Gemini 3.1 Pro vs GPT-5.1 Codex
Side-by-side benchmark comparison across coding, math, reasoning, speed, and pricing.
Gemini 3.1 Pro by Google wins on 8 of 14 benchmarks against GPT-5.1 Codex by OpenAI, which leads on 6. This head-to-head comparison covers coding, math, reasoning, speed, and pricing metrics from the AI Value Index.
Category-by-Category Breakdown
General Intelligence: In general intelligence, Gemini 3.1 Pro scores 1501 on Chatbot Arena ELO compared to GPT-5.1 Codex's 1395, while Gemini 3.1 Pro scores 92.6% on MMLU-Pro compared to GPT-5.1 Codex's 82.0%.
Coding: In coding, GPT-5.1 Codex scores 96.0% on HumanEval+ compared to Gemini 3.1 Pro's 93.0%, while Gemini 3.1 Pro scores 80.6% on SWE-bench Verified compared to GPT-5.1 Codex's 78.0%, while GPT-5.1 Codex scores 85.0% on LiveCodeBench compared to Gemini 3.1 Pro's 75.0%.
Math: In math, Gemini 3.1 Pro scores 93.0% on MATH compared to GPT-5.1 Codex's 85.0%, while Gemini 3.1 Pro scores 98.0% on GSM8K compared to GPT-5.1 Codex's 95.0%.
Reasoning: In reasoning, Gemini 3.1 Pro scores 94.1% on GPQA Diamond compared to GPT-5.1 Codex's 65.0%, while Gemini 3.1 Pro scores 77.1% on ARC-AGI compared to GPT-5.1 Codex's 52.0%.
Context: In context, Gemini 3.1 Pro scores 1.0M on Context Length compared to GPT-5.1 Codex's 400K.
Pricing Comparison
Gemini 3.1 Pro costs $2.0/1M input tokens and $12.0/1M output tokens, while GPT-5.1 Codex costs $1.3/1M input and $10.0/1M output. GPT-5.1 Codex is the more affordable option for API usage.
Speed Comparison
Gemini 3.1 Pro generates output at 65 tok/s compared to GPT-5.1 Codex's 85 tok/s, and the time to first token is 420 ms for Gemini 3.1 Pro versus 400 ms for GPT-5.1 Codex. GPT-5.1 Codex delivers faster throughput.
Verdict
For developers prioritizing coding and general intelligence and math, Gemini 3.1 Pro has the edge. For those who value affordability and speed, GPT-5.1 Codex is the stronger choice.
View Individual Model Pages
Gemini 3.1 Pro vs GPT-5.1 Codex — FAQ
Which is better, Gemini 3.1 Pro or GPT-5.1 Codex?
Gemini 3.1 Pro wins on more benchmarks overall (8 vs 6). However, the best choice depends on your specific needs — each model excels in different areas.
How does Gemini 3.1 Pro compare to GPT-5.1 Codex for coding?
Gemini 3.1 Pro is better for coding, scoring 80.6% on SWE-bench Verified compared to 78.0%. SWE-bench tests real-world software engineering by resolving actual GitHub issues.
Is Gemini 3.1 Pro cheaper than GPT-5.1 Codex?
Yes, GPT-5.1 Codex is cheaper. Gemini 3.1 Pro costs $2.0/1M input and $12.0/1M output tokens. GPT-5.1 Codex costs $1.3/1M input and $10.0/1M output tokens.
Which is faster, Gemini 3.1 Pro or GPT-5.1 Codex?
GPT-5.1 Codex is faster, generating output at 85 tok/s compared to 65 tok/s. Faster output speed means shorter wait times for API responses.
What benchmarks does the Gemini 3.1 Pro vs GPT-5.1 Codex comparison cover?
This comparison covers 14 benchmarks including Chatbot Arena ELO, MMLU-Pro, HumanEval+, MATH, SWE-bench Verified, GPQA Diamond, Output Speed, Time to First Token, and more. Metrics span general intelligence, coding, math, reasoning, speed, and cost categories.