Price Per TokenPrice Per Token
Anthropic
Anthropic
vs
OpenAI
OpenAI

Claude Sonnet 4.6 vs o3

A detailed comparison of pricing, benchmarks, and capabilities

Best Coding Model Leaderboard Find the top LLM for coding by benchmarks and community votes

114 out of our 298 tracked models have had a price change in February.

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

Key Takeaways

Claude Sonnet 4.6 wins:

  • Larger context window
  • Higher intelligence benchmark
  • Better at coding

o3 wins:

  • Cheaper input tokens
  • Cheaper output tokens
  • Faster response time
  • Better at math
Price Advantage
o3
Benchmark Advantage
Claude Sonnet 4.6
Context Window
Claude Sonnet 4.6
Speed
o3

Pricing Comparison

Price Comparison

MetricClaude Sonnet 4.6o3Winner
Input (per 1M tokens)$3.00$2.00 o3
Output (per 1M tokens)$15.00$8.00 o3
Cache Read (per 1M)$300000.00$500000.00 Claude Sonnet 4.6
Cache Write (per 1M)$3750000.00N/A Claude Sonnet 4.6
Using a 3:1 input/output ratio, o3 is 42% cheaper overall.

Claude Sonnet 4.6 Providers

Amazon Bedrock $3.00 (Cheapest)
Google $3.00 (Cheapest)
Anthropic $3.00 (Cheapest)

o3 Providers

OpenAI $2.00 (Cheapest)
Vercel $2.00 (Cheapest)

Benchmark Comparison

8
Benchmarks Compared
2
Claude Sonnet 4.6 Wins
1
o3 Wins

Benchmark Scores

BenchmarkClaude Sonnet 4.6o3Winner
Intelligence Index
Overall intelligence score
44.338.3
Coding Index
Code generation & understanding
46.438.4
Math Index
Mathematical reasoning
-88.3-
MMLU Pro
Academic knowledge
-85.3-
GPQA
Graduate-level science
79.982.7
LiveCodeBench
Competitive programming
-80.8-
Aider
Real-world code editing
-81.3-
AIME
Competition math
-90.3-
Claude Sonnet 4.6 significantly outperforms in coding benchmarks.

Cost vs Quality

X-axis:
Y-axis:
Loading chart...
Other models

Context & Performance

Context Window

Claude Sonnet 4.6
1,000,000
tokens
Max output: 128,000 tokens
o3
200,000
tokens
Max output: 100,000 tokens
Claude Sonnet 4.6 has a 80% larger context window.

Speed Performance

MetricClaude Sonnet 4.6o3Winner
Tokens/second56.3 tok/s108.8 tok/s
Time to First Token0.80s22.13s
o3 responds 93% faster on average.

Capabilities

Feature Comparison

FeatureClaude Sonnet 4.6o3
Vision (Image Input)
Tool/Function Calls
Reasoning Mode
Audio Input
Audio Output
PDF Input
Prompt Caching
Web Search

License & Release

PropertyClaude Sonnet 4.6o3
LicenseProprietaryProprietary
AuthorAnthropicOpenAI
ReleasedFeb 2026Apr 2025

Claude Sonnet 4.6 Modalities

Input
textimage
Output
text

o3 Modalities

Input
imagetextfile
Output
text

Related Comparisons

Compare Claude Sonnet 4.6 with:

Compare o3 with:

Frequently Asked Questions

o3 has cheaper input pricing at $2.00/M tokens. o3 has cheaper output pricing at $8.00/M tokens.
Claude Sonnet 4.6 scores higher on coding benchmarks with a score of 46.4, compared to o3's score of 38.4.
Claude Sonnet 4.6 has a 1,000,000 token context window, while o3 has a 200,000 token context window.
Claude Sonnet 4.6 supports vision. o3 supports vision.