← Back to all models
G

Gemini 2.5 Flash

by Google DeepMind
Efficient Paid API Multimodal 🏆 Ranked #22 of 85
81.7
Overall Score
out of 100
About

Google DeepMind's latest fast multimodal model with strong reasoning and a 1 million token context window. Bridges the gap between Flash speed and Pro capability, with thinking mode for harder tasks.

Key Metrics
Context Window
1.0M
tokens
Avg Response
540
milliseconds
Input Cost
$0.15
per million tokens
Output Cost
$0.6
per million tokens
Arena ELO
1300
Chatbot Arena rating
MT-Bench
9.0
out of 10
Benchmark Scores
MMLU
86.0%
HumanEval
89.0%
MATH
84.0%
GPQA
62.0%
MT-Bench
90.0/10
Capability Profile
Strengths & Limitations
Strengths
✓ Fast and capable ✓ Low cost ✓ Thinking mode ✓ Multimodal ✓ Large context
Limitations
⚠ Below Pro on hardest tasks ⚠ Newer model with less community data
Ideal Use Cases
Agentic workflows Chatbots Code assistance Document analysis Rapid prototyping
Model Details
Provider Google DeepMind
Released 2025-05-20
Type Paid API
Multimodal Yes
Tier Efficient
Global rank #22 / 85
Pricing (USD)
Input tokens $0.15/M
Output tokens $0.6/M
Per 1,000 tokens ≈ $0.0001 input / $0.0006 output
All Benchmarks
MMLU 86.0%
HumanEval 89.0%
MATH 84.0%
GPQA 62.0%
MT-Bench 9.0/10
Arena ELO 1300
Compare this model View Rankings

You might also consider