Skip to content
llmwaves

Gemini 2.5 Flash

Google · released Jun 17, 2025

ProprietaryReasoningTool useStructured outputVisionAudio inVideo in

Gemini 2.5 Flash is Google's state-of-the-art workhorse model, specifically designed for advanced reasoning, coding, mathematics, and scientific tasks. It includes built-in "thinking" capabilities, enabling it to provide responses with greater...

Specification

Context window
1.05M
Max output
66K
Knowledge cutoff
Jan 31, 2025
Parameters
Undisclosed
Licence
Proprietary
Serving providers
2
Moderated
No
Uptime
100.0%

Intelligence

14.2

46th percentile

Coding

Coding Index

Agentic

Agentic Index

Output speed

92 t/s

Median across providers

Latency

516ms

Time to first token

Cost per task

$0.22

Estimated

Benchmarks

Where the score comes from

The Intelligence Index is a composite. These are the underlying evaluations this model was actually measured on.

Evaluation scores

Percentage correct · higher is better

  • MMLU-Pro
    80.9%
  • GPQA Diamond
    68.3%
  • AIME 2025
    60.3%
  • LiveCodeBench
    49.5%
  • AA-LCR (long context)
    48.0%
  • IFBench
    39.0%
  • SciCode
    29.1%
  • τ²-bench (Telecom)
    14.9%
  • Terminal-Bench Hard
    12.1%
  • Humanity's Last Exam
    4.7%

An evaluation missing from this list was not run for this model — it is not a zero.

View as table
EvaluationScore
MMLU-Pro80.9%
GPQA Diamond68.3%
AIME 202560.3%
LiveCodeBench49.5%
AA-LCR (long context)48.0%
IFBench39.0%
SciCode29.1%
τ²-bench (Telecom)14.9%
Terminal-Bench Hard12.1%
Humanity's Last Exam4.7%

Against its peers

Intelligence Index · this model highlighted, nearest peers in grey

Peers are the models sitting closest on the Intelligence Index — the set you would realistically choose between.

View as table
ModelIntelligence
Mistral Medium 3.114.7
Solar Pro 314.5
Llama 4 Maverick14.5
Qwen3 VL 235B A22B Instruct14.4
Gemini 2.5 Flash14.2
Ling-2.6-flash14.2
Qwen3 Next 80B A3B Instruct13.8
Qwen3 Coder 30B A3B Instruct13.6

Percentile among all indexed models

Intelligence46th
Mathematics57th
Terminal work48th
Arena Elo25th

Pricing

What it costs to run

List prices per million tokens, plus what one representative task works out to.

List price

Input / 1M tokens
$0.3
Output / 1M tokens
$2.5
Cached input / 1M
$0.03
Blended 3:1
$0.85

One task, estimated

$0.22

Input tokens
50,000
Output tokens
80,000
Profile
Reasoning

Estimated from list pricing: 50K input tokens plus 80K output tokens for reasoning models (25K for non-reasoning).

Serving providers

Speed and latency figures are medians across these providers, so a widely-served model reports a blend rather than any single endpoint.

Arena

Head-to-head generation quality

Elo from pairwise judgements, broken out by the kind of thing the model was asked to build.

Overall Elo
1,097
Win rate
45.7%
Strongest at
Websites
Tournaments
5,472

Elo by category

Dot position on a 1,025–1,100 scale · Elo has no meaningful zero

Agent categories (full-stack apps, mobile apps) are only scored for models tested in agent harnesses.

View as table
CategoryEloWin rate
Websites109745.7%
Data visualisation108145.7%
3D scenes107644.4%
Game development104543.5%
UI components104043.6%