Multi-dimensional Performance Evaluation on TimeSage-MT
18.17Numerical AccuracyGLM-5.1
Evaluation Results
| Method | Links | |||||
|---|---|---|---|---|---|---|
| GLM-5.12026.05 | 18.17 | 28.79 | 29.48 | 62.88 | 78.06 | |
| GPT-5.3-Codex2026.05 | 17.7 | 21.18 | 35.14 | 59.45 | 77.79 | |
| Claude-Sonnet-4.62026.05 | 17.68 | 29.94 | 28.75 | 59.38 | 78.51 | |
| Qwen-3.5-122B-A10B2026.05 | 15.75 | 22.77 | 29.89 | 63.93 | 72.89 | |
| MiniMax-M2.72026.05 | 15.54 | 22.28 | 27.87 | 64.08 | 71.74 | |
| Gemini-3-Flash-Preview2026.05 | 15.25 | 16.66 | 31.1 | 52.69 | 72.39 |