Model Comparison

Claude 4 Sonnet (Non-reasoning) vs GPT-4o mini

Anthropic vs OpenAI

OpenAI's GPT-4o mini costs less per intelligence point, even though Anthropic's Claude 4 Sonnet (Non-reasoning) scores higher.

Data last updated March 4, 2026

GPT-4o mini delivers more intelligence per dollar, while Claude 4 Sonnet (Non-reasoning) leads on raw benchmark scores. Claude 4 Sonnet (Non-reasoning) costs $0.03 per request vs $0.0014 for GPT-4o mini (at 5K input / 1K output tokens). The question is whether Claude 4 Sonnet (Non-reasoning)'s higher scores justify the 22x price premium.

Benchmarks & Performance

Metric Claude 4 Sonnet (Non-reasoning) GPT-4o mini
Intelligence Index 33.0 12.6
MMLU-Pro 0.8 0.6
GPQA 0.7 0.4
AIME 0.4 0.1
Output tokens/sec 48.5 50.9
Time to first token 1.03s 0.47s
Context window 200,000 128,000

Pricing per 1M Tokens

List prices as published by the provider. Not adjusted for token efficiency.

Metric Claude 4 Sonnet (Non-reasoning) GPT-4o mini
Input price / 1M tokens $3.00 $0.15
Output price / 1M tokens $15.00 $0.60
Cache hit price / 1M tokens $0.30 $0.08

Intelligence vs Price

10 15 20 25 30 35 40 $0.001 $0.002 $0.005 $0.01 $0.02 $0.05 Typical request cost (5K input + 1K output) Intelligence Index Gemini 2.5 Pro DeepSeek R1 0528 GPT-4.1 GPT-4.1 mini Claude 4.5 Sonn... Gemini 2.5 Flas... Grok 3 mini Rea... Claude 4 Sonnet (Non-reasoning) GPT-4o mini
Claude 4 Sonnet (Non-reasoning) GPT-4o mini Other models

Value Analysis

Cost per IQ point based on a typical request of 5,000 input and 1,000 output tokens.

Cheaper (list price)

GPT-4o mini

Higher Benchmarks

Claude 4 Sonnet (Non-reasoning)

Better Value ($/IQ point)

GPT-4o mini

Claude 4 Sonnet (Non-reasoning)

$0.0009 / IQ point

GPT-4o mini

$0.0001 / IQ point

Frequently Asked Questions

How much cheaper is GPT-4o mini than Claude 4 Sonnet (Non-reasoning)?

GPT-4o mini is dramatically cheaper — 22x less per request than Claude 4 Sonnet (Non-reasoning). GPT-4o mini is cheaper on both input ($0.15/M vs $3.0/M) and output ($0.6/M vs $15.0/M). At a fraction of the cost, GPT-4o mini saves significantly in production workloads. This comparison assumes a typical request of 5,000 input and 1,000 output tokens (5:1 ratio). Actual ratios vary by workload — chat and completion tasks typically run 2:1, code review around 3:1, document analysis and summarization 10:1 to 50:1, and embedding workloads are pure input with no output tokens.

How much does Claude 4 Sonnet (Non-reasoning) outperform GPT-4o mini on benchmarks?

Claude 4 Sonnet (Non-reasoning) scores higher overall (33.0 vs 12.6). Claude 4 Sonnet (Non-reasoning) leads on MMLU-Pro (0.84 vs 0.65), GPQA (0.68 vs 0.43), AIME (0.41 vs 0.12). If mathematical reasoning matters, Claude 4 Sonnet (Non-reasoning)'s AIME score of 0.41 gives it an edge.

Which generates output faster, Claude 4 Sonnet (Non-reasoning) or GPT-4o mini?

GPT-4o mini is 5% faster at 50.9 tokens per second compared to Claude 4 Sonnet (Non-reasoning) at 48.5 tokens per second. GPT-4o mini also starts generating sooner at 0.47s vs 1.03s time to first token. The speed difference matters for chatbots but is less relevant in batch processing.

Which has a larger context window, Claude 4 Sonnet (Non-reasoning) or GPT-4o mini?

Claude 4 Sonnet (Non-reasoning) has a 56% larger context window at 200,000 tokens vs GPT-4o mini at 128,000 tokens. That's roughly 266 vs 170 pages of text. The extra context capacity in Claude 4 Sonnet (Non-reasoning) matters for document analysis and long conversations.

Is GPT-4o mini worth choosing over Claude 4 Sonnet (Non-reasoning) on value alone?

GPT-4o mini offers dramatically better value — $0.0001 per intelligence point vs Claude 4 Sonnet (Non-reasoning) at $0.0009. GPT-4o mini is cheaper, which offsets Claude 4 Sonnet (Non-reasoning)'s higher benchmark scores to deliver more value per dollar. If raw benchmark scores matter less than cost for your use case, GPT-4o mini is the efficient choice.

Which model benefits more from prompt caching, Claude 4 Sonnet (Non-reasoning) or GPT-4o mini?

With prompt caching, GPT-4o mini is dramatically cheaper — 17x less per request than Claude 4 Sonnet (Non-reasoning). Caching saves 45% on Claude 4 Sonnet (Non-reasoning) and 28% on GPT-4o mini compared to standard input prices. Claude 4 Sonnet (Non-reasoning) benefits more from caching. If your workload has repetitive prompts, Claude 4 Sonnet (Non-reasoning)'s cache discount gives it a bigger cost advantage than list prices suggest.

Pricing verified against official vendor documentation. Updated daily. See our methodology.

Related Comparisons

Stop guessing. Start measuring.

Create an account, install the SDK, and see your first margin data in minutes.

See My Margin Data

No credit card required