Google model product
The latest preview version of Google's most advanced reasoning Gemini model, capable of solving complex problems. Built for the agentic era with enhanced reasoning capabilities, multimodal understanding (text, image, video, audio), and a 1M token context window. Features thinking preview, code execution, grounding with Google Search, system instructions, function calling, and controlled generation. Supports up to 3,000 images per prompt, 45-60 minutes of video, and 8.4 hours of audio.
Updated Aug 10, 2026. Default version: Gemini 2.5 Pro Preview 06-05
Structured fields from the published default version.
This profile uses the latest version under this unique model that has a calculated LLMBoard score. Arena and price are excluded.
Published benchmark records for the scored version Gemini 2.5 Pro Preview 06-05.
| FACTS Grounding | 0.9 | 1 | 13 | 100.0% | C | |
| Global-MMLU-Lite | 0.9 | 1 | 14 | 100.0% | C | |
| Vibe-Eval | 0.7 | 1 | 8 | 100.0% | C | |
| Aider-Polyglot | 0.8 | 2 | 22 | 95.2% | C | |
| MMMU | 0.8 | 10 | 63 | 85.5% | C | |
| SimpleQA | 0.5 | 12 | 46 | 75.6% | C | |
| VideoMMMU | 0.8 | 12 | 26 | 56.0% | C | |
| MRCR v2 (8-needle) | 0.2 | 20 | 21 | 5.0% | C | |
| LiveCodeBench | 0.7 | 23 | 73 | 69.4% | C | |
| GPQA | 0.9 | 45 | 233 | 81.0% | C | |
| AIME 2025 | 0.9 | 52 | 114 | 54.9% | C | |
| Humanity's Last Exam | 0.2 | 56 | 92 | 39.6% | C | |
| SWE-Bench Verified | 0.7 | 69 | 104 | 34.0% | C |
Preference and agent-evaluation signals from published Arena datasets.
The default version has no published Arena rows, or its source alias has not been resolved.
Official vendor API PAYG pricing is summarized first. The table then lists individual provider offerings without treating their minimum as the official price.
| Jiekou.AI | gemini-2.5-pro-preview-06-05 | global | $1.13 | $9 | 1M | |
| OpenRouter | google/gemini-2.5-pro-preview | global | $1.25 | $10 | 1M | |
| NanoGPT | gemini-2.5-pro-preview-06-05 | global | $2.5 | $10 | 1M |
Official prices use only the vendor's configured official Provider and positive standard USD PAYG rates. Third-party offers remain explicitly labeled.
All published versions linked to this unique model. The score columns identify the version used by the current overall ranking.
| Gemini 2.5 Pro Preview 06-05 | 78.0 | N/A | 1M | 65.5K | No | Proprietary | |
| Gemini 2.5 Pro | N/A | N/A | 1M | 65.5K | No | Proprietary |
A concise description based on the published model registry.
The latest preview version of Google's most advanced reasoning Gemini model, capable of solving complex problems. Built for the agentic era with enhanced reasoning capabilities, multimodal understanding (text, image, video, audio), and a 1M token context window. Features thinking preview, code execution, grounding with Google Search, system instructions, function calling, and controlled generation. Supports up to 3,000 images per prompt, 45-60 minutes of video, and 8.4 hours of audio.
Use the benchmark, Arena and pricing sections above as separate evidence. A missing field means the current data snapshot does not support that claim.
Data snapshot: 2026-08-07. Editorial model content is not available in the backend.
Open a comparison with the three ranked models immediately above and below this model.
Recommendations prioritize the same model type and family, then the closest published LLMBoard score.
Common questions about Gemini 2.5 Pro.
Gemini 2.5 Pro's default version was released on Jun 5, 2025.
No official standard PAYG price is currently available for Gemini 2.5 Pro. The lowest tracked third-party offer starts at $1.13 input and $9 output via Jiekou.AI.
Gemini 2.5 Pro is published under Google in the model registry.
The default version has a 1M token context window.
No. The default version is not marked as having publicly available weights.
3 published provider offerings are linked to the default version.
Nearby ranked alternatives include Hy3, DeepSeek-V4-Pro, Claude Opus 4.7.