Filter model performance by the number of turns in a conversation.
Filter the leaderboard to only show models that have an open license.
Last updated about 1 month ago
| Rank | Overall | Name | VIBE Score | Confidence Interval | Votes | Downvote % | Abort % | Latency | Cost (Image) |
|---|---|---|---|---|---|---|---|---|---|
| 1 | 53 | 844 | ±7 | 9.4K | 8.5% | 1.7% | 62.4s | $0 | |
| 2 | 46 | 904 | ±5 | 15.2K | 6.9% | 2.1% | 76.5s | $0 | |
| 3 | 26 | 1105 | ±3 | 96.6K | 10.0% | 3.5% | 47.8s | $0.01 | |
| 4 | 20 | 1161 | ±2 | 96.3K | 5.9% | 3.6% | 47.5s | $0.04 | |
| 5 | 4 | 1522 | ±3 | 56K | 3.2% | 1.8% | 46.0s | $0.04 |