讯飞星火V2.0: benchmark results
Provider: Other.
Aggregate Rating 1389 ± 43, rank #6571 of 10916 rated models, from 7 benchmark results.
Strongest benchmark results
| Benchmark | Score | Metric | Percentile |
|---|---|---|---|
| SuperCLUE-Agent (October 2023) - Task Planning | 39.19 | Score | 50 |
| SuperCLUE-Agent (October 2023) - Tool Use | 48.12 | Score | 38.9 |
| SuperCLUE General (October 2023) - Open-Ended Questions (OPEN) | 47.95 | Score | 35 |
| SuperCLUE-Agent (October 2023) - Overall | 41.95 | Score | 33.3 |
| SuperCLUE-Agent (October 2023) - Long & Short-term Memory | 36.58 | Score | 27.8 |
| SuperCLUE General (October 2023) - Overall | 55.24 | Score | 25 |
| SuperCLUE General (October 2023) - Objective Questions (OPT) | 66.18 | Score | 20 |
Interactive version: theaggregate.ai/model?slug=v2-0 · How It Works · Data refreshed daily, snapshot 2026-11-08.