GPT-5.1 Codex (high) vs Gemini 2.5 Pro

Comparing 2 AI models · 6 benchmarks · OpenAI, Google

Most Affordable
OpenAI logo
GPT-5.1 Codex (high)
$1.25/1M
Highest Intelligence
OpenAI logo
GPT-5.1 Codex (high)
86.0% GPQA
Best for Coding
OpenAI logo
GPT-5.1 Codex (high)
35.1 Coding Index
Price Difference
1.0x
input cost range

Composite Indices

Intelligence, Coding, Math

Standard Benchmarks

Academic and industry benchmarks

Benchmark Winners

6 tests
OpenAI logo

GPT-5.1 Codex (high)

4
  • GPQA
  • HLE
  • LiveCodeBench
  • AIME 2025
Google logo

Gemini 2.5 Pro

2
  • MMLU Pro
  • MATH 500
Metric
OpenAI logo GPT-5.1 Codex (high)
OpenAI
Google logo Gemini 2.5 Pro
Google
Pricing
Per 1M tokens
Input Cost $1.25/1M $1.25/1M
Output Cost $10.00/1M $10.00/1M
Blended Cost 3:1 input/output ratio
$3.44/1M $3.44/1M
Specifications
Organization Model creator
OpenAI Google
Release Date Launch date
Nov 13, 2025 Jun 5, 2025
Performance & Speed
Throughput Output speed
190.0 tok/s 154.7 tok/s
Time to First Token (TTFT) Initial response delay
15165ms 35671ms
Latency Time to first answer token
15165ms 35671ms
Composite Indices
Intelligence Index Overall reasoning capability
41.5 34.1
Coding Index Programming ability
35.1 30.8
Math Index Mathematical reasoning
95.7 87.7
Standard Benchmarks
GPQA Graduate-level reasoning
86.0% 84.4%
MMLU Pro Advanced knowledge
86.0% 86.2%
HLE Hard language evaluation
23.4% 21.1%
LiveCodeBench Real-world coding tasks
84.9%