Compare/GPT-5 nano (medium) vs Gemini 2.5 Flash-Lite Preview (Sep '25) (Non-reasoning)

GPT-5 nano (medium)vsGemini 2.5 Flash-Lite Preview (Sep '25) (Non-reasoning)

Side-by-side comparison of pricing, 12 benchmarks, and generation speed.

OpenAI

GPT-5 nano (medium)

Input
$0.05/M
Output
$0.4/M
Speed
165 tok/s
TTFT
41.55s
Google

Gemini 2.5 Flash-Lite Preview (Sep '25) (Non-reasoning)

Input
$0.1/M
Output
$0.4/M
Speed
344 tok/s
TTFT
0.36s

Winner by Category

Cheaper
GPT-5 nano (medium)
Faster (tok/s)
Gemini 2.5 Flash-Lite Preview (Sep '25) (Non-reasoning)
Lower Latency
Gemini 2.5 Flash-Lite Preview (Sep '25) (Non-reasoning)
Benchmarks (10-1)
GPT-5 nano (medium)

Pricing Comparison

MetricGPT-5 nano (medium)Gemini 2.5 Flash-Lite Preview (Sep '25) (Non-reasoning)
Input ($/M tokens)$0.05$0.1
Output ($/M tokens)$0.4$0.4
Cost for 1M input + 100K output tokens:
GPT-5 nano (medium)$0.09
Gemini 2.5 Flash-Lite Preview (Sep '25) (Non-reasoning)$0.14

Speed Comparison

Output Speed (tokens/s) — higher is better
GPT-5 nano (medium)
165 tok/s
Gemini 2.5 Flash-Lite Preview (Sep '25) (Non-reasoning)
344 tok/s
Time to First Token (seconds) — lower is better
GPT-5 nano (medium)
41.55s
Gemini 2.5 Flash-Lite Preview (Sep '25) (Non-reasoning)
0.36s

Benchmark Comparison

Data from Artificial Analysis API — 12 benchmarks

Intelligence Index
25.919.4
Coding Index
22.914.5
Math Index
78.346.7
GPQA Diamond
67.0%65.1%
MMLU-Pro
77.2%79.6%
LiveCodeBench
76.3%64.1%
AIME 2025
78.3%46.7%
MATH-500
Humanity's Last Exam
7.6%4.6%
SciCode
33.8%28.5%
IFBench
65.9%41.8%
TerminalBench
17.4%7.6%
GPT-5 nano (medium)10 wins
1 winsGemini 2.5 Flash-Lite Preview (Sep '25) (Non-reasoning)

Frequently Asked Questions

Which is cheaper, GPT-5 nano (medium) or Gemini 2.5 Flash-Lite Preview (Sep '25) (Non-reasoning)?

GPT-5 nano (medium) is cheaper overall. Its blended price (3:1 input/output ratio) is $0.14/M tokens vs $0.17/M for Gemini 2.5 Flash-Lite Preview (Sep '25) (Non-reasoning).

Which model performs better on benchmarks?

GPT-5 nano (medium) wins 10 out of 12 benchmarks compared to 1 for Gemini 2.5 Flash-Lite Preview (Sep '25) (Non-reasoning). See the detailed benchmark chart above for per-category results.

Which is faster for real-time applications?

Gemini 2.5 Flash-Lite Preview (Sep '25) (Non-reasoning) generates tokens faster at 344 tok/s vs 165 tok/s. However, Gemini 2.5 Flash-Lite Preview (Sep '25) (Non-reasoning) has lower time-to-first-token (0.36s vs 41.55s).

When should I use GPT-5 nano (medium) vs Gemini 2.5 Flash-Lite Preview (Sep '25) (Non-reasoning)?

Choose based on your priorities: GPT-5 nano (medium) for lower cost, GPT-5 nano (medium) for stronger benchmark performance, and Gemini 2.5 Flash-Lite Preview (Sep '25) (Non-reasoning) for faster generation. For latency-sensitive apps, check the TTFT comparison above.