Requesty

claude-sonnet-4-6 vs gpt-5

Side-by-side comparison of claude-sonnet-4-6 and gpt-5: benchmarks, pricing, context window and capabilities. Both are accessible through Requesty's unified API. claude-sonnet-4-6 outperforms gpt-5 on 6 of 7 shared benchmarks.

Benchmark comparison

Intelligence Indexreasoning
claude-sonnet-4-647.2%
gpt-534.7%
Coding Indexcoding
claude-sonnet-4-663.0%
gpt-537.8%
Math Indexmath
claude-sonnet-4-6N/A
gpt-594.3%
GPQA Diamondreasoning
claude-sonnet-4-687.5%
gpt-585.4%
AIME 2025math
claude-sonnet-4-6N/A
gpt-594.3%
LiveCodeBenchcoding
claude-sonnet-4-6N/A
gpt-584.6%
Terminal-Bench Hardagentic
claude-sonnet-4-653.0%
gpt-532.6%
τ²-Benchagentic
claude-sonnet-4-675.7%
gpt-584.8%
SciCodecoding
claude-sonnet-4-646.8%
gpt-542.9%
MMLU Proknowledge
claude-sonnet-4-6N/A
gpt-587.1%
Humanity's Last Examreasoning
claude-sonnet-4-630.0%
gpt-526.5%

Scores sourced from official model cards, Artificial Analysis, and public leaderboards. Benchmarks measure specific skills and don't capture every aspect of model quality.

Pricing & specifications

claude-sonnet-4-6gpt-5
Input price / 1M$3.00$1.25
Output price / 1M$15.00$10.00
Context window1M tokens400K tokens
Max output64K tokens128K tokens
Vision inputYesYes
Tool callingYesYes
ReasoningYesYes
Prompt cachingYesYes
Computer useYesN/A
ProviderAnthropic PBCOpenAI Inc.

Questions people ask

Is claude-sonnet-4-6 better than gpt-5?
claude-sonnet-4-6 outperforms gpt-5 on 6 of 7 shared benchmarks. See the benchmark comparison above for specifics: claude-sonnet-4-6 and gpt-5 have different strengths across reasoning, coding, math and multimodal tasks.
Which is cheaper, claude-sonnet-4-6 or gpt-5?
gpt-5 is cheaper. claude-sonnet-4-6 costs $3.00/$15.00 per 1M input/output tokens, while gpt-5 costs $1.25/$10.00.
Can I use claude-sonnet-4-6 and gpt-5 through the same API?
Yes. Requesty provides a single OpenAI-compatible API that routes to both. Change just the "model" parameter to switch between "anthropic/claude-sonnet-4-6" and "openai/gpt-5", no other code changes needed.
What are the context windows?
claude-sonnet-4-6 supports up to 1M tokens of context. gpt-5 supports up to 400K tokens. Longer context means you can feed larger documents or codebases in a single prompt, though quality often degrades past 128K for most models.

Switch between claude-sonnet-4-6 and gpt-5 with one line of code

Requesty provides a single OpenAI-compatible API for 600+ models. Change the model parameter, not your code.