Compare/Claude 4 Opus (Non-reasoning) vs GPT-4 Turbo

Claude 4 Opus (Non-reasoning)vsGPT-4 Turbo

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

Anthropic

Claude 4 Opus (Non-reasoning)

Input
$15/M
Output
$75/M
Speed
39 tok/s
TTFT
1.24s
OpenAI

GPT-4 Turbo

Input
$10/M
Output
$30/M
Speed
30 tok/s
TTFT
0.87s

Winner by Category

Cheaper
GPT-4 Turbo
Faster (tok/s)
Claude 4 Opus (Non-reasoning)
Lower Latency
GPT-4 Turbo
Benchmarks (10-1)
Claude 4 Opus (Non-reasoning)

Pricing Comparison

MetricClaude 4 Opus (Non-reasoning)GPT-4 Turbo
Input ($/M tokens)$15$10
Output ($/M tokens)$75$30
Cost for 1M input + 100K output tokens:
Claude 4 Opus (Non-reasoning)$22.50
GPT-4 Turbo$13.00

Speed Comparison

Output Speed (tokens/s) — higher is better
Claude 4 Opus (Non-reasoning)
39 tok/s
GPT-4 Turbo
30 tok/s
Time to First Token (seconds) — lower is better
Claude 4 Opus (Non-reasoning)
1.24s
GPT-4 Turbo
0.87s

Benchmark Comparison

Data from Artificial Analysis API — 12 benchmarks

Intelligence Index
33.013.7
Coding Index
21.5
Math Index
36.3
GPQA Diamond
70.1%
MMLU-Pro
86.0%69.4%
LiveCodeBench
54.2%29.1%
AIME 2025
36.3%
MATH-500
94.1%73.7%
Humanity's Last Exam
5.9%3.3%
SciCode
40.9%31.9%
IFBench
43.3%
TerminalBench
Claude 4 Opus (Non-reasoning)10 wins
1 winsGPT-4 Turbo

Frequently Asked Questions

Which is cheaper, Claude 4 Opus (Non-reasoning) or GPT-4 Turbo?

GPT-4 Turbo is cheaper overall. Its blended price (3:1 input/output ratio) is $15.00/M tokens vs $30.00/M for Claude 4 Opus (Non-reasoning).

Which model performs better on benchmarks?

Claude 4 Opus (Non-reasoning) wins 10 out of 12 benchmarks compared to 1 for GPT-4 Turbo. See the detailed benchmark chart above for per-category results.

Which is faster for real-time applications?

Claude 4 Opus (Non-reasoning) generates tokens faster at 39 tok/s vs 30 tok/s. However, GPT-4 Turbo has lower time-to-first-token (0.87s vs 1.24s).

When should I use Claude 4 Opus (Non-reasoning) vs GPT-4 Turbo?

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