# Chatgpt 4o Latest 20250326 vs Step 3

> Chatgpt 4o Latest 20250326 is the stronger model overall, scoring 43.2 to 39.9 on the Noometry Index.

- Canonical page: https://noometry.com/compare/chatgpt-4o-vs-step-3
- Last updated: 2026-10-10
- Shared benchmarks: 17

## Summary

- They share 17 benchmarks with published results for both. Chatgpt 4o Latest 20250326 scores higher in 9 categories and Step 3 in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Chatgpt 4o Latest 20250326 leads 62.8 to 54.5.
- The biggest single-benchmark swing is Kagi LLM Benchmark: 75% for Chatgpt 4o Latest 20250326 and 62.3% for Step 3.
- Step 3 has downloadable open weights; the other is API-only.

## Snapshot

| | Chatgpt 4o Latest 20250326 | Step 3 |
|---|---|---|
| Provider | OpenAI | StepFun |
| Noometry Index | 43.2 | 39.9 |
| Rank | 84 | 145 |
| Context | — | — |
| Input $/M | — | — |
| Output $/M | — | — |
| Weights | Proprietary | Open |

## Coding

- Chatgpt 4o Latest 20250326: 41.0 (#122)
- Step 3: 39.5 (#144)

| Benchmark | Chatgpt 4o Latest 20250326 | Step 3 |
|---|---|---|
| LMArena Coding | 1413 | 1367 |

## Reasoning

- Chatgpt 4o Latest 20250326: 32.8 (#64)
- Step 3: 27.6 (#102)

| Benchmark | Chatgpt 4o Latest 20250326 | Step 3 |
|---|---|---|
| Kagi LLM Benchmark | 75% | 62.3% |
| LMArena Hard Prompts | 1424 | 1355 |

## Math

- Chatgpt 4o Latest 20250326: 35.8 (#134)
- Step 3: 34.9 (#148)

| Benchmark | Chatgpt 4o Latest 20250326 | Step 3 |
|---|---|---|
| LMArena Math | 1407 | 1366 |

## Knowledge

- Chatgpt 4o Latest 20250326: 38.7 (#131)
- Step 3: 36.2 (#161)

| Benchmark | Chatgpt 4o Latest 20250326 | Step 3 |
|---|---|---|
| LMArena Expert | 1400 | 1333 |
| Confabulations | 16.6% | — |

## Multimodal

- Chatgpt 4o Latest 20250326: 38.9 (#54)
- Step 3: 34.9 (#81)

| Benchmark | Chatgpt 4o Latest 20250326 | Step 3 |
|---|---|---|
| LMArena Vision | 1243 | 1176 |

## Multilingual

- Chatgpt 4o Latest 20250326: 53.1 (#72)
- Step 3: 46.5 (#154)

| Benchmark | Chatgpt 4o Latest 20250326 | Step 3 |
|---|---|---|
| LMArena Non-English | 1419 | 1327 |
| LMArena Chinese | 1456 | 1396 |
| LMArena German | 1424 | 1371 |
| LMArena Korean | 1397 | 1271 |
| LMArena Russian | 1429 | 1331 |
| LMArena Spanish | 1435 | 1372 |
| LMArena French | 1447 | — |
| LMArena Japanese | 1406 | — |

## Instruction Following

- Chatgpt 4o Latest 20250326: 74.2 (#102)
- Step 3: 70.6 (#159)

| Benchmark | Chatgpt 4o Latest 20250326 | Step 3 |
|---|---|---|
| LMArena Instruction Following | 1403 | 1332 |

## Long Context

- Chatgpt 4o Latest 20250326: 43.1 (#104)
- Step 3: 40.3 (#152)

| Benchmark | Chatgpt 4o Latest 20250326 | Step 3 |
|---|---|---|
| LMArena Longer Query | 1413 | 1326 |

## Writing & Preference

- Chatgpt 4o Latest 20250326: 62.8 (#68)
- Step 3: 54.5 (#146)

| Benchmark | Chatgpt 4o Latest 20250326 | Step 3 |
|---|---|---|
| LMArena Text | 1429 | 1351 |
| LMArena Creative Writing | 1406 | 1322 |
| LMArena Multi-Turn | 1454 | 1340 |
| EQ-Bench Creative Writing | 1501 | — |

## FAQ

### Is Chatgpt 4o Latest 20250326 better than Step 3?

Chatgpt 4o Latest 20250326 is the stronger model overall, scoring 43.2 to 39.9 on the Noometry Index.

### Is Chatgpt 4o Latest 20250326 or Step 3 better for coding?

Chatgpt 4o Latest 20250326 scores higher on coding benchmarks: 41.0 versus 39.5 in the Noometry coding category.

### How many benchmarks do Chatgpt 4o Latest 20250326 and Step 3 share?

17 benchmarks have published results for both models. Chatgpt 4o Latest 20250326 has 21 scored results on Noometry and Step 3 has 17.