GoogleGemini 2.0Arena #103Dec 11, 2024

Gemini 2.0 Flash

Gemini 2.0 Flash delivers next-gen features and improved capabilities, including superior speed, native tool use, multimodal generation, and a 1M token context window.

Context Window
1.0M
tokens
Max Output
8K
tokens
Released
Dec 11, 2024
Arena Rank
#103
of 305 models
Output Speed
285
tokens/sec
Time to First Token
320ms
TTFT

Capabilities

👁Vision
🧠Reasoning
🔧Tool Calling
⚡Prompt Caching
🖥Computer Use
🎨Image Generation

Pricing Comparison

RouterInput / 1MOutput / 1MCached Input / 1M
Vercel AI$0.10$0.40—
Martian$0.10$0.40—

Benchmarks

Artificial Analysis
Intelligence IndexArtificial Analysis
53/100
Coding IndexArtificial Analysis
44/100
Math IndexArtificial Analysis
58/100
MMLU-PROArtificial Analysis
0.708/1
GPQA DiamondArtificial Analysis
0.518/1
MATH-500Artificial Analysis
0.748/1
AIME 2024Artificial Analysis
0.08/1
LiveCodeBenchArtificial Analysis
0.378/1
SciCodeArtificial Analysis
0.148/1

Model IDs

Tags

implicit-caching
Compare with another model

Related Models

Google#109

Gemini 2.0 Flash Lite

1.0M ctx$0.07/1M in
Google

Gemini 2.0 Flash 001

1.0M ctx$0.10/1M in
Google

Google: Gemini 2.0 Flash Lite

1.0M ctx$0.07/1M in
Google#3

Gemini 3 Pro Preview

1.0M ctx$2.00/1M in
Google#5

Gemini 3 Flash Preview

1.0M ctx$0.50/1M in
Google#16

Gemini 2.5 Pro

1.0M ctx$1.25/1M in
← Back to all models