Gemini 1.5 Flash
Multimodal
Zero-eval
#2XSTest
#2WMT23
#2PhysicsFinals
+5 more
by Google
+
+
+
+
About
Gemini 1.5 Flash was created as a fast and efficient multimodal model, designed to provide quick responses while handling text, images, and other modalities. Built for applications requiring low latency and high throughput, it balances capability with speed to serve real-time and high-volume use cases.
+
+
+
+
Pricing Range
Input (per 1M)$0.15 -$0.15
Output (per 1M)$0.60 -$0.60
Providers1
+
+
+
+
Timeline
AnnouncedMay 1, 2024
ReleasedMay 1, 2024
Knowledge CutoffNov 1, 2023
+
+
+
+
Specifications
Capabilities
Multimodal
+
+
+
+
License & Family
License
Proprietary
Performance Overview
Performance metrics and category breakdown
Overall Performance
22 benchmarks
Average Score
66.8%
Best Score
97.0%
High Performers (80%+)
5Performance Metrics
Max Context Window
1.1MAvg Throughput
150.0 tok/sAvg Latency
0ms+
+
+
+
All Benchmark Results for Gemini 1.5 Flash
Complete list of benchmark scores with detailed information
| XSTest | text | 0.97 | 97.0% | Self-reported | |
| HellaSwag | text | 0.86 | 86.5% | Self-reported | |
| GSM8k | text | 0.86 | 86.2% | Self-reported | |
| BIG-Bench Hard | text | 0.85 | 85.5% | Self-reported | |
| MGSM | text | 0.83 | 82.6% | Self-reported | |
| Natural2Code | text | 0.80 | 79.8% | Self-reported | |
| MMLU | text | 0.79 | 78.9% | Self-reported | |
| MATH | text | 0.78 | 77.9% | Self-reported | |
| Video-MME | multimodal | 0.76 | 76.1% | Self-reported | |
| HumanEval | text | 0.74 | 74.3% | Self-reported |
Showing 1 to 10 of 22 benchmarks
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+