Google model product
Gemini 2.5 Pro
5 Pro is Google's latest preview reasoning model with multimodal understanding and a 1M token context window.
Updated Sep 8, 2026. Default version: Gemini 2.5 Pro Preview 06-05
LLMBoard Score49.3Gemini 2.5 Pro Preview 06-05
Coverage40%13 benchmark families
Context window1MTokens
Official input price$1.25Google API
Gemini 2.5 Pro Capability Profile
This profile uses the model's current scored version. Arena ratings and prices are shown separately.
Gemini 2.5 Pro Benchmark Results
Benchmark scores for Gemini 2.5 Pro Preview 06-05.
Sort by
Benchmark | Score | Rank | Participants | Percentile | Evidence | Evaluated |
|---|
| BenchmarkFACTS Grounding | Score87.80% | Rank01 | Participants13 | Percentile100.00% | EvidenceC | Evaluated |
| BenchmarkGlobal-MMLU-Lite | Score89.20% | Rank01 | Participants15 | Percentile100.00% | EvidenceC | Evaluated |
| BenchmarkVibe-Eval | Score67.20% | Rank01 | Participants8 | Percentile100.00% | EvidenceC | Evaluated |
| BenchmarkAider-Polyglot | Score82.20% | Rank02 | Participants22 | Percentile95.24% | EvidenceC | Evaluated |
| BenchmarkMMMU | Score82.00% | Rank10 | Participants64 | Percentile85.71% | EvidenceC | Evaluated |
| BenchmarkSimpleQA | Score54.00% | Rank12 | Participants47 | Percentile76.09% | EvidenceC | Evaluated |
| BenchmarkVideoMMMU | Score83.60% | Rank12 | Participants26 | Percentile56.00% | EvidenceC | Evaluated |
| BenchmarkMRCR v2 (8-needle) | Score16.40% | Rank23 | Participants24 | Percentile4.35% | EvidenceC | Evaluated |
| BenchmarkLiveCodeBench | Score69.00% | Rank25 | Participants75 | Percentile67.57% | EvidenceC | Evaluated |
| BenchmarkGPQA | Score86.40% | Rank53 | Participants247 | Percentile78.86% | EvidenceC | Evaluated |
| BenchmarkAIME 2025 | Score88.00% | Rank54 | Participants119 | Percentile55.08% | EvidenceC | Evaluated |
| BenchmarkHumanity's Last Exam | Score21.60% | Rank66 | Participants103 | Percentile36.27% | EvidenceC | Evaluated |
| BenchmarkSWE-Bench Verified | Score67.20% | Rank75 | Participants113 | Percentile33.93% | EvidenceC | Evaluated |
Gemini 2.5 Pro Arena Results
Preference and agent-evaluation results for the default version.
No Arena results
The default version does not have a matching Arena result yet.
Gemini 2.5 Pro Pricing
Official vendor API pricing appears first, followed by individual provider offers.
- Official API
- $1.25 input, $10 output per 1M
- Official provider
- Lowest third-party
- From $1.13 input, $9 output per 1M via Jiekou.AI
- Tracked offerings
- 4
Sort by
Provider | Provider model ID | Region | Input / 1M | Output / 1M | Context | Updated |
|---|
| ProviderJiekou.AI | Provider model IDgemini-2.5-pro-preview-06-05 | Regionglobal | Input / 1M$1.13 | Output / 1M$9 | Context1M | Updated |
| ProviderOpenRouter | Provider model IDgoogle/gemini-2.5-pro-preview | Regionglobal | Input / 1M$1.25 | Output / 1M$10 | Context1M | Updated |
| ProviderNanoGPT | Provider model IDgemini-2.5-pro-preview-06-05 | Regionglobal | Input / 1M$2.5 | Output / 1M$10 | Context1M | Updated |
Official prices use only the vendor's configured official Provider and positive standard USD PAYG rates. Third-party offers remain explicitly labeled.
Gemini 2.5 Pro Runtime Performance
Provider-specific output speed and catalog latency for Gemini 2.5 Pro Preview 06-05. Runtime does not affect the capability score.
Sort by
Provider | Output Speed | Catalog Latency | Max Input | Max Output | Updated |
|---|
| ProviderGoogle | Output Speed85.00 tok/s | Catalog Latency0.70 s | Max Input1M | Max Output65.5K | Updated |
Output Speed is generated output tokens received per second. Catalog latency is reported separately from observed provider TTFT.
Gemini 2.5 Pro Specifications
Technical details for the model's default version.
- Version
- Gemini 2.5 Pro Preview 06-05
- Released
- Jun 5, 2025
- Knowledge cutoff
- Jan 31, 2025
- Parameters
- N/A
- Context window
- 1M
- Max output
- 65.5K
- Inputs
- image, text
- Outputs
- text
- Open weights
- No
- License
- Proprietary
Gemini 2.5 Pro Versions
Available versions of this model. The score column identifies the version used in the overall ranking.
Sort by
Version | Released | LLMBoard | Parameters | Context | Max output | Open weights | License |
|---|
| VersionGemini 2.5 Pro Preview 06-05 | Released | LLMBoard49.25 | ParametersN/A | Context1M | Max output65.5K | Open weightsNo | LicenseProprietary |
| VersionGemini 2.5 Pro | Released | LLMBoardN/A | ParametersN/A | Context1M | Max output65.5K | Open weightsNo | LicenseProprietary |
Models similar to Gemini 2.5 Pro
Recommendations prioritize the same model type and family, then the closest LLMBoard score.
GO
Google
Gemini 3.1 Flash Lite
GOGoogle
Gemma 4 26B A4B
GOGoogle
Gemini 3.5 Flash Lite
GOGoogle
Gemma 4 31B
GOGoogle
Gemini 2.5 Flash
GOGoogle
Gemma 4 12B
What is Gemini 2.5 Pro?
Key information about Gemini 2.5 Pro and its available data.
5 Pro is an llm from Google designed to solve complex problems using enhanced reasoning across text, images, video, and audio. It supports thinking preview, code execution, grounding with Google Search, system instructions, function calling, and controlled generation.
Data as of 2026-09-08.
FAQ
Common questions about Gemini 2.5 Pro.
When was Gemini 2.5 Pro released?
Gemini 2.5 Pro's default version was released on Jun 5, 2025.
How much does Gemini 2.5 Pro cost?
Gemini 2.5 Pro's official API price is $1.25 per million input tokens and $10 per million output tokens via Google. The lowest tracked third-party offer starts at $1.13 input and $9 output via Jiekou.AI.
Who created Gemini 2.5 Pro?
Gemini 2.5 Pro was created by Google.
What is the context window for Gemini 2.5 Pro?
The default version has a 1M token context window.
Is Gemini 2.5 Pro open weight?
No. The default version is not marked as having publicly available weights.