Claude 3 Opus vs GPT-4o

Side-by-side benchmark comparison across coding, math, reasoning, speed, and pricing.

GPT-4o by OpenAI wins on 17 of 20 benchmarks against Claude 3 Opus by Anthropic, which leads on 3. This head-to-head comparison covers coding, math, reasoning, speed, and pricing metrics from our benchmark data.

Category-by-Category Breakdown

General Intelligence: In general intelligence, GPT-4o scores 1280 on Chatbot Arena ELO compared to Claude 3 Opus's 1240, while GPT-4o scores 72.6% on MMLU-Pro compared to Claude 3 Opus's 68.0%, while GPT-4o scores 9.3 on MT-Bench compared to Claude 3 Opus's 8.8, while GPT-4o scores 85.3% on IFEval compared to Claude 3 Opus's 82.0%, while GPT-4o scores 40.1% on SimpleQA compared to Claude 3 Opus's 29.0%, while GPT-4o scores 83.5% on TruthfulQA compared to Claude 3 Opus's 81.0%.

Coding: In coding, GPT-4o scores 87.2% on HumanEval+ compared to Claude 3 Opus's 78.0%, while GPT-4o scores 30.7% on SWE-bench Verified compared to Claude 3 Opus's 22.0%, while GPT-4o scores 38.0% on LiveCodeBench compared to Claude 3 Opus's 32.0%.

Math: In math, GPT-4o scores 74.6% on MATH compared to Claude 3 Opus's 68.0%, while GPT-4o scores 92.0% on GSM8K compared to Claude 3 Opus's 88.0%.

Reasoning: In reasoning, Claude 3 Opus scores 59.4% on GPQA Diamond compared to GPT-4o's 53.6%, while Claude 3 Opus scores 8.0% on ARC-AGI compared to GPT-4o's 5.0%, while GPT-4o scores 87.3% on BBH compared to Claude 3 Opus's 86.8%, while GPT-4o scores 92.5% on Winogrande compared to Claude 3 Opus's 90.5%.

Context: In context, Claude 3 Opus scores 200K on Context Length compared to GPT-4o's 128K.

Pricing Comparison

Claude 3 Opus costs $15.0/1M input tokens and $75.0/1M output tokens, while GPT-4o costs $2.5/1M input and $10.0/1M output. GPT-4o is the more affordable option for API usage.

Speed Comparison

Claude 3 Opus generates output at 25 tok/s compared to GPT-4o's 143 tok/s, and the time to first token is 800 ms for Claude 3 Opus versus 450 ms for GPT-4o. GPT-4o delivers faster throughput.

Verdict

GPT-4o leads across the board in coding, general intelligence, math, affordability, speed, making it the stronger overall choice in this comparison.

View Individual Model Pages

Claude 3 Opus vs GPT-4o — FAQ

Which is better, Claude 3 Opus or GPT-4o?

GPT-4o wins on more benchmarks overall (17 vs 3). However, the best choice depends on your specific needs — each model excels in different areas.

How does Claude 3 Opus compare to GPT-4o for coding?

GPT-4o is better for coding, scoring 30.7% on SWE-bench Verified compared to 22.0%. SWE-bench tests real-world software engineering by resolving actual GitHub issues.

Is Claude 3 Opus cheaper than GPT-4o?

Yes, GPT-4o is cheaper. Claude 3 Opus costs $15.0/1M input and $75.0/1M output tokens. GPT-4o costs $2.5/1M input and $10.0/1M output tokens.

Which is faster, Claude 3 Opus or GPT-4o?

GPT-4o is faster, generating output at 143 tok/s compared to 25 tok/s. Faster output speed means shorter wait times for API responses.

What benchmarks does the Claude 3 Opus vs GPT-4o comparison cover?

This comparison covers 20 benchmarks including Chatbot Arena ELO, MMLU-Pro, HumanEval+, MT-Bench, IFEval, SimpleQA, MATH, TruthfulQA, and more. Metrics span general intelligence, coding, math, reasoning, speed, and cost categories.