasoning2026.0280.3
DeepSeek-R1Model Family=DeepSeek Family, Reasoning Variant=Reasoning2026.0280.1
GPT-4oModel Family=GPT Family, Reasoning Variant=Non-Reasoning2026.0279.7
Qwen3-32B-ReasoningModel Family=Qwen3-32B, Reasoning Variant=Reasoning2026.0277.5
DeepSeek-V3Model Family=DeepSeek Family, Reasoning Variant=Non-Reasoning2026.0276.3
Qwen3-32BModel Family=Qwen3-32B, Reasoning Variant=Non-Reasoning2026.0275.4
Qwen3-8B-ReasoningModel Family=Qwen3-8B, Reasoning Variant=Reasoning2026.0272.9
Qwen3-8BModel Family=Qwen3-8B, Reasoning Variant=Non-Reasoning2026.0267.4