Emotional Understanding on STEU
90.91AccuracyClaude 3.7 Sonnet
Evaluation Results
| Method | Links | |
|---|---|---|
| Claude 3.7 SonnetMemory Condition=No Memory2025.10 | 90.91 | |
| Claude 3.5 SonnetMemory Condition=No Memory2025.10 | 84.85 | |
| DeepSeek-R1Memory Condition=No Memory2025.10 | 84.85 | |
| Llama 3.2 90BMemory Condition=No Memory2025.10 | 84.85 | |
| Claude 3.5 SonnetMemory Condition=Advantaged2025.10 | 83.33 | |
| Claude 3.5 SonnetMemory Condition=Disadvantaged2025.10 | 82.03 | |
| DeepSeek-R1Memory Condition=Advantaged2025.10 | 81.62 | |
| Claude 3.7 SonnetMemory Condition=Advantaged2025.10 | 80.1 | |
| Llama 3.1 405BMemory Condition=No Memory2025.10 | 78.79 | |
| Llama 4 MaverickMemory Condition=No Memory2025.10 | 78.55 | |
| Claude 3.7 SonnetMemory Condition=Disadvantaged2025.10 | 77.37 | |
| DeepSeek-R1Memory Condition=Disadvantaged2025.10 | 76.57 | |
| Llama 4 MaverickMemory Condition=Advantaged2025.10 | 75.96 | |
| Qwen3 4BMemory Condition=Disadvantaged2025.10 | 75.58 | |
| Qwen3 4BMemory Condition=Advantaged2025.10 | 74.81 | |
| Ministral-8B-Instruct-2410Memory Condition=Disadvantaged2025.10 | 73.84 | |
| Ministral-8B-Instruct-2410Memory Condition=No Memory2025.10 | 72.73 | |
| Ministral-8B-Instruct-2410Memory Condition=Advantaged2025.10 | 72.73 | |
| Qwen3 4BMemory Condition=No Memory2025.10 | 72.73 | |
| Llama 4 MaverickMemory Condition=Disadvantaged2025.10 | 70.81 | |
| GPT-OSS 20BMemory Condition=Advantaged2025.10 | 69.92 | |
| DeepSeek-V3Memory Condition=No Memory2025.10 | 69.7 | |
| GPT-OSS 20BMemory Condition=Disadvantaged2025.10 | 69.49 | |
| Claude 3.5 HaikuMemory Condition=No Memory2025.10 | 69.05 | |
| DeepSeek-V3Memory Condition=Advantaged2025.10 | 68.99 | |
| DeepSeek-V3Memory Condition=Disadvantaged2025.10 | 68.18 | |
| Claude 3.5 HaikuMemory Condition=Disadvantaged2025.10 | 67.89 | |
| Claude 3.5 HaikuMemory Condition=Advantaged2025.10 | 67.47 | |
| Phi4 reasoningMemory Condition=Advantaged2025.10 | 66.97 | |
| Phi4 reasoningMemory Condition=No Memory2025.10 | 66.67 | |
| Phi4 reasoningMemory Condition=Disadvantaged2025.10 | 66.26 | |
| Qwen2.5 7BMemory Condition=Disadvantaged2025.10 | 65.56 | |
| Llama 3.2 90BMemory Condition=Advantaged2025.10 | 64.91 | |
| Llama 3.1 405BMemory Condition=Advantaged2025.10 | 64.42 | |
| GPT-OSS 20BMemory Condition=No Memory2025.10 | 63.64 | |
| Command RMemory Condition=No Memory2025.10 | 63.64 | |
| Qwen2.5 7BMemory Condition=No Memory2025.10 | 63.64 | |
| Llama 3.1 405BMemory Condition=Disadvantaged2025.10 | 62.31 | |
| Llama 3.2 90BMemory Condition=Disadvantaged2025.10 | 62.24 | |
| Command RMemory Condition=Advantaged2025.10 | 60.91 | |
| Command RMemory Condition=Disadvantaged2025.10 | 60.36 | |
| Qwen2.5 7BMemory Condition=Advantaged2025.10 | 58.69 | |
| Phi-4-mini-instructMemory Condition=No Memory2025.10 | 54.55 | |
| Phi-4-mini-instructMemory Condition=Disadvantaged2025.10 | 54.23 | |
| Phi-4-mini-instructMemory Condition=Advantaged2025.10 | 54.08 |