Gemini 2.0 Flash
Multimodal
Zero-eval
#1Natural2Code
#1HiddenMath
#1CoVoST2
+2 more
by Google
About
Gemini 2.0 Flash is a multimodal language model developed by Google. It achieves strong performance with an average score of 66.7% across 13 benchmarks. It excels particularly in Natural2Code (92.9%), MATH (89.7%), FACTS Grounding (83.6%). 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 2024, it represents Google's latest advancement in AI technology.
Pricing Range
Input (per 1M)$0.10 -$0.10
Output (per 1M)$0.40 -$0.40
Providers1
Timeline
AnnouncedDec 1, 2024
ReleasedDec 1, 2024
Knowledge CutoffAug 1, 2024
Specifications
Capabilities
Multimodal
License & Family
License
Proprietary
Benchmark Performance Overview
Performance metrics and category breakdown
Overall Performance
13 benchmarks
Average Score
66.7%
Best Score
92.9%
High Performers (80%+)
3Performance Metrics
Max Context Window
1.1MAvg Throughput
183.0 tok/sAvg Latency
0msTop Categories
factuality
83.6%
math
76.4%
vision
70.7%
general
62.6%
code
61.4%
Benchmark Performance
Top benchmark scores with normalized values (0-100%)
Ranking Across Benchmarks
Position relative to other models on each benchmark
Natural2Code
Rank #1 of 8
#1Gemini 2.0 Flash
92.9%
#2Gemini 1.5 Pro
85.4%
#3Gemma 3 27B
84.5%
#4Gemma 3 12B
80.7%
MATH
Rank #3 of 63
#1o1
96.4%
#2o3-mini
97.9%
#3Gemini 2.0 Flash
89.7%
#4Gemma 3 27B
89.0%
#5Gemini 2.0 Flash-Lite
86.8%
#6Gemini 1.5 Pro
86.5%
FACTS Grounding
Rank #4 of 9
#1Gemini 2.5 Flash-Lite
84.1%
#2Gemini 2.5 Flash
85.3%
#3Gemini 2.5 Pro Preview 06-05
87.8%
#4Gemini 2.0 Flash
83.6%
#5Gemini 2.0 Flash-Lite
83.6%
#6Gemma 3 12B
75.8%
#7Gemma 3 27B
74.9%
MMLU-Pro
Rank #8 of 60
#5Claude 3.5 Sonnet
77.6%
#6Llama 4 Maverick
80.5%
#7Kimi K2 Instruct
81.1%
#8Gemini 2.0 Flash
76.4%
#9Claude 3.5 Sonnet
76.1%
#10Phi 4 Reasoning Plus
76.0%
#11DeepSeek-V3
75.9%
EgoSchema
Rank #5 of 9
#2Nova Pro
72.1%
#3GPT-4o
72.2%
#4Qwen2.5 VL 72B Instruct
76.2%
#5Gemini 2.0 Flash
71.5%
#6Nova Lite
71.4%
#7Qwen2.5-Omni-7B
68.6%
#8Gemini 2.0 Flash-Lite
67.2%
All Benchmark Results for Gemini 2.0 Flash
Complete list of benchmark scores with detailed information
Natural2Code Natural2Code benchmark | code | text | 0.93 | 92.9% | Self-reported |
MATH MATH benchmark | math | text | 0.90 | 89.7% | Self-reported |
FACTS Grounding FACTS Grounding benchmark | factuality | text | 0.84 | 83.6% | Self-reported |
MMLU-Pro MMLU-Pro benchmark | general | text | 0.76 | 76.4% | Self-reported |
EgoSchema EgoSchema benchmark | general | text | 0.71 | 71.5% | Self-reported |
MMMU MMMU benchmark | vision | multimodal | 0.71 | 70.7% | Self-reported |
MRCR MRCR benchmark | general | text | 0.69 | 69.2% | Self-reported |
HiddenMath HiddenMath benchmark | math | text | 0.63 | 63.0% | Self-reported |
GPQA GPQA benchmark | general | text | 0.62 | 62.1% | Self-reported |
Bird-SQL (dev) Bird-SQL (dev) benchmark | general | text | 0.57 | 56.9% | Self-reported |
Showing 1 to 10 of 13 benchmarks
Resources