Gemini 2.5 Pro Preview 06-05

google/gemini-2.5-pro-preview-06-05

Google Gemini 2.5 Pro Preview 06‑05, released on 2025‑06‑05, accepts file, image, text, and audio inputs and generates text output. It supports tool usage and reasoning, operates with a context length of 1,048,576 tokens, and is priced at $1.25 per M input tokens and $10 per M output tokens. The model’s weights are not open.

  • tool use
  • structured outputs
  • reasoning

At a glance

providergoogle
releasedJun 5, 2025
context1.0M
input / M$1.25

Specifications

What the API gives you

Context window
1.0M tokens
Max output
66K tokens
Input price
$1.25 / 1M tokens
Output price
$10 / 1M tokens
Cache read
$0.13 / 1M tokens
Modalities
file, image, text, audio → text
Knowledge cutoff
Jan 31, 2025
Released
Jun 5, 2025

Measured evidence

Public benchmark record

Aider Polyglot
76.9%2026-10-20
GPQA Diamond (Epoch AI)
84.8% ± 2.62025-06-05evaluated 2025-06-05
GPQA Diamond (Epoch AI)
66.7% ± 3.42025-06-03evaluated 2025-06-03

LMArena data licensed CC-BY-4.0. Aider (Apache-2.0) and SWE-bench (MIT) are open. Design Arena uses blind human preference.

Task evidence

How broad is the support?

Each status is exact to this model version and the selected task. Official release claims remain provisional.

  • Best Local LLM for CodingProvisional evidence

    38% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LiveBench Coding or LMArena WebDev. 4 of 4 configured evaluation feeds currently have results.

  • Best LLM for Debugging & Code ReviewProvisional evidence

    22% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LiveBench Coding or LMArena WebDev. 5 of 5 configured evaluation feeds currently have results.

  • Best LLM for Code CompletionProvisional evidence

    21% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LiveBench Coding or LMArena WebDev. 3 of 3 configured evaluation feeds currently have results.

  • Best LLM for Logic & Problem SolvingProvisional evidence

    18% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from LiveBench Instruction Following or LiveBench Reasoning. 5 of 5 configured evaluation feeds currently have results.

  • Best LLM for Math & ReasoningProvisional evidence

    12% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from FrontierMath Tiers 1-3 (Epoch AI) or OTIS Mock AIME (Epoch AI). 7 of 7 configured evaluation feeds currently have results.

  • Best LLM for CodingProvisional evidence

    11% of intended weighted task evidence across 1 independent source; broader independent confirmation is still missing from Design Arena Coding or LiveBench Coding. 7 of 7 configured evaluation feeds currently have results.

Recommendation coverage

Where this model appears

Not currently included in a published recommendation. The task evidence panel above says exactly what is confirmed and what is still missing.

Catalog data via OpenRouter and models.dev. Last checked within the past 6 hours.