Gemini 2.5 Flash vs GPT-5

Benchmarks, API pricing and specs, head to head. Data updated 2026-06-10.

Gemini 2.5 Flash

Google · Jun 2025

The 2025 fast-tier favorite: hybrid reasoning, full multimodality and a 1M context at $0.30/$2.50.

GPT-5

OpenAI · Aug 2025

70.7

OpenAI's August 2025 unified flagship that merged the GPT and o-series reasoning lines into one model with selectable effort.

The verdict

GPT-5 wins 3 of the 3 benchmarks these models share, against 0 for Gemini 2.5 Flash. On price the gap is dramatic: Gemini 2.5 Flash works out roughly 4.0x cheaper per blended million tokens. Gemini 2.5 Flash also takes 1.0M of context versus 400K for GPT-5.

Benchmark head-to-head 03

SWE-bench Verified
~48.9%74.9%
Gemini 2.5 FlashGPT-5
GPQA Diamond
~78.3%85.7%
Gemini 2.5 FlashGPT-5
MMMU
~76.9%84.2%
Gemini 2.5 FlashGPT-5

Specs & pricing

Gemini 2.5 FlashGPT-5
modhub Index70.7
Input price / 1M$0.3$1.25
Output price / 1M$2.5$10
Context window1.0M400K
Max output66K128K
Open weightsnono
Reasoning modelyesyes
Multimodal inputtext, image, audio, videotext, image
Knowledge cutoffJan 2025Sep 2024
ReleasedJun 2025Aug 2025
Example monthly cost*$6.75$27.50

* 10M input + 1.5M output tokens per month at list prices, no caching. Green = better value on that row.

Frequently asked questions

Which is better, Gemini 2.5 Flash or GPT-5?
GPT-5 wins 3 of the 3 benchmarks these models share, against 0 for Gemini 2.5 Flash. On price the gap is dramatic: Gemini 2.5 Flash works out roughly 4.0x cheaper per blended million tokens. Gemini 2.5 Flash also takes 1.0M of context versus 400K for GPT-5.
Which is cheaper, Gemini 2.5 Flash or GPT-5?
Gemini 2.5 Flash costs $0.3/$2.5 per million input/output tokens, while GPT-5 costs $1.25/$10. For a typical workload of 10M input and 1.5M output tokens per month, that's $6.75 versus $27.50.
Which model is better for coding, Gemini 2.5 Flash or GPT-5?
On SWE-bench Verified — the standard agentic-coding benchmark — GPT-5 scores 74.9% versus ~48.9% for Gemini 2.5 Flash, making GPT-5 the stronger pick for coding agents.

More comparisons