Machine Learning on Timely-Eval
0.939Leaf Classification AccuracyTimelyLM-8B
Evaluation Results
| Method | Links | ||||
|---|---|---|---|---|---|
| TimelyLM-8Bsize=8B2026.01 | 0.939 | 0.744 | 0.761 | 0.84 | |
| DeepSeek-V3.22026.01 | 0.72 | 0.681 | 0.686 | 0.78 | |
| Gemini2.5-provariant=pro2026.01 | 0.714 | 0.654 | 0.746 | 0.751 | |
| GPT-5.1(medium)variant=medium2026.01 | 0.675 | 0.635 | 0.58 | 0.79 | |
| Qwen3-32Bsize=32B2026.01 | 0.518 | 0.501 | 0.59 | 0.572 | |
| Qwen3-14Bsize=14B2026.01 | 0.464 | 0.559 | 0.607 | 0.706 | |
| Qwen3-8Bsize=8B2026.01 | 0.32 | 0.178 | 0.286 | 0.519 |