# Chatgpt 4o Latest 20250326 vs GPT-4.5

> Chatgpt 4o Latest 20250326 is the stronger model overall, scoring 43.2 to 36.9 on the Noometry Index.

- Canonical page: https://noometry.com/compare/chatgpt-4o-vs-gpt-4-5
- Last updated: 2026-10-10
- Shared benchmarks: 19

## Summary

- They share 19 benchmarks with published results for both. Chatgpt 4o Latest 20250326 scores higher in 8 categories and GPT-4.5 in 1 category; 7 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Chatgpt 4o Latest 20250326 leads 32.8 to 14.1.

## Snapshot

| | Chatgpt 4o Latest 20250326 | GPT-4.5 |
|---|---|---|
| Provider | OpenAI | OpenAI |
| Noometry Index | 43.2 | 36.9 |
| Rank | 84 | 200 |
| Context | — | — |
| Input $/M | — | — |
| Output $/M | — | — |
| Weights | Proprietary | Proprietary |

## Coding

- Chatgpt 4o Latest 20250326: 41.0 (#122)
- GPT-4.5: 41.8 (#102)

| Benchmark | Chatgpt 4o Latest 20250326 | GPT-4.5 |
|---|---|---|
| LMArena Coding | 1413 | 1397 |
| Aider Polyglot | — | 44.9% |
| WeirdML | — | 39.4% |
| LiveBench Coding | — | 75.2% |

## Agentic & Tool Use

- Chatgpt 4o Latest 20250326: —
- GPT-4.5: 27.6 (#92)

| Benchmark | Chatgpt 4o Latest 20250326 | GPT-4.5 |
|---|---|---|
| Cybench | — | 17.5% |

## Reasoning

- Chatgpt 4o Latest 20250326: 32.8 (#64)
- GPT-4.5: 14.1 (#320)

| Benchmark | Chatgpt 4o Latest 20250326 | GPT-4.5 |
|---|---|---|
| LMArena Hard Prompts | 1424 | 1404 |
| ARC-AGI-2 | — | 0.8% |
| SimpleBench | — | 34.5% |
| Kagi LLM Benchmark | 75% | — |
| ARC-AGI-1 | — | 10.3% |
| EnigmaEval | — | 3.2% |
| LiveBench Reasoning | — | 71.1% |
| LiveBench Data Analysis | — | 64.3% |
| Epoch Capabilities Index | — | 136.74 |
| ForecastBench | — | 61.7 |
| LiveBench | — | 69% |

## Math

- Chatgpt 4o Latest 20250326: 35.8 (#134)
- GPT-4.5: 31.0 (#200)

| Benchmark | Chatgpt 4o Latest 20250326 | GPT-4.5 |
|---|---|---|
| LMArena Math | 1407 | 1412 |
| OTIS Mock AIME 2024-2025 | — | 37.8% |
| LiveBench Math | — | 69.3% |
| MATH Level 5 | — | 78.6% |

## Knowledge

- Chatgpt 4o Latest 20250326: 38.7 (#131)
- GPT-4.5: 32.4 (#205)

| Benchmark | Chatgpt 4o Latest 20250326 | GPT-4.5 |
|---|---|---|
| Confabulations | 16.6% | 13.6% |
| LMArena Expert | 1400 | 1394 |
| GPQA Diamond | — | 68.7% |
| Humanity's Last Exam | — | 5.4% |

## Multimodal

- Chatgpt 4o Latest 20250326: 38.9 (#54)
- GPT-4.5: 37.0 (#68)

| Benchmark | Chatgpt 4o Latest 20250326 | GPT-4.5 |
|---|---|---|
| LMArena Vision | 1243 | 1195 |
| VPCT | — | 45% |

## Multilingual

- Chatgpt 4o Latest 20250326: 53.1 (#72)
- GPT-4.5: 52.7 (#78)

| Benchmark | Chatgpt 4o Latest 20250326 | GPT-4.5 |
|---|---|---|
| LMArena Non-English | 1419 | 1413 |
| LMArena Chinese | 1456 | 1421 |
| LMArena French | 1447 | 1417 |
| LMArena German | 1424 | 1457 |
| LMArena Japanese | 1406 | 1416 |
| LMArena Korean | 1397 | 1392 |
| LMArena Russian | 1429 | 1419 |
| LMArena Spanish | 1435 | — |

## Instruction Following

- Chatgpt 4o Latest 20250326: 74.2 (#102)
- GPT-4.5: 72.8 (#129)

| Benchmark | Chatgpt 4o Latest 20250326 | GPT-4.5 |
|---|---|---|
| LMArena Instruction Following | 1403 | 1404 |
| LiveBench Instruction Following | — | 72.3% |

## Long Context

- Chatgpt 4o Latest 20250326: 43.1 (#104)
- GPT-4.5: 40.4 (#150)

| Benchmark | Chatgpt 4o Latest 20250326 | GPT-4.5 |
|---|---|---|
| LMArena Longer Query | 1413 | 1406 |
| Fiction.LiveBench | — | 63.9% |

## Writing & Preference

- Chatgpt 4o Latest 20250326: 62.8 (#68)
- GPT-4.5: 57.1 (#129)

| Benchmark | Chatgpt 4o Latest 20250326 | GPT-4.5 |
|---|---|---|
| LMArena Text | 1429 | 1417 |
| LMArena Creative Writing | 1406 | 1394 |
| EQ-Bench Creative Writing | 1501 | 1258 |
| LMArena Multi-Turn | 1454 | 1444 |
| Short-Story Creative Writing | — | 75.6% |
| LiveBench Language | — | 61.5% |

## FAQ

### Is Chatgpt 4o Latest 20250326 better than GPT-4.5?

Chatgpt 4o Latest 20250326 is the stronger model overall, scoring 43.2 to 36.9 on the Noometry Index.

### Is Chatgpt 4o Latest 20250326 or GPT-4.5 better for coding?

They score almost the same on coding (41.0 vs 41.8); test both on your own repository before choosing.

### How many benchmarks do Chatgpt 4o Latest 20250326 and GPT-4.5 share?

19 benchmarks have published results for both models. Chatgpt 4o Latest 20250326 has 21 scored results on Noometry and GPT-4.5 has 42.