NEWHow AI models draw the world map · Gecko Tests
Beta
Home/Models/Gemini 2.5 Pro Preview 06-05
Google DeepMind logo

Gemini 2.5 Pro Preview 06-05

by Google DeepMind · Released Jun 2025

Multimodal1M ContextPreview
73.5
avg score
Rank #28
Compare
Better than 91% of all models
Context
1.0M tokens (~524 books)
Input $/1M
$1.25
Output $/1M
$10.00
Type
multimodal
License
Proprietary
Benchmarks
4 tested
Data as of
About

Gemini 2.5 Pro is Google’s state-of-the-art AI model designed for advanced reasoning, coding, mathematics, and scientific tasks. It employs “thinking” capabilities, enabling it to reason through responses with enhanced accuracy...

Tested on 4 benchmarks · BenchGecko score 73.5. Top scores: Aider polyglot (83.1%), TutorBench (55.6%), VISTA (54.6%).

Looking for similar performance at lower cost?
gpt-oss-120b (free) scores 74.2 (101% as good) at $0.00/1M input · 100% cheaper
Capabilities
coding
83.1
#3 globally
knowledge
55.1
#90 globally
agentic
10.1
#57 globally
Benchmark Scores
Compare All
Tested on 4 benchmarks · Ranked across 3 categories
Score Distribution (all 312 models)
0255075100
▲ You are here
codingCompare coding →
Aider polyglot

Multi-language code editing from Aider. Tests editing ability across Python, JavaScript, TypeScript, Java, C++, Go, Rust, and more.

83.1·
knowledgeCompare knowledge →
TutorBench

SEAL TutorBench. Evaluates ability to explain concepts clearly for educational purposes.

55.6·
VISTA

SEAL VISTA. Visual question answering and image understanding benchmark.

54.6·
agenticCompare agentic →
SWE-Bench Pro (Private)

SEAL SWE-bench Pro (Private). Harder private set of software engineering tasks.

10.1·
Quick compare:vs Muse SparkDeepSeek logovs DeepSeek R1 Distill Qwen 14Bnousresearch logovs Hermes 3 70B Instruct
Excellent (85+) Good (70-85) Average (50-70) Below (<50)
Model Family · Google DeepMind Gemini 2.5 Pro
Jun 2025
58.7
$1.25/M in1.0Mctx50 benchmarks
Jun 2025
$0.63/M in(-0.63)1.0Mctx
May 2025
$1.25/M in(+0.63)1.0Mctx1 benchmark
Jun 2025
73.5+14.8
$1.25/M in1.0Mctx4 benchmarks
See the full Gemini 2.5 Pro family →
Similar Models
Muse Spark
Unknown
73.3n/a
DeepSeek logo
DeepSeek R1 Distill Qwen 14B
DeepSeek
73.7n/a
nousresearch logo
Hermes 3 70B Instruct
nousresearch
73.2$0.70/1M
Links
Info
Google DeepMindPricing explorerDevelopers · API
Research
Technical Report
Documentation
API DocsPlayground
Community
@Google DeepMind
BenchGecko API
gemini-2-5-pro-preview
Specifications
  • Typemultimodal
  • Context1.0M tokens (~524 books)
  • ReleasedJun 2025
  • LicenseProprietary
  • Statuspreview
  • Cost / Message~$0.013
Available On
Google DeepMind logoGoogle DeepMind$1.25
Categories
codingknowledgeagentic
Learn More
context-windowtransformertokens
Share & Export
Tweet
Related Models
Muse Spark
73.3
DeepSeek logoDeepSeek R1 Distill Qwen 14B
73.7
nousresearch logoHermes 3 70B Instruct
73.2
OpenAI logogpt-oss-120b (free)
74.2
Gemini 2.5 Pro Preview 06-05 is a proprietary multimodal AI model by Google DeepMind, released in June 2025. It has an average benchmark score of 73.5. Context window: 1M tokens.

Related Models

Muse Spark · UnknownDeepSeek R1 Distill Qwen 14B · DeepSeekHermes 3 70B Instruct · nousresearchgpt-oss-120b (free) · OpenAIMiniMax M2 · minimax

Benchmarks

Aider polyglotTutorBenchVISTASWE-Bench Pro (Private)

Related Pages

Google DeepMind · ProviderGoogle DeepMind · EconomyAll ModelsCompare ModelsPricingDevelopers · APIContext Window · Glossary

Key facts · as of 2026-10-05

  • Gemini 2.5 Pro Preview 06-05 by Google DeepMind. BenchGecko score 73.5, rank 28 of 312 scored models (normalized average of public benchmark scores).
  • List price $1.25 input · $10.00 output per 1M tokens (as of 2026-10-05).
  • Sold by 7 providers (as of 2026-10-05): Google AI Studio $0.63 in / $5.00 out · Google $1.25 in / $10.00 out · Google $1.25 in / $10.00 out · Google $1.25 in / $10.00 out · Google AI Studio $1.25 in / $10.00 out · and 2 more. Every provider

How to cite · data as of 2026-10-05

Gemini 2.5 Pro Preview 06-05 · benchmarks, pricing and providers. BenchGecko, data as of 2026-10-05. https://benchgecko.ai/model/gemini-2-5-pro-preview

Credit "Source: BenchGecko" with a link. Prices per provider and Gecko Tests are BenchGecko data (CC BY 4.0); benchmark scores keep their original source, listed in the JSON. JSON · llms.txt · MCP