Skip to main content

GPT-5.2-Codex vs GPT-6 Astra

SpecGPT-5.2-CodexGPT-6 Astra
Respan Index30.1 (#91)72.3 (#7)
Blended price per 1M$4.81$20
Context window400K1.1M
Input / output per 1M$1.75 / $14$10 / $50
Max output128K128K
Inputtext, visiontext, vision
Released2025-12-182026-09-03

Respan Index by category

Each category is scored 0 to 100, and how far ahead the winner is. Leads under a point are close to even.

CategoryGPT-5.2-CodexGPT-6 Astra
Coding18.8 GPT-5.2-Codex58.5 GPT-6 Astra
Agents22.4 GPT-5.2-Codex78.3 GPT-6 Astra
Reasoning35.7 GPT-5.2-Codex86.0 GPT-6 Astra
Knowledge & language34.4 GPT-5.2-Codex75.6 GPT-6 Astra
Human preference49.4 GPT-5.2-Codex60.1 GPT-6 Astra

How the Respan Index works

Benchmarks both report

GPT-6 Astra leads on 7 of the 8 benchmarks both report. Higher is better. Each score links to where it was published.

BenchmarkGPT-5.2-CodexGPT-6 Astra
LMArena WebDev (LMArena)13391763
LiveBench Agentic Coding (LiveBench)49.4%57.3%
LiveBench Coding (LiveBench)83.6%80.4%
LiveBench Data Analysis (LiveBench)78.2%83%
LiveBench Instruction Following (LiveBench)66.4%75.6%
LiveBench Language (LiveBench)73.7%89.4%
LiveBench Mathematics (LiveBench)88.8%96.8%
LiveBench Reasoning (LiveBench)77.7%92.7%

FAQ

Is GPT-5.2-Codex better than GPT-6 Astra?

GPT-6 Astra scores 72.3 on the Respan Index (#7), ahead of GPT-5.2-Codex at 30.1 (#91). GPT-6 Astra leads on 7 of the 8 benchmarks both report.

Which is cheaper, GPT-5.2-Codex or GPT-6 Astra?

GPT-5.2-Codex lists at $1.75 input and $14 output per 1M tokens; GPT-6 Astra at $10 and $50. GPT-5.2-Codex is 4.2x cheaper per token at list price.

Which has the larger context window?

GPT-5.2-Codex accepts 400K tokens and GPT-6 Astra 1.1M tokens.

Compare other models

vs

Built for AI agents.
Break less.
Ship more.