Back to LeaderboardCompare View
Model profile
Google

Gemini 2.5 Pro Preview (May' 25)

Gemini 2.5 Pro Preview (May' 25) is a budget text-first model from Google with a heavy runtime profile, unknown context posture, and the clearest fit around coding / agent workflows.

Best for: Coding / Agent workflowsHeavy latencyUnknown contextBudget pricing
Intelligence
29.5

Benchmark blend

Coding
0.770

Dev workflow signal

Context
N/A

Unknown

Input Price
$1.25

Budget tier

Decision snapshot
50

Gemini 2.5 Pro Preview (May' 25) currently reads as a budget text-first option with unknown context and a heavy runtime profile.

Overall profile
Use-case specific
Best for
Coding / Agent workflows
Latency tier
Heavy
Price tier
Budget
Source coverage
OpenRouterArtificial Analysis
Compare this modelSee leaderboard

Decision Strip

Decision rail before the raw tables

Core buy-side signals stay in one pass. The rest of the page expands only after intelligence, speed, context, and price are clear.

Intelligence
29.5
30

General reasoning and benchmark headroom.

Limited
Speed
N/A
46

Latency data is partial.

Situational
Context
N/A
34

How much prompt and task state can stay in view.

Limited
Price
$1.25
86

$10.00 output / 1M

Efficient

Editorial Profile

Gemini 2.5 Pro Preview (May' 25) in one narrative

Positioning, tradeoffs, and fit are consolidated into one read instead of repeating the same story across separate cards.

Use-case specificCoding score 77Math score 99

The Gemini 2.5 Pro Preview (May' 25) AI model by Google.

Identity

Google text-first profile

Positioning

Coding / Agent workflows with unknown context and heavy runtime.

Cost posture

Efficient spend profile. More comfortable for sustained prompt volume if the capability fit is right.

Strengths

  • Coding indicators point to a strong developer workflow fit.

Tradeoffs

  • Budget-friendly input pricing is a strength, but raw capability may vary by workload.

  • Latency profile is better for deliberate runs than rapid back-and-forth chat.

  • Current metadata points to a text-first profile rather than a broad multimodal one.

Best fit

  • Code generation, refactors, test writing, and tool-assisted debugging.

Compare Next

Similar profiles worth opening next

Google

Gemini 3 Pro Preview (high)

Intelligence
48.4
Context
N/A
Input Price
$2.00
CompareOpen profile
Google

Gemini 3 Flash Preview (Non-reasoning)

Intelligence
35.0
Context
N/A
Input Price
$0.50
CompareOpen profile
Google

Gemini 2.5 Flash Preview (Sep '25) (Reasoning)

Intelligence
31.1
Context
N/A
Input Price
$0.30
CompareOpen profile

Benchmarks

Grouped by job-to-be-done

Only benchmark categories with actual signal are shown. Secondary values stay as simple definitions instead of nested micro-cards.

General intelligence

Broad reasoning, knowledge depth, and flagship benchmark posture.

Intelligence Index
29.5
MMLU Pro
83.7%
GPQA
82.2%
HLE
15.4%
Coding

Software implementation, debugging quality, and coding benchmark signal.

LiveCodeBench
0.770
SciCode
41.6%
Math

Formal reasoning, structured problem solving, and competition-style math.

AIME
84.3%
Math 500
98.6%

Specs & Pricing

Technical snapshot and cost posture

Specs stay neutral, pricing gets emphasis through values rather than extra containers. Raw provider internals remain in metadata at the end.

Technical snapshot
Context Window
N/A
Vision
Text-first
Price architecture
Input
per 1M input tokens
$1.25
Output
per 1M output tokens
$10.00
Blended
AA 3:1 mix
$3.44

This model is relatively efficient on price. It is the easier fit when sustained prompt volume matters.

Metadata

Raw source tables at the end

Verification details remain available, but the page no longer forces them ahead of the editorial read.