Gemini 2.5 Flash Preview (Sep '25) (Reasoning)
GoogleGemini
Description
A thinking model designed for a balance between price and performance. It builds upon Gemini 2.0 Flash with upgraded reasoning, hybrid thinking control, multimodal capabilities (text, image, video, audio input), and a 1M token input context window.
Release Date
2025-09-25
Parameters
—
Context Length
1.0M
Modalities
audio, image, pdf, text, video
Capability Radar
40
general
64
coding
78
reasoning
52
scienceest.
74
agents
80
multimodal
Science uses a reasoning proxy when dedicated science benchmarks are unavailable.
Rankings
| Domain | #Rank | Score | Source |
|---|---|---|---|
| Code Ranking | 114 | 63.0 | AA |
| General Ranking | 160 | 55.0 | AA |
| Math Reasoning | 91 | 79.0 | AA |
| Science | 127 | 57.0 | AA |
Benchmark Scores (LLM Stats)
Biology
GPQA
82.8%SR
Code
Aider-Polyglot
61.9%SR
SWE-Bench Verified
60.4%SR
Aider-Polyglot Edit
56.7%SR
Factuality
FACTS Grounding
85.3%SR
SimpleQA
26.9%SR
General
Global-MMLU-Lite
88.4%SR
MMMU
79.7%SR
Vibe-Eval
65.4%SR
LiveCodeBench v5
63.9%SR
MRCR
32.0%SR
Math
AIME 2024
88.0%SR
AIME 2025
72.0%SR
Humanity's Last Exam
11.0%SR
AA Evaluation Indices
Math Index78.3
Intelligence Index23.8
Mmlu Pro0.8
Gpqa0.8
Aime 250.8
Livecodebench0.7
Lcr0.6
Ifbench0.5
Tau20.5
Scicode0.4
Terminalbench Hard0.2
Hle0.1
LLM Stats Category Scores
Language90
Grounding90
Physics80
Healthcare80
Biology80
Chemistry80
Multimodal70
Math60
Reasoning60
Factuality60
Frontend Development60
General60
Code60
Vision50
Long Context20
Pricing
Input PriceFree
Output PriceFree
Blended Price (3:1)Free
Cache Read Price$0.03 / 1M tokens
Speed
Tokens/sec0.0
Time to First Token0.00s
Time to Answer0.00s
Provider Price Ranking
No provider data available