Node Classification on ReasoningFlow manually annotated set (test)
86.5F1 ScoreGemini-3-Flash
Evaluation results
| Method | Links | ||
|---|---|---|---|
| Gemini-3-FlashDecoding strategy=greedy decoding, Segmentation type=ground-truth segmentation2026.06 | 86.5 | 0.82 | |
| Gemini-3.1-ProDecoding strategy=greedy decoding, Segmentation type=ground-truth segmentation2026.06 | 85.9 | 0.812 | |
| GPT-5.1Decoding strategy=greedy decoding, Segmentation type=ground-truth segmentation2026.06 | 83.3 | 0.761 | |
| Gemini-2.5-FlashDecoding strategy=greedy decoding, Segmentation type=ground-truth segmentation2026.06 | 81.1 | 0.749 | |
| GPT-5-miniDecoding strategy=greedy decoding, Segmentation type=ground-truth segmentation2026.06 | 79.2 | 0.741 |