Data Analysis on DABStep easy
83.33AccuracyClaude Sonnet 4.5
Evaluation Results
| Method | Links | |
|---|---|---|
| Claude Sonnet 4.5Model Type=Proprietary2026.01 | 83.33 | |
| Claude Sonnet 4Model Type=Proprietary2026.01 | 81.94 | |
| Kimi K2 InstructModel Type=Open-sourced2026.01 | 77.78 | |
| Deepseek-v3.1Model Type=Open-sourced2026.01 | 76.39 | |
| GPT-5Reasoning effort=medium, Model Type=Proprietary2026.01 | 75 | |
| Qwen3-Coder 480BModel Type=Open-sourced2026.01 | 75 | |
| GPT-5.1Reasoning effort=high, Model Type=Proprietary2026.01 | 73.61 | |
| GPT-4oModel Type=Proprietary2026.01 | 73.61 | |
| Qwen3 235B InstructModel Type=Open-sourced2026.01 | 73.61 | |
| GPT-5.1Reasoning effort=none, Model Type=Proprietary2026.01 | 70.83 | |
| GPT-OSS-120BModel Type=Open-sourced2026.01 | 70.83 | |
| Qwen3-4B-InstructModel Type=Open-sourced2026.01 | 58.33 | |
| Qwen2.5-7B-InstructModel Type=Open-sourced2026.01 | 47.22 |