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 % | Speed | Latency | Context | Cost (Input) | Cost (Output) |
|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 1 | 3 | 1185 | ±4 | 11.4K | 2.6% | 1.3% | 48 tps | 1.3s | 200K | $5.00 | $25.00 | |
| 2 | 4 | 1175 | ±4 | 12.3K | 6.5% | 1.9% | 41 tps | 1.4s | 200K | $3.00 | $15.00 | |
| 3 | 4 | 1172 | ±5 | 7.2K | 2.2% | 1.7% | 46 tps | 3.4s | 200K | $5.00 | $25.00 | |
| 4 | 9 | 1123 | ±5 | 6.9K | 6.4% | 1.4% | 38 tps | 3.7s | 200K | $3.00 | $15.00 | |
| 5 | 13 | 1034 | ±4 | 12.9K | 4.5% | 1.5% | 46 tps | 1.5s | 200K | $3.00 | $15.00 | |
| 6 | 16 | 1021 | ±4 | 17.5K | 2.9% | 1.3% | 42 tps | 1.9s | 200K | $3.00 | $15.00 |