# GPT-5.3 Codex vs o1

> GPT-5.3 Codex is the stronger model overall, scoring 45.5 to 40.6 on the Noometry Index.

- Canonical page: https://noometry.com/compare/gpt-5-3-codex-vs-o1
- Last updated: 2026-10-10
- Shared benchmarks: 3

## Summary

- They share 3 benchmarks with published results for both. GPT-5.3 Codex scores higher in 2 categories and o1 in 0 categories; 2 gaps are clear of the uncertainty.
- The widest gap is in agentic & tool use, where GPT-5.3 Codex leads 47.8 to 24.3.
- The biggest single-benchmark swing is WeirdML: 79.3% for GPT-5.3 Codex and 47.6% for o1.
- GPT-5.3 Codex is cheaper at $1.75 / $14 per million input/output tokens, against $15 / $60 for o1.
- GPT-5.3 Codex accepts more context: 400K tokens versus 200K.

## Snapshot

| | GPT-5.3 Codex | o1 |
|---|---|---|
| Provider | OpenAI | OpenAI |
| Noometry Index | 45.5 | 40.6 |
| Rank | 61 | 140 |
| Context | 400K | 200K |
| Input $/M | $1.75 | $15 |
| Output $/M | $14 | $60 |
| Weights | Proprietary | Proprietary |

## Coding

- GPT-5.3 Codex: 48.5 (#51)
- o1: 45.7 (#64)

| Benchmark | GPT-5.3 Codex | o1 |
|---|---|---|
| WeirdML | 79.3% | 47.6% |
| SWE-bench Verified | 74.8% | — |
| Aider Polyglot | — | 61.7% |
| LMArena WebDev | 1408 | — |
| LiveBench Coding | — | 69.7% |
| LMArena Coding | — | 1367 |
| CadEval | — | 56% |
| ALE-Bench | 1,655 | — |
| HumanEval+ | — | 89% |
| MBPP+ | — | 80.2% |

## Agentic & Tool Use

- GPT-5.3 Codex: 47.8 (#9)
- o1: 24.3 (#111)

| Benchmark | GPT-5.3 Codex | o1 |
|---|---|---|
| METR Time Horizons | 74.5% | 51.1% |
| Terminal-Bench | 78.4% | — |
| Cybench | — | 10% |
| Vending-Bench 2 | 5,940 | — |

## Reasoning

- GPT-5.3 Codex: —
- o1: 27.5 (#103)

| Benchmark | GPT-5.3 Codex | o1 |
|---|---|---|
| Epoch Capabilities Index | 156.84 | 141.92 |
| SimpleBench | — | 41.7% |
| ARC-AGI-1 | — | 30.7% |
| Chess Puzzles | — | 15% |
| EnigmaEval | — | 5.7% |
| LiveBench Reasoning | — | 91.6% |
| LMArena Hard Prompts | — | 1372 |
| DTBench | — | 74.7% |
| LiveBench Data Analysis | — | 65.5% |
| LMCA | — | 22.3% |
| LiveBench | — | 75.7% |

## Math

- GPT-5.3 Codex: —
- o1: 34.9 (#150)

| Benchmark | GPT-5.3 Codex | o1 |
|---|---|---|
| FrontierMath (Tiers 1-3) | — | 14.7% |
| OTIS Mock AIME 2024-2025 | — | 73.3% |
| LiveBench Math | — | 80.3% |
| LMArena Math | — | 1388 |
| MATH Level 5 | — | 94.7% |
| FrontierMath (Feb 2025 set) | — | 9.3% |

## Knowledge

- GPT-5.3 Codex: —
- o1: 41.5 (#101)

| Benchmark | GPT-5.3 Codex | o1 |
|---|---|---|
| GPQA Diamond | — | 76.8% |
| Humanity's Last Exam | — | 8% |
| SimpleQA Verified | — | 41.1% |
| Confabulations | — | 11.7% |
| LMArena Expert | — | 1362 |

## Multimodal

- GPT-5.3 Codex: —
- o1: 33.6 (#87)

| Benchmark | GPT-5.3 Codex | o1 |
|---|---|---|
| LMArena Vision | — | 1168 |
| GeoBench | — | 80% |
| VPCT | — | 37% |
| SpatialViz-Bench | — | 41.4% |

## Multilingual

- GPT-5.3 Codex: —
- o1: 48.8 (#137)

| Benchmark | GPT-5.3 Codex | o1 |
|---|---|---|
| LMArena Non-English | — | 1359 |
| LMArena Chinese | — | 1394 |
| LMArena French | — | 1343 |
| LMArena German | — | 1337 |
| LMArena Japanese | — | 1346 |
| LMArena Korean | — | 1396 |
| LMArena Russian | — | 1356 |
| LMArena Spanish | — | 1345 |

## Instruction Following

- GPT-5.3 Codex: —
- o1: 75.0 (#82)

| Benchmark | GPT-5.3 Codex | o1 |
|---|---|---|
| LiveBench Instruction Following | — | 81.5% |
| LMArena Instruction Following | — | 1368 |

## Long Context

- GPT-5.3 Codex: —
- o1: 50.3 (#9)

| Benchmark | GPT-5.3 Codex | o1 |
|---|---|---|
| Fiction.LiveBench | — | 83.3% |
| LMArena Longer Query | — | 1378 |

## Writing & Preference

- GPT-5.3 Codex: —
- o1: 55.8 (#139)

| Benchmark | GPT-5.3 Codex | o1 |
|---|---|---|
| LMArena Text | — | 1366 |
| LMArena Creative Writing | — | 1347 |
| Short-Story Creative Writing | — | 70.2% |
| LMArena Multi-Turn | — | 1368 |
| LiveBench Language | — | 65.4% |

## FAQ

### Is GPT-5.3 Codex better than o1?

GPT-5.3 Codex is the stronger model overall, scoring 45.5 to 40.6 on the Noometry Index.

### Which is cheaper, GPT-5.3 Codex or o1?

GPT-5.3 Codex is cheaper. It lists at $1.75 per million input tokens and $14 per million output tokens; o1 lists at $15 and $60.

### Is GPT-5.3 Codex or o1 better for coding?

GPT-5.3 Codex scores higher on coding benchmarks: 48.5 versus 45.7 in the Noometry coding category.

### Which has the bigger context window?

GPT-5.3 Codex does, with 400K tokens against 200K.

### How many benchmarks do GPT-5.3 Codex and o1 share?

3 benchmarks have published results for both models. GPT-5.3 Codex has 8 scored results on Noometry and o1 has 52.