# GPT-5.1-Codex vs GPT-5.3 Codex

> Side-by-side benchmark comparison for GPT-5.1-Codex and GPT-5.3 Codex across agentic, coding, multimodal, knowledge, reasoning, multilingual, and math tasks.

- Canonical page: https://benchlm.ai/compare/gpt-5-1-codex-vs-gpt-5-3-codex
- Last updated: September 4, 2026

- Shared sourced benchmarks: 3
- HTML indexing: indexable
- Ranking lane: BenchAlign v5

## Quick Verdict

Evidence is too thin for a benchmark verdict: GPT-5.1-Codex and GPT-5.3 Codex share only 3 sourced benchmark rows.

## Summary

- Only 3 shared sourced benchmark rows are available. That is not enough for a broad capability verdict, so this mirror does not name an overall winner.
- GPT-5.1-Codex has the lower published output-token price.

## Model Snapshot

| Property | GPT-5.1-Codex | GPT-5.3 Codex |
|----------|----------|----------|
| Creator | OpenAI | OpenAI |
| Type | Proprietary | Proprietary |
| Reasoning | Reasoning | Reasoning |
| Context | 400K | 400K |
| Independent public score (not head-to-head) | 51.62 | 65.22 |
| Benchmarks Covered | 3 | 8 |
| Pricing (input/output) | $1.25 / $10.00 | $1.75 / $14.00 |

## Category Breakdown

### Agentic

- Winner: Insufficient shared evidence
- GPT-5.1-Codex public-lane score: 51.4 (Estimated · #54/151)
- GPT-5.3 Codex public-lane score: 62.3 (Estimated · #19/151)

| Benchmark | GPT-5.1-Codex | GPT-5.3 Codex | Winner |
|-----------|-----------|-----------|--------|
| Gert Labs | 49.68% | 57.47% | GPT-5.3 Codex |
| JobBench | 26.2% | 33.7% | GPT-5.3 Codex |
| Terminal-Bench 2.0 | Coming soon | 77.3% | Coming soon |
| OSWorld-Verified | Coming soon | 64.7% | Coming soon |

### Coding

- Winner: Insufficient shared evidence
- GPT-5.1-Codex public-lane score: 47.4 (Estimated · #89/183)
- GPT-5.3 Codex public-lane score: 62.7 (Supported · #16/183)

| Benchmark | GPT-5.1-Codex | GPT-5.3 Codex | Winner |
|-----------|-----------|-----------|--------|
| Vibe Code Bench | 13.12% | 61.77% | GPT-5.3 Codex |
| SWE-bench Verified | Coming soon | 85% | Coming soon |
| SWE-bench Pro | Coming soon | 56.8% | Coming soon |
| SWE-Rebench | Coming soon | 58.2% | Coming soon |

### Multimodal & Grounded

- Winner: Insufficient shared evidence
- GPT-5.1-Codex public-lane score: 66.8 (Unranked · 1 rankable row)
- GPT-5.3 Codex public-lane score: 75.6 (Unranked · 1 rankable row)

### Reasoning

- Winner: Insufficient shared evidence
- GPT-5.1-Codex public-lane score: 70.6 (Unranked · 2 rankable rows)
- GPT-5.3 Codex public-lane score: 77.3 (Unranked · 2 rankable rows)

### Knowledge

- Winner: Insufficient shared evidence
- GPT-5.1-Codex public-lane score: 53.3 (Estimated · #69/181)
- GPT-5.3 Codex public-lane score: 66.3 (Estimated · #22/181)

### Instruction Following

- Winner: Insufficient shared evidence
- GPT-5.1-Codex public-lane score: 85.3 (#42/120)
- GPT-5.3 Codex public-lane score: 92.3 (#15/120)

## FAQ

### Is there enough evidence to pick between GPT-5.1-Codex and GPT-5.3 Codex?

Not yet. The models share only 3 sourced benchmark rows, so this mirror reports the available measurements and metadata without naming a broad winner.

### What can I compare safely on this page?

Published pricing, context windows, model type, and individual shared benchmark rows are directly comparable. Independent overall scores and non-overlapping benchmark coverage are labeled separately and should not be read as a controlled head-to-head result.

## Related Comparisons

- [GPT-5.1-Codex vs GPT-5.3-Codex-Spark](/compare/gpt-5-1-codex-vs-gpt-5-3-codex-spark)
- [GPT-5.3 Codex vs GPT-5.3-Codex-Spark](/compare/gpt-5-3-codex-vs-gpt-5-3-codex-spark)
- [GPT-5.1-Codex vs Claude Fable 5.1](/compare/claude-fable-5-1-vs-gpt-5-1-codex)
- [GPT-5.3 Codex vs Claude Fable 5.1](/compare/claude-fable-5-1-vs-gpt-5-3-codex)

## Explore More

- [GPT-5.1-Codex profile](/models/gpt-5-1-codex)
- [GPT-5.3 Codex profile](/models/gpt-5-3-codex)
- [Compare Pricing](/llm-pricing)
- [Alternative Finder](/tools/alternative-finder)
- [LLM Selector](/tools/llm-selector)
- [Overall Rankings](/best/overall)