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 | 2 | 1213 | ±4 | 20.2K | 2.4% | 4.1% | 63 tps | 12.2s | 400K | $1.25 | $10.00 | |
| 2 | 6 | 1146 | ±5 | 7.8K | 2.4% | 1.5% | 73 tps | 2.4s | 400K | $1.25 | $10.00 | |
| 3 | 10 | 1109 | ±3 | 9.9K | 7.2% | 4.5% | 51 tps | 23.7s | 400K | $1.25 | $10.00 | |
| 4 | 12 | 1076 | ±4 | 16.1K | 2.9% | 8.3% | 5 tps | 34.6s | 400K | $1.75 | $14.00 | |
| 5 | 17 | 999 | ±3 | 7.1K | 3.7% | 3.4% | 35 tps | 5.1s | 128K | $2.00 | $8.00 | |
| 6 | 18 | 990 | ±4 | 12.7K | 3.0% | 1.6% | 68 tps | 4.8s | 400K | $0.25 | $2.00 | |
| 7 | 19 | 983 | ±3 | 17.2K | 3.0% | 6.0% | 65 tps | 8.7s | 400K | $0.25 | $2.00 | |
| 8 | 20 | 960 | ±5 | 7.9K | 3.5% | 2.2% | 50 tps | 4.6s | 128K | $1.10 | $4.40 | |
| 9 | 23 | 930 | ±4 | 16K | 3.5% | 11.1% | 56 tps | 16.0s | 400K | $1.25 | $10.00 | |
| 10 | 29 | 892 | ±3 | 10.8K | 3.6% | 1.1% | 53 tps | 2.4s | 128K | $3.00 | $12.00 | |
| 11 | 32 | 877 | ±5 | 60.8K | 2.4% | 0.8% | 49 tps | 3.4s | 128K | $2.50 | $10.00 | |
| 12 | 32 | 874 | ±4 | 62.4K | 2.4% | 0.6% | 86 tps | 2.2s | 128K | $0.15 | $0.60 | |
| 13 | 34 | 844 | ±4 | 10.6K | 3.6% | 0.5% | 71 tps | 1.4s | 128K | $0.25 | $2.00 | |
| 14 | 35 | 694 | ±7 | 7.3K | 4.9% | 23.6% | 55 tps | 21.1s | 400K | $0.25 | $2.00 |