Theory of Mind on ToMBench
81.8AccuracyGPT-o3
Evaluation Results
| Method | Links | |
|---|---|---|
| GPT-o3Model Family=GPT Family, Reasoning Variant=Reasoning2026.02 | 81.8 | |
| GPT-o4-miniModel Family=GPT Family, Reasoning Variant=Non-Reasoning2026.02 | 80.3 | |
| DeepSeek-R1Model Family=DeepSeek Family, Reasoning Variant=Reasoning2026.02 | 80.1 | |
| GPT-4oModel Family=GPT Family, Reasoning Variant=Non-Reasoning2026.02 | 79.7 | |
| Qwen3-32B-ReasoningModel Family=Qwen3-32B, Reasoning Variant=Reasoning2026.02 | 77.5 | |
| DeepSeek-V3Model Family=DeepSeek Family, Reasoning Variant=Non-Reasoning2026.02 | 76.3 | |
| Qwen3-32BModel Family=Qwen3-32B, Reasoning Variant=Non-Reasoning2026.02 | 75.4 | |
| Qwen3-8B-ReasoningModel Family=Qwen3-8B, Reasoning Variant=Reasoning2026.02 | 72.9 | |
| Qwen3-8BModel Family=Qwen3-8B, Reasoning Variant=Non-Reasoning2026.02 | 67.4 |