Price Per TokenPrice Per Token
OpenAI
OpenAI
vs
OpenAI
OpenAI

GPT-3.5 Turbo vs GPT-5

A detailed comparison of pricing, benchmarks, and capabilities

OpenClaw

Best LLMs for OpenClaw Vote for which model works best with OpenClaw

112 out of our 301 tracked models have had a price change in February.

Get our weekly newsletter on pricing changes, new releases, and tools.

Key Takeaways

GPT-3.5 Turbo wins:

  • Cheaper input tokens
  • Cheaper output tokens
  • Faster response time

GPT-5 wins:

  • Larger context window
  • Higher intelligence benchmark
  • Better at coding
  • Better at math
  • Supports vision
  • Supports tool calls
Price Advantage
GPT-3.5 Turbo
Benchmark Advantage
GPT-5
Context Window
GPT-5
Speed
GPT-3.5 Turbo

Pricing Comparison

Price Comparison

MetricGPT-3.5 TurboGPT-5Winner
Input (per 1M tokens)$0.50$1.25 GPT-3.5 Turbo
Output (per 1M tokens)$1.50$10.00 GPT-3.5 Turbo
Cache Read (per 1M)N/A$125000.00 GPT-5
Using a 3:1 input/output ratio, GPT-3.5 Turbo is 78% cheaper overall.

GPT-3.5 Turbo Providers

OpenAI $0.50 (Cheapest)
Vercel $0.50 (Cheapest)
Azure $1.50

GPT-5 Providers

OpenAI $1.25 (Cheapest)
Azure $1.25 (Cheapest)

Benchmark Comparison

8
Benchmarks Compared
0
GPT-3.5 Turbo Wins
5
GPT-5 Wins

Benchmark Scores

BenchmarkGPT-3.5 TurboGPT-5Winner
Intelligence Index
Overall intelligence score
9.044.6
Coding Index
Code generation & understanding
10.736.0
Math Index
Mathematical reasoning
-94.3-
MMLU Pro
Academic knowledge
46.287.1
GPQA
Graduate-level science
29.785.4
LiveCodeBench
Competitive programming
-84.6-
Aider
Real-world code editing
57.988.0
AIME
Competition math
-95.7-
GPT-5 significantly outperforms in coding benchmarks.

Cost vs Quality

X-axis:
Y-axis:
Loading chart...
GPT-3.5 Turbo
Other models

Context & Performance

Context Window

GPT-3.5 Turbo
16,385
tokens
Max output: 4,096 tokens
GPT-5
400,000
tokens
Max output: 128,000 tokens
GPT-5 has a 96% larger context window.

Speed Performance

MetricGPT-3.5 TurboGPT-5Winner
Tokens/second95.2 tok/s83.1 tok/s
Time to First Token0.41s109.19s
GPT-3.5 Turbo responds 15% faster on average.

Capabilities

Feature Comparison

FeatureGPT-3.5 TurboGPT-5
Vision (Image Input)
Tool/Function Calls
Reasoning Mode
Audio Input
Audio Output
PDF Input
Prompt Caching
Web Search

License & Release

PropertyGPT-3.5 TurboGPT-5
LicenseProprietaryProprietary
AuthorOpenAIOpenAI
ReleasedMay 2023Aug 2025

GPT-3.5 Turbo Modalities

Input
text
Output
text

GPT-5 Modalities

Input
textimagefile
Output
text

Related Comparisons

Compare GPT-3.5 Turbo with:

Compare GPT-5 with:

Frequently Asked Questions

GPT-3.5 Turbo has cheaper input pricing at $0.50/M tokens. GPT-3.5 Turbo has cheaper output pricing at $1.50/M tokens.
GPT-5 scores higher on coding benchmarks with a score of 36.0, compared to GPT-3.5 Turbo's score of 10.7.
GPT-3.5 Turbo has a 16,385 token context window, while GPT-5 has a 400,000 token context window.
GPT-3.5 Turbo does not support vision. GPT-5 supports vision.