Compare/GPT-4 vs Claude 3 Opus

GPT-4vsClaude 3 Opus

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

OpenAI

GPT-4

Input
$30/M
Output
$60/M
Speed
38 tok/s
TTFT
0.82s
Anthropic

Claude 3 Opus

Input
$15/M
Output
$75/M
Speed
TTFT

Winner by Category

Cheaper
Claude 3 Opus
Faster (tok/s)
GPT-4
Lower Latency
Claude 3 Opus
Benchmarks (0-8)
Claude 3 Opus

Pricing Comparison

MetricGPT-4Claude 3 Opus
Input ($/M tokens)$30$15
Output ($/M tokens)$60$75
Cost for 1M input + 100K output tokens:
GPT-4$36.00
Claude 3 Opus$22.50

Speed Comparison

Output Speed (tokens/s) — higher is better
GPT-4
38 tok/s
Claude 3 Opus
Time to First Token (seconds) — lower is better
GPT-4
0.82s
Claude 3 Opus

Benchmark Comparison

Data from Artificial Analysis API — 12 benchmarks

Intelligence Index
12.818.0
Coding Index
13.119.5
Math Index
GPQA Diamond
48.9%
MMLU-Pro
69.6%
LiveCodeBench
27.9%
AIME 2025
MATH-500
64.1%
Humanity's Last Exam
3.1%
SciCode
23.3%
IFBench
TerminalBench
GPT-40 wins
8 winsClaude 3 Opus

Frequently Asked Questions

Which is cheaper, GPT-4 or Claude 3 Opus?

Claude 3 Opus is cheaper overall. Its blended price (3:1 input/output ratio) is $30.00/M tokens vs $37.50/M for GPT-4.

Which model performs better on benchmarks?

Claude 3 Opus wins 8 out of 12 benchmarks compared to 0 for GPT-4. See the detailed benchmark chart above for per-category results.

Which is faster for real-time applications?

GPT-4 generates tokens faster at 38 tok/s vs 0 tok/s. However, Claude 3 Opus has lower time-to-first-token (0.00s vs 0.82s).

When should I use GPT-4 vs Claude 3 Opus?

Choose based on your priorities: Claude 3 Opus for lower cost, Claude 3 Opus for stronger benchmark performance, and GPT-4 for faster generation. For latency-sensitive apps, check the TTFT comparison above.