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 | 1 | 1226 | ±4 | 5.8K | 3.2% | 1.9% | 29 tps | 24.2s | 1M | $2.00 | $12.00 | |
| 2 | 6 | 1150 | ±5 | 8.6K | 2.6% | 1.0% | 6 tps | 1.8s | 1M | $0.50 | $3.00 | |
| 3 | 8 | 1139 | ±4 | 15.1K | 2.6% | 1.4% | 2 tps | 8.9s | 1M | $0.50 | $3.00 | |
| 4 | 13 | 1030 | ±2 | 35.5K | 4.3% | 1.6% | 42 tps | 5.1s | 1M | $1.25 | $10.00 | |
| 5 | 20 | 962 | ±3 | 14K | 3.8% | 1.4% | 82 tps | 5.2s | 1M | $0.30 | $2.50 | |
| 6 | 23 | 933 | ±3 | 80.4K | 2.0% | 1.3% | 80 tps | 5.3s | 1M | $0.30 | $2.50 | |
| 7 | 26 | 900 | ±5 | 40.5K | 2.8% | 12.7% | 74 tps | 0.8s | 1M | $0.15 | $0.60 | |
| 8 | 26 | 898 | ±3 | 22.5K | 3.3% | 0.8% | 129 tps | 2.0s | 1M | $0.10 | $0.40 | |
| 9 | 29 | 891 | ±4 | 18.2K | 4.0% | 0.8% | 88 tps | 3.8s | 1M | $0.10 | $0.40 |