Claude Opus 5.5 vs GPT-5.2-Codex
| Spec | Claude Opus 5.5 | GPT-5.2-Codex |
|---|---|---|
| Respan Index | 74.1 (#1) | 29.6 (#84) |
| Blended price per 1M | $4 | $4.81 |
| Context window | 1M | 400K |
| Input / output per 1M | $2 / $10 | $1.75 / $14 |
| Max output | 128K | 128K |
| Input | text, vision | text, vision |
| Released | 2026-09-22 | 2025-12-18 |
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.
| Category | Claude Opus 5.5 | GPT-5.2-Codex |
|---|---|---|
| Coding | 68.3 Claude Opus 5.5 | 18.2 GPT-5.2-Codex |
| Agents | 79.1 Claude Opus 5.5 | 21.5 GPT-5.2-Codex |
| Reasoning | 83.9 Claude Opus 5.5 | 35.6 GPT-5.2-Codex |
| Knowledge & language | 70.4 Claude Opus 5.5 | 34.4 GPT-5.2-Codex |
| Human preference | 61.4 Claude Opus 5.5 | 49.0 GPT-5.2-Codex |
Benchmarks both report
Claude Opus 5.5 leads on 8 of the 8 benchmarks both report. Higher is better. Each score links to where it was published.
| Benchmark | Claude Opus 5.5 | GPT-5.2-Codex |
|---|---|---|
| LMArena WebDev (LMArena) | 1810 | 1339 |
| LiveBench Agentic Coding (LiveBench) | 71.7% | 49.4% |
| LiveBench Coding (LiveBench) | 89.3% | 83.6% |
| LiveBench Data Analysis (LiveBench) | 80.3% | 78.2% |
| LiveBench Instruction Following (LiveBench) | 67% | 66.4% |
| LiveBench Language (LiveBench) | 86.3% | 73.7% |
| LiveBench Mathematics (LiveBench) | 97.1% | 88.8% |
| LiveBench Reasoning (LiveBench) | 92.2% | 77.7% |
FAQ
Is Claude Opus 5.5 better than GPT-5.2-Codex?
Claude Opus 5.5 scores 74.1 on the Respan Index (#1), ahead of GPT-5.2-Codex at 29.6 (#84). Claude Opus 5.5 leads on 8 of the 8 benchmarks both report.
Which is cheaper, Claude Opus 5.5 or GPT-5.2-Codex?
Claude Opus 5.5 lists at $2 input and $10 output per 1M tokens; GPT-5.2-Codex at $1.75 and $14. Claude Opus 5.5 is 1.2x cheaper per token at list price.
Which has the larger context window?
Claude Opus 5.5 accepts 1M tokens and GPT-5.2-Codex 400K tokens.