GPT-5 vs GPT-5.1
Side-by-side benchmark comparison across coding, math, reasoning, speed, and pricing.
GPT-5.1 by OpenAI wins on 9 of 19 benchmarks against GPT-5 by OpenAI, 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-5.1 scores 1464 on Chatbot Arena ELO compared to GPT-5's 1390, while both score 86.0% on MMLU-Pro, while GPT-5.1 scores 91.0% on IFEval compared to GPT-5's 90.0%.
Coding: In coding, GPT-5.1 scores 93.0% on HumanEval+ compared to GPT-5's 92.0%, while GPT-5.1 scores 76.3% on SWE-bench Verified compared to GPT-5's 74.9%, while GPT-5.1 scores 82.0% on LiveCodeBench compared to GPT-5's 78.0%, while both score 59.2% on BFCL, while GPT-5.1 scores 49.4 on AA Coding Index compared to GPT-5's 37.8.
Math: In math, GPT-5.1 scores 95.0% on MATH compared to GPT-5's 94.6%, while GPT-5.1 scores 98.5% on GSM8K compared to GPT-5's 98.0%, while GPT-5 scores 94.6% on AIME 2025 compared to GPT-5.1's 94.0%.
Reasoning: In reasoning, GPT-5.1 scores 88.1% on GPQA Diamond compared to GPT-5's 87.3%, while both score 50.0% on ARC-AGI.
Context: In context, both score 400K on Context Length.
Pricing Comparison
GPT-5 costs $1.3/1M input tokens and $10.0/1M output tokens, while GPT-5.1 costs $1.3/1M input and $10.0/1M output. Both models are priced identically for input tokens.
Speed Comparison
GPT-5 generates output at 100 tok/s compared to GPT-5.1's 95 tok/s, and the time to first token is 320 ms for GPT-5 versus 350 ms for GPT-5.1. GPT-5 delivers faster throughput.
Verdict
For developers prioritizing speed, GPT-5 has the edge. For those who value coding and general intelligence and math, GPT-5.1 is the stronger choice.
View Individual Model Pages
GPT-5 vs GPT-5.1 — FAQ
Which is better, GPT-5 or GPT-5.1?
GPT-5.1 wins on more benchmarks overall (9 vs 3). However, the best choice depends on your specific needs — each model excels in different areas.
How does GPT-5 compare to GPT-5.1 for coding?
GPT-5.1 is better for coding, scoring 76.3% on SWE-bench Verified compared to 74.9%. SWE-bench tests real-world software engineering by resolving actual GitHub issues.
Is GPT-5 cheaper than GPT-5.1?
Both models are priced the same at $1.3/1M input tokens. GPT-5 output costs $10.0/1M and GPT-5.1 output costs $10.0/1M.
Which is faster, GPT-5 or GPT-5.1?
GPT-5 is faster, generating output at 100 tok/s compared to 95 tok/s. Faster output speed means shorter wait times for API responses.
What benchmarks does the GPT-5 vs GPT-5.1 comparison cover?
This comparison covers 19 benchmarks including Chatbot Arena ELO, MMLU-Pro, HumanEval+, IFEval, MATH, GPQA Diamond, SWE-bench Verified, Output Speed, and more. Metrics span general intelligence, coding, math, reasoning, speed, and cost categories.