Gemini 2.5 Pro Preview 06-05
Gemini 2.5 Pro is Google’s state-of-the-art AI model designed for advanced reasoning, coding, mathematics, and scientific tasks.
text + image + audio + file → text · made by Google
Sold by 2 ways
| Seller | Lane | Rate |
|---|---|---|
| Nous Research aggregator | standard | $1.25per Mtok in$10per Mtok out$0.000001per image$0.12per Mtok cached$0.38per Mtok cache writeinference-api.nousresearch.com · read 2026-09-12 |
| OpenRouter aggregator | standard | $1.25per Mtok in$10per Mtok out$0.000001per image$0.12per Mtok cached$0.38per Mtok cache writeopenrouter.ai · read 2026-08-24 |
Measured 18 standings
| Place | Board | Metric | Score |
|---|---|---|---|
| 4thof 69 | Aider polyglot coding leaderboard | Percent correct | 83.1 |
| 4thof 72 | Aider polyglot — Epoch AI | Percent correct | 83.1 |
| 4thof 28 | LiveCodeBench Leaderboard (default window 8/1/2024–5/1/2025, 454 problems) | Pass@1 | 73.6 |
| 6thof 42 | Fictionlivebench — Epoch AI | 120k token score | 0.875 |
| 12thof 38 | Vpct — Epoch AI | Correct | 0.464 |
| 13thof 13 | Rli — Epoch AI | Score | 0.83 |
| 15thof 51 | Humanity's Last Exam (Epoch AI replication) | Accuracy | 21.64 |
| 21stof 102 | Simplebench — Epoch AI | Score (AVG@5) | 0.624 |
| 26thof 46 | Enigma eval — Epoch AI | Accuracy | 5.57 |
| 28thof 50 | Metr time horizons — Epoch AI | average_score | 0.554 |
| 31stof 38 | Gso — Epoch AI | Score OPT@1 | 0.039 |
| 33rdof 41 | Deepresearchbench — Epoch AI | Average score | 0.428 |
| 55thof 101 | FrontierMath (Tiers 1-3) | mean_score | 10.345 |
| 57thof 72 | Frontiermath tier 4 — Epoch AI | mean_score | 2.083 |
| 91stof 313 | GPQA Diamond | mean_score | 84.848 |
| 180thof 244 | Arc agi — Epoch AI | Score | 31.3 |
| 221stof 227 | Arc agi 2 — Epoch AI | Score | 0 |
| 322ndof 656 | Epoch capabilities index — Epoch AI | ECI Score | 145.29 |
About
Gemini 2.5 Pro Preview 06-05 — a text model from Google, sold by 2 companies from $1.25 in and $10 out per million tokens, placed 4th of 72 on Aider polyglot — Epoch AI.
It takes text, images, audio and files and returns text, with a context window of 1,048,576 tokens. It was published in June 2025, trained on material up to January 2025. Its sellers say it can reason step by step and call a tool. The catalogue files it under reasoning, code and agents. Two companies sell it. The cheapest is $1.25 in and $10 out per million tokens at Nous Research. It has been measured on 18 boards, and stands best at 4th of 72 on Aider polyglot — Epoch AI.
Every current figure
- Maker
- Register
- model
- Takes
- text + image + audio + file
- Returns
- text
- Context
- 1,048,576 tokens
- Longest answer
- 65,536 tokens
- Published
- June 2025
- Knowledge to
- January 2025
- Licence
- not read
- Sellers
- 2
- Maker's own price
- not read
- Price
- $1.25 in and $10 out per million tokens — Nous Research
- Boards
- 18
- Best place
- 4th of 72 — Aider polyglot — Epoch AI
Known as 4 names
gemini-2.5-pro-preview-06-05 (32k think)gemini-2.5-pro-preview-06-05 (default think)Gemini-2.5-Pro-06-05google/gemini-2.5-pro-preview