Gemini 2.0 Flash-Lite
Multimodal
Zero-eval
#1MRCR 1M
#1Bird-SQL (dev)
#2CoVoST2
+2 more
by Google
+
+
+
+
About
Gemini 2.0 Flash-Lite is a multimodal language model developed by Google. The model shows competitive results across 13 benchmarks. It excels particularly in MATH (86.8%), FACTS Grounding (83.6%), Global-MMLU-Lite (78.2%). With a 1.1M token context window, it can handle extensive documents and complex multi-turn conversations. The model is available through 1 API provider. As a multimodal model, it can process and understand text, images, and other input formats seamlessly. Released in 2025, it represents Google's latest advancement in AI technology.
+
+
+
+
Pricing Range
Input (per 1M)$0.07 -$0.07
Output (per 1M)$0.30 -$0.30
Providers1
+
+
+
+
Timeline
AnnouncedFeb 5, 2025
ReleasedFeb 5, 2025
Knowledge CutoffJun 1, 2024
+
+
+
+
Specifications
Capabilities
Multimodal
+
+
+
+
License & Family
License
Proprietary
Performance Overview
Performance metrics and category breakdown
Overall Performance
13 benchmarks
Average Score
59.0%
Best Score
86.8%
High Performers (80%+)
2Performance Metrics
Max Context Window
1.1MAvg Throughput
85.0 tok/sAvg Latency
1ms+
+
+
+
All Benchmark Results for Gemini 2.0 Flash-Lite
Complete list of benchmark scores with detailed information
| MATH | text | 0.87 | 86.8% | Self-reported | |
| FACTS Grounding | text | 0.84 | 83.6% | Self-reported | |
| Global-MMLU-Lite | text | 0.78 | 78.2% | Self-reported | |
| MMLU-Pro | text | 0.72 | 71.6% | Self-reported | |
| MMMU | multimodal | 0.68 | 68.0% | Self-reported | |
| EgoSchema | video | 0.67 | 67.2% | Self-reported | |
| MRCR 1M | text | 0.58 | 58.0% | Self-reported | |
| Bird-SQL (dev) | text | 0.57 | 57.4% | Self-reported | |
| HiddenMath | text | 0.55 | 55.3% | Self-reported | |
| GPQA | text | 0.52 | 51.5% | Self-reported |
Showing 1 to 10 of 13 benchmarks