Sky-Chat-3.0: benchmark results
Provider: Other.
Aggregate Rating 1568 ± 29, rank #1431 of 10916 rated models, from 22 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| SuperCLUE General (December 2024) - Liberal Arts | 79.1 | Score | 82.4 |
| SuperCLUE General (March 2025) - Science Reasoning | 63 | Score | 72.9 |
| SuperCLUE General (October 2024) - Liberal Arts | 75.46 | Score | 68.3 |
| SuperCLUE General (December 2024) - Overall | 63 | Score | 60.8 |
| SuperCLUE General (March 2025) - Agent | 38.84 | Score | 60 |
| SuperCLUE General (March 2025) - Text Understanding and Creation | 77.66 | Score | 58.6 |
| SuperCLUE General (March 2025) - Precise Instruction Following | 21.83 | Score | 57.1 |
| SuperCLUE General (December 2024) - Hard | 44.5 | Score | 56.8 |
| SuperCLUE General (December 2024) - Science | 65.4 | Score | 56.8 |
| SuperCLUE General (March 2025) - Overall | 49.17 | Score | 54.3 |
| SuperCLUE General (March 2025) - Math Reasoning | 38.6 | Score | 51.4 |
| SuperCLUE General (October 2024) - Overall | 62.64 | Score | 46.3 |
Interactive version: theaggregate.ai/model?slug=sky-chat-3-0 · How It Works · Data refreshed daily, snapshot 2026-11-08.