The Model Index
Models/Google

Gemini 2.5 Pro (Jun 2025)

GoogleClosed weights

Gemini 2.5 Pro (Jun 2025) is a closed AI model from Google with an index score of 145 (GPT-4 = 100), rank 80 of 217.

145129–161Index score#80 of 217 models
$1.25/ $10Price per million tokensinput / output · via OpenRouter
1.05MContext windowtokens it reads at once
5 Jun 2025ReleasedReplaced by Gemini 3 Pro

Where it sitson the frontier

801001201401601802002023202420252026GPT-4 at launch = 100Gemini 2.5 Pro (Jun 2025)

o3 reached this score 2 months earlier.

Test resultsby area · tick = best by any model

Reasoning & knowledgeevidence
GPQA Diamond (Epoch AI)
85%
Humanity's Last Exam
22%
Mathsevidence
FrontierMath (tiers 1-3)
25%
Codingevidence
SWE-bench Verified
58%
Terminal-Bench 4.0
no result
Agentsevidence
APEX-Agents
no result
Professional workno evidence yet
Finance Agent (v2)
no result
Novel problemsno evidence yet
ARC-AGI-2
no result
Long tasksevidence
METR time horizon
33 sec

Third-party results only, at the model’s best standard setting. Hover a bar for who ran it.

What others sayrank on each leaderboard

The Model Indexthird-party tests, our method#80of 217 · 145

Best attop three among current models

Replaced by Gemini 3 Pro; it no longer leads any category among current models.

Where to use itprices checked 18 Nov 2026

API providers 1 · per 1M tokens, in / out

Host prices from OpenRouter; going direct can differ.

Facts and sources

Released5 Jun 2025
Announcementnot linked yet
Release entry–
Scored asGemini 2.5 Pro (Jun 2025)
Output speed–
Hugging Faceclosed weights

Google releasesaround this one

This page as a chartDownload PNG