TeleChat2-Large: benchmark results
Provider: Other.
Aggregate Rating 1579 ± 29, rank #1266 of 10916 rated models, from 12 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| SuperCLUE General (December 2024) - Liberal Arts | 79.5 | Score | 86.5 |
| SuperCLUE-Agent - Long & Short-term Memory | 80.43 | Score | 80 |
| SuperCLUE-Agent - Overall | 74.48 | Score | 80 |
| SuperCLUE General (October 2024) - Hard | 44.28 | Score | 73.2 |
| SuperCLUE General (October 2024) - Liberal Arts | 75.54 | Score | 70.7 |
| SuperCLUE-Agent - Task Planning | 71.86 | Score | 70 |
| SuperCLUE-Agent - Tool Use | 71.94 | Score | 70 |
| SuperCLUE General (October 2024) - Overall | 66.23 | Score | 58.5 |
| SuperCLUE General (October 2024) - Science | 78.85 | Score | 53.7 |
| SuperCLUE General (December 2024) - Overall | 62.3 | Score | 52.7 |
| SuperCLUE General (December 2024) - Hard | 43.3 | Score | 51.4 |
| SuperCLUE General (December 2024) - Science | 64.1 | Score | 48.6 |
Interactive version: theaggregate.ai/model?slug=telechat2-large · How It Works · Data refreshed daily, snapshot 2026-11-08.