Compare/Claude 3.7 Sonnet (Non-reasoning) vs GPT-4o (May '24)

Claude 3.7 Sonnet (Non-reasoning)vsGPT-4o (May '24)

Side-by-side comparison of pricing, 12 benchmarks, and generation speed.

Anthropic

Claude 3.7 Sonnet (Non-reasoning)

Input
$3/M
Output
$15/M
Speed
TTFT
OpenAI

GPT-4o (May '24)

Input
$5/M
Output
$15/M
Speed
78 tok/s
TTFT
0.54s

Winner by Category

Cheaper
Claude 3.7 Sonnet (Non-reasoning)
Faster (tok/s)
GPT-4o (May '24)
Lower Latency
Claude 3.7 Sonnet (Non-reasoning)
Benchmarks (12-0)
Claude 3.7 Sonnet (Non-reasoning)

Pricing Comparison

MetricClaude 3.7 Sonnet (Non-reasoning)GPT-4o (May '24)
Input ($/M tokens)$3$5
Output ($/M tokens)$15$15
Cost for 1M input + 100K output tokens:
Claude 3.7 Sonnet (Non-reasoning)$4.50
GPT-4o (May '24)$6.50

Speed Comparison

Output Speed (tokens/s) — higher is better
Claude 3.7 Sonnet (Non-reasoning)
GPT-4o (May '24)
78 tok/s
Time to First Token (seconds) — lower is better
Claude 3.7 Sonnet (Non-reasoning)
GPT-4o (May '24)
0.54s

Benchmark Comparison

Data from Artificial Analysis API — 12 benchmarks

Intelligence Index
30.814.5
Coding Index
26.724.2
Math Index
21.0
GPQA Diamond
65.6%52.6%
MMLU-Pro
80.3%74.0%
LiveCodeBench
39.4%33.4%
AIME 2025
21.0%
MATH-500
85.0%79.1%
Humanity's Last Exam
4.8%2.8%
SciCode
37.6%30.9%
IFBench
44.0%
TerminalBench
21.2%
Claude 3.7 Sonnet (Non-reasoning)12 wins
0 winsGPT-4o (May '24)

Frequently Asked Questions

Which is cheaper, Claude 3.7 Sonnet (Non-reasoning) or GPT-4o (May '24)?

Claude 3.7 Sonnet (Non-reasoning) is cheaper overall. Its blended price (3:1 input/output ratio) is $6.00/M tokens vs $7.50/M for GPT-4o (May '24).

Which model performs better on benchmarks?

Claude 3.7 Sonnet (Non-reasoning) wins 12 out of 12 benchmarks compared to 0 for GPT-4o (May '24). See the detailed benchmark chart above for per-category results.

Which is faster for real-time applications?

GPT-4o (May '24) generates tokens faster at 78 tok/s vs 0 tok/s. Claude 3.7 Sonnet (Non-reasoning) also has lower time-to-first-token (0.00s vs 0.54s).

When should I use Claude 3.7 Sonnet (Non-reasoning) vs GPT-4o (May '24)?

Choose based on your priorities: Claude 3.7 Sonnet (Non-reasoning) for lower cost, Claude 3.7 Sonnet (Non-reasoning) for stronger benchmark performance, and GPT-4o (May '24) for faster generation. For latency-sensitive apps, check the TTFT comparison above.