live
weekly refresh
basedagi.org
▸ compare

Anthropic: Claude Sonnet 4.6 vs OpenAI: GPT-5.4

Side-by-side benchmark comparison based on independent public data. Scores, pricing, context, and task breakdown.

▸ verdict
Anthropic: Claude Sonnet 4.6
89.1
vs
OpenAI: GPT-5.4
88.9
These two models are effectively tied on overall score within the two-point margin. Choose based on pricing, context window, or task-specific performance below.
▸ score breakdown
TaskAnthropic: Claude Sonnet 4.6OpenAI: GPT-5.4Δ
Overall89.188.9+0.2
Coding56.3
Reasoning67.672.4-4.8
Math
Writing87.9
JSON
▸ specs & pricing
AttributeAnthropic: Claude Sonnet 4.6OpenAI: GPT-5.4
ProviderAnthropicOpenai
Context window1M1M
Input $/M tokens$3.00/M$2.50/M
Output $/M tokens$15.00/M$15.00/M
Weightsproprietaryproprietary
▸ frequently asked

Is Anthropic: Claude Sonnet 4.6 better than OpenAI: GPT-5.4?

Anthropic: Claude Sonnet 4.6 and OpenAI: GPT-5.4 are closely matched in overall score. Choose based on pricing, context window, or the task-specific scores in the table above.

Which is cheaper: Anthropic: Claude Sonnet 4.6 or OpenAI: GPT-5.4?

OpenAI: GPT-5.4 is cheaper at $2.5/M input tokens vs $3/M for Anthropic: Claude Sonnet 4.6.

Which model is better for coding?

Both models perform similarly on coding benchmarks (SWE-Bench, Aider Polyglot, LiveCodeBench).