Price Per TokenPrice Per Token
Anthropic
Anthropic
vs
OpenAI
OpenAI

Claude 3.5 Haiku vs GPT-5.2 Pro

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

Claude 3.5 Haiku wins:

  • Cheaper input tokens
  • Cheaper output tokens

GPT-5.2 Pro wins:

  • Larger context window
  • Faster response time
  • Higher intelligence benchmark
  • Better at coding
  • Better at math
Price Advantage
Claude 3.5 Haiku
Benchmark Advantage
GPT-5.2 Pro
Context Window
GPT-5.2 Pro
Speed
GPT-5.2 Pro

Pricing Comparison

Price Comparison

MetricClaude 3.5 HaikuGPT-5.2 ProWinner
Input (per 1M tokens)$0.80$21.00 Claude 3.5 Haiku
Output (per 1M tokens)$4.00$168.00 Claude 3.5 Haiku
Cache Read (per 1M)$80000.00N/A Claude 3.5 Haiku
Cache Write (per 1M)$1000000.00N/A Claude 3.5 Haiku
Using a 3:1 input/output ratio, Claude 3.5 Haiku is 97% cheaper overall.

Claude 3.5 Haiku Providers

Vercel $0.80 (Cheapest)
Amazon Bedrock $0.80 (Cheapest)
Google $0.80 (Cheapest)
Anthropic $0.80 (Cheapest)

GPT-5.2 Pro Providers

OpenAI $21.00 (Cheapest)

Benchmark Comparison

7
Benchmarks Compared
0
Claude 3.5 Haiku Wins
5
GPT-5.2 Pro Wins

Benchmark Scores

BenchmarkClaude 3.5 HaikuGPT-5.2 ProWinner
Intelligence Index
Overall intelligence score
18.751.2
Coding Index
Code generation & understanding
10.748.7
Math Index
Mathematical reasoning
-99.0-
MMLU Pro
Academic knowledge
63.487.4
GPQA
Graduate-level science
40.890.3
LiveCodeBench
Competitive programming
31.488.9
AIME
Competition math
3.3--
GPT-5.2 Pro significantly outperforms in coding benchmarks.

Cost vs Quality

X-axis:
Y-axis:
Loading chart...
Claude 3.5 Haiku
Other models

Context & Performance

Context Window

Claude 3.5 Haiku
200,000
tokens
Max output: 8,192 tokens
GPT-5.2 Pro
400,000
tokens
Max output: 128,000 tokens
GPT-5.2 Pro has a 50% larger context window.

Speed Performance

MetricClaude 3.5 HaikuGPT-5.2 ProWinner
Tokens/second49.4 tok/s98.3 tok/s
Time to First Token0.68s46.57s
GPT-5.2 Pro responds 99% faster on average.

Capabilities

Feature Comparison

FeatureClaude 3.5 HaikuGPT-5.2 Pro
Vision (Image Input)
Tool/Function Calls
Reasoning Mode
Audio Input
Audio Output
PDF Input
Prompt Caching
Web Search

License & Release

PropertyClaude 3.5 HaikuGPT-5.2 Pro
LicenseProprietaryProprietary
AuthorAnthropicOpenAI
ReleasedNov 2024Dec 2025

Claude 3.5 Haiku Modalities

Input
textimage
Output
text

GPT-5.2 Pro Modalities

Input
imagetextfile
Output
text

Related Comparisons

Compare Claude 3.5 Haiku with:

Compare GPT-5.2 Pro with:

Frequently Asked Questions

Claude 3.5 Haiku has cheaper input pricing at $0.80/M tokens. Claude 3.5 Haiku has cheaper output pricing at $4.00/M tokens.
GPT-5.2 Pro scores higher on coding benchmarks with a score of 48.7, compared to Claude 3.5 Haiku's score of 10.7.
Claude 3.5 Haiku has a 200,000 token context window, while GPT-5.2 Pro has a 400,000 token context window.
Claude 3.5 Haiku supports vision. GPT-5.2 Pro supports vision.