# GPT-5 vs GPT-5.2-Codex

> Side-by-side benchmark comparison for GPT-5 and GPT-5.2-Codex across agentic, coding, multimodal, knowledge, reasoning, multilingual, and math tasks.

- Canonical page: https://benchlm.ai/compare/gpt-5-vs-gpt-5-2-codex
- Last updated: November 18, 2026

- Shared sourced benchmarks: 4
- HTML indexing: indexable
- Ranking lane: BenchAlign v5.8

## Quick Verdict

GPT-5.2-Codex leads by point estimate. Conditional score ranges do not establish rank confidence. Choose using the category evidence and your own workload tests.

## Summary

- GPT-5.2-Codex has the higher overall point estimate 54.17 to 48.96. Conditional score ranges do not establish rank confidence.
- The clearest category separation is in coding, where the averages are 36.7 for GPT-5 and 44.8 for GPT-5.2-Codex.
- The biggest single benchmark swing is Vibe Code Bench in Coding, with scores of 20.09% and 37.91%.
- GPT-5 is the cheaper option on output tokens, which matters if you expect large responses or heavy interactive use.
- GPT-5.2-Codex also has the larger context window at 400K.

## Model Snapshot

| Property | GPT-5 | GPT-5.2-Codex |
|----------|----------|----------|
| Creator | OpenAI | OpenAI |
| Type | Proprietary | Proprietary |
| Reasoning | Reasoning | Reasoning |
| Context | 128K | 400K |
| Overall Score | 48.96 | 54.17 |
| Benchmarks Covered | 6 | 6 |
| Pricing (input/output) | $1.25 / $10.00 | $1.75 / $14.00 |

## Category Breakdown

### Agentic

- Winner: Not comparable
- GPT-5 public-lane score: Coming soon
- GPT-5.2-Codex public-lane score: 43.7 (Estimated · #71/138)

| Benchmark | GPT-5 | GPT-5.2-Codex | Winner |
|-----------|-----------|-----------|--------|
| JobBench | 8.5% | 26.0% | GPT-5.2-Codex |
| Gert Labs | Coming soon | 51.79% | Coming soon |

### Coding

- Winner: Directional only
- GPT-5 public-lane score: 36.7 (Estimated · #85/160)
- GPT-5.2-Codex public-lane score: 44.8 (Supported · #59/160)

| Benchmark | GPT-5 | GPT-5.2-Codex | Winner |
|-----------|-----------|-----------|--------|
| Vibe Code Bench | 20.09% | 37.91% | GPT-5.2-Codex |
| LiveCodeBench (Vals) | 85.9% | 88.0% | GPT-5.2-Codex |
| SWE-bench (Vals) | 69.0% | 72.4% | GPT-5.2-Codex |
| PostTrainBench v1 | Coming soon | 17.2% | Coming soon |

### Reasoning

- Winner: Directional only
- GPT-5 public-lane score: 43.7 (Estimated · #75/159)
- GPT-5.2-Codex public-lane score: 43.2 (Estimated · #77/159)

### Knowledge

- Winner: Directional only
- GPT-5 public-lane score: 53.1 (Supported · #67/179)
- GPT-5.2-Codex public-lane score: 56.7 (Estimated · #62/179)

| Benchmark | GPT-5 | GPT-5.2-Codex | Winner |
|-----------|-----------|-----------|--------|
| GPQA Diamond (Vals) | 85.6% | Coming soon | Coming soon |
| MMLU-Pro (Vals) | 86.5% | Coming soon | Coming soon |

### Instruction Following

- Winner: Directional only
- GPT-5 public-lane score: 89.4 (#35/157)
- GPT-5.2-Codex public-lane score: 93.8 (#6/157)

## FAQ

### Which is better overall, GPT-5 or GPT-5.2-Codex?

GPT-5.2-Codex has the higher overall point estimate. Conditional score ranges do not establish rank confidence.

### Where is the biggest gap between GPT-5 and GPT-5.2-Codex?

The widest category gap is in coding, where the averages are 36.7 for GPT-5 and 44.8 for GPT-5.2-Codex.

### How many benchmarks does GPT-5 cover on BenchLM?

GPT-5 currently has 6 sourced benchmark scores on BenchLM.

### How many benchmarks does GPT-5.2-Codex cover on BenchLM?

GPT-5.2-Codex currently has 6 sourced benchmark scores on BenchLM.

## Related Comparisons

- [GPT-5 vs GPT-5 mini](/compare/gpt-5-vs-gpt-5-mini)
- [GPT-5.2-Codex vs GPT-5 mini](/compare/gpt-5-2-codex-vs-gpt-5-mini)
- [GPT-5 vs GPT-5 nano](/compare/gpt-5-vs-gpt-5-nano)
- [GPT-5.2-Codex vs GPT-5 nano](/compare/gpt-5-2-codex-vs-gpt-5-nano)

## Explore More

- [GPT-5 profile](/models/gpt-5)
- [GPT-5.2-Codex profile](/models/gpt-5-2-codex)
- [Compare Pricing](/llm-pricing)
- [Alternative Finder](/tools/alternative-finder)
- [LLM Selector](/tools/llm-selector)
- [Overall Rankings](/best/overall)
