Google DeepMind

Gemini 2.5 Flash

Multimodal

by Google DeepMind

+
+
+
+
About

Gemini 2.5 Flash, released by Google in June 2025, applies the multimodal and reasoning architecture of Gemini 2.5 in a faster, more cost-efficient form factor. It targets high-throughput production use cases where the full Gemini 2.5 Pro would be unnecessarily expensive — designed for the large segment of API applications where speed and cost per call matter as much as peak accuracy on demanding benchmarks.

+
+
+
+
Pricing Range
Input (per 1M)$0.15 -$0.15
Output (per 1M)$0.60 -$0.60
Providers2
+
+
+
+
Timeline
ReleasedApr 17, 2025
+
+
+
+
Specifications
Capabilities
Multimodal
+
+
+
+
License & Family
License
Proprietary
Performance Overview
Performance metrics and category breakdown

Overall Performance

4 benchmarks
Average Score
4.2%
Best Score
12.1%
High Performers (80%+)
0

Performance Metrics

Max Context Window
1.0M

Top Categories

Reasoning
12.1%
Tool Use
3.4%
Agents
2.5%
Multimodal
-1.0%
+
+
+
+
All Benchmark Results for Gemini 2.5 Flash
Complete list of benchmark scores with detailed information
Humanity's Last Exam
Reasoning
12.08
12.1%
Unverified
MCP-Atlas
Tool Use
3.40
3.4%
Unverified
BrowseComp
Agents
2.50
2.5%
Unverified
MMMU
Multimodal
-1.00
-1.0%
Unverified