Gemini 2.5 Flash Preview 4/17 (Nonthinking)

Model

Gemini 2.5 Flash Preview 4/17 (Nonthinking)

Release Date: Apr 17, 2025

Developer Google 🇺🇸

Context Window 1M

Max Output Tokens 66k

Token Costs (in/out) $0.30/2.50

Weights Private

Input Modalities

Accuracy

65.98 %

Avg. Cost (In/Out)

$ 0.30 / $ 2.50

Latency

17.74 s

Vals Index

BenchmarksAccuracyRankings

0.0%

±0.98

72/98

0.0%

±0.89

83/145

0.0%

±2.41

116/138

0.0%

±1.18

111/143

0.0%

±0.40

44/146

0.0%

±1.12

73/93

Proprietary BenchmarksAcademic BenchmarksIndustry Partners

Vals

View Hyperparameter Settings

Default Provider : Google

Temperature: 1

Top P: Default

Top K: Default

Max Output Tokens: 65,536

Updates

May 5, 2025

Google's Gemini 2.5 Flash (Nonthinking) evaluated on most benchmarks

We just evaluated Gemini 2.5 Flash Preview (Nonthinking) on most benchmarks.

Gemini 2.5 Flash Preview (Nonthinking) is a lightweight alternative to Google’s flagship model, Gemini 2.5 Pro Exp. Gemini 2.5 Flash Preview (Nonthinking) runs at a fraction of the cost and latency, rendering it a more accessible option.
Like Claude 3.7 Sonnet (Nonthinking), Gemini 2.5 Flash Preview (Nonthinking) is a hybrid reasoning model, meaning it can adaptively choose how much to think before responding.
Gemini 2.5 Flash Preview (Nonthinking) excels on LegalBench, coming second only to the flagship Gemini 2.5 Pro Exp (and outperforming its own thinking variant, Gemini 2.5 Flash Preview (Thinking), by 1%).
We consistently had difficulty with Google’s API during evaluation, which prevented us from reporting full results. We’re working with a representative from the Gemini team to resolve those issues.