Jamba 1.5 Mini
Zero-eval
by AI21 Labs
+
+
+
+
About
Jamba 1.5 Mini was created as a more compact hybrid model, designed to bring the benefits of Jamba's architecture to resource-conscious deployments. Built to provide long-context capabilities with reduced computational requirements, it enables efficient processing of extended inputs in practical applications.
+
+
+
+
Pricing Range
Input (per 1M)$0.20 -$0.20
Output (per 1M)$0.40 -$0.40
Providers2
+
+
+
+
Timeline
AnnouncedAug 22, 2024
ReleasedAug 22, 2024
Knowledge CutoffMar 5, 2024
+
+
+
+
License & Family
License
Jamba Open Model License
Performance Overview
Performance metrics and category breakdown
Overall Performance
8 benchmarks
Average Score
56.1%
Best Score
85.7%
High Performers (80%+)
1Performance Metrics
Max Context Window
512.3KAvg Throughput
100.0 tok/sAvg Latency
0ms+
+
+
+
All Benchmark Results for Jamba 1.5 Mini
Complete list of benchmark scores with detailed information
| ARC-C | text | 0.86 | 85.7% | Self-reported | |
| GSM8k | text | 0.76 | 75.8% | Self-reported | |
| MMLU | text | 0.70 | 69.7% | Self-reported | |
| TruthfulQA | text | 0.54 | 54.1% | Self-reported | |
| Arena Hard | text | 0.46 | 46.1% | Self-reported | |
| MMLU-Pro | text | 0.42 | 42.5% | Self-reported | |
| Wild Bench | text | 0.42 | 42.4% | Self-reported | |
| GPQA | text | 0.32 | 32.3% | Self-reported |
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+