AI model comparison
Claude Sonnet 4.6 vs GPT-5.2-Codex
Pricing, context window, benchmarks, and features compared side by side. Or skip the guesswork and send one prompt to both.
Anthropic
Claude Sonnet 4.6
Sonnet 4.6 is Anthropic's most capable Sonnet-class model yet, with frontier performance across coding, agents, and professional work.
- Input / 1M
- $3
- Output / 1M
- $15
- Context
- 1M
OpenAI
GPT-5.2-Codex
GPT-5.2-Codex is an upgraded version of GPT-5.1-Codex optimized for software engineering and coding workflows.
- Input / 1M
- $1.75
- Output / 1M
- $14
- Context
- 400K
At a glance
Quick verdict
How the two models stack up on the things people ask about most.
Lower price
GPT-5.2-Codex
1.3x cheaper for a typical chat
Higher intelligence score
Claude Sonnet 4.6
30.1 vs 28.5 on Artificial Analysis
Larger context window
Claude Sonnet 4.6
1M vs 400K tokens
Newer release
Claude Sonnet 4.6
Released February 17, 2026
Benchmarks
Benchmark scores
Independent scores from Artificial Analysis. Higher is better.
Intelligence index
Claude Sonnet 4.630.1GPT-5.2-Codex28.5Coding index
Claude Sonnet 4.663GPT-5.2-CodexNot availableAgentic index
Claude Sonnet 4.631.8GPT-5.2-CodexNot availablePricing
Claude Sonnet 4.6 vs GPT-5.2-Codex API pricing
Per-token API rates. Cheaper option highlighted.
| Metric | Claude Sonnet 4.6 | GPT-5.2-Codex |
|---|---|---|
| Input tokensPer 1M tokens | $3 | $1.75 |
| Output tokensPer 1M tokens | $15 | $14 |
| Cached input (read)Per 1M tokens | $0.30 | $0.18 |
| Cache writePer 1M tokens | $3.75 | Not available |
| Web searchPer request | $0.01 | $0.01 |
What it costs in practice
Estimated cost per 1,000 requests at standard rates. Coding and long-document figures also show the cost when the input is already cached.
Chat message
2K in, 500 out
Claude Sonnet 4.6$13.50GPT-5.2-Codex$10.50Coding task
30K in, 4K out
Claude Sonnet 4.6$150$69 cachedGPT-5.2-Codex$108.50$61.25 cachedLong document summary
150K in, 2K out
Claude Sonnet 4.6$480$75 cachedGPT-5.2-Codex$290.50$54.25 cachedSpecs
Context window and capabilities
How much each model can read, how much it can write, and what it accepts as input.
| Metric | Claude Sonnet 4.6 | GPT-5.2-Codex |
|---|---|---|
| Context window | 1M tokens | 400K tokens |
| Max output | 128K tokens | 128K tokens |
| Input types | File, Image, Text | Image, Text |
| Output types | Text | Text |
| Reasoning effort levels | Max, High, Medium, Low | Extra high, High, Medium, Low |
| Default reasoning effort | Medium | Medium |
| Release date | February 17, 2026 | January 14, 2026 |
Features
Supported features
API features available for each model.
| Metric | Claude Sonnet 4.6 | GPT-5.2-Codex |
|---|---|---|
| Tool calling | Supported | Supported |
| Structured outputs | Supported | Supported |
| JSON mode | Supported | Supported |
| Reasoning | Supported | Supported |
| Temperature | Supported | Not supported |
| Stop sequences | Supported | Not supported |
| Deterministic seed | Not supported | Supported |
| Verbosity control | Supported | Supported |
Keep exploring
More on these models
Other head-to-heads, the full model page, and the alternatives list for each model.
Claude Sonnet 4.6View full model details- Claude Sonnet 4.6 vs GLM 5.2
- Claude Sonnet 4.6 vs Claude Sonnet 5
- Claude Sonnet 4.6 vs Gemini 3.5 Flash
- Claude Sonnet 4.6 vs GPT-5.3-Codex
- Claude Sonnet 4.6 vs Claude Opus 4.6
- Claude Sonnet 4.6 vs GPT-5.2
- Claude Sonnet 4.6 vs Gemini 3.1 Pro Preview
- Claude Sonnet 4.6 vs Qwen3.7 Max
- Claude Sonnet 4.6 vs Claude Opus 4.5
- Claude Sonnet 4.6 vs Claude Sonnet 4.5
- Claude Sonnet 4.6 vs Claude Opus 4.1
- Claude Sonnet 4.6 vs Claude Sonnet 4
Our take
GPT-5.2-Codex is 1.3x cheaper for a typical chat. Claude Sonnet 4.6 scores higher on the Artificial Analysis Intelligence Index (30.1 vs 28.5). Claude Sonnet 4.6 has the larger context window (1M vs 400K tokens). The right pick depends on your workload, so the quickest way to settle it is to send the same prompt to both and compare.
FAQ
Frequently asked questions
Is Claude Sonnet 4.6 or GPT-5.2-Codex cheaper?
GPT-5.2-Codex is cheaper for a typical chat (2K input tokens and 500 output tokens). GPT-5.2-Codex costs $1.75 per 1M input tokens and $14 per 1M output tokens, while Claude Sonnet 4.6 costs $3 per 1M input tokens and $15 per 1M output tokens.
Which has a bigger context window, Claude Sonnet 4.6 or GPT-5.2-Codex?
Claude Sonnet 4.6 supports up to 1M tokens of context, compared with 400K for GPT-5.2-Codex.
Is Claude Sonnet 4.6 smarter than GPT-5.2-Codex?
On the Artificial Analysis Intelligence Index, Claude Sonnet 4.6 scores 30.1 and GPT-5.2-Codex scores 28.5, putting Claude Sonnet 4.6 ahead. Benchmarks don't capture everything, so the best test is running your own prompts through both.
Can I use Claude Sonnet 4.6 and GPT-5.2-Codex at the same time?
Yes. Shortcut Chat sends one prompt to multiple models at once, so you can see Claude Sonnet 4.6 and GPT-5.2-Codex answer side by side and keep the better response.
Why choose? Ask both.
Send one prompt to Claude Sonnet 4.6 and GPT-5.2-Codex at the same time. Compare the answers side by side and keep the best one.