Model comparison
Chatgpt 4o Latest 20250326 vs Step 5 Preview
Step 5 Preview is the stronger model overall, scoring 47.9 to 43.8 on the Noometry Index.
Last verified . 14 shared benchmarks.
StepFunSummary
- They share 14 benchmarks with published results for both. Chatgpt 4o Latest 20250326 scores higher in 0 categories and Step 5 Preview in 9 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in coding, where Step 5 Preview leads 51.8 to 41.6.
Side by side
| Chatgpt 4o Latest 20250326 | Step 5 Preview | |
|---|---|---|
| Provider | OpenAI | StepFun |
| Noometry Index | 43.8 | 47.9 |
| Released | — | 2026-09-16 |
| Weights | Proprietary | Proprietary |
| Context window | — | 1.02M |
| Max output | — | 66K |
| Input $ / M tokens | — | $1 |
| Output $ / M tokens | — | $2.70 |
| Results tracked | 21 | 18 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Step 5 Preview leads
Chatgpt 4o Latest 20250326: 41.6 (#122), Step 5 Preview: 51.8 (#36)
| Benchmark | Chatgpt 4o Latest 20250326 | Step 5 Preview |
|---|---|---|
| LMArena Coding | 1413 | 1480 |
| LMArena WebDev | — | 1564 |
| SciCode | — | 58.9% |
Reasoning Step 5 Preview leads
Chatgpt 4o Latest 20250326: 33.8 (#71), Step 5 Preview: 40.0 (#57)
| Benchmark | Chatgpt 4o Latest 20250326 | Step 5 Preview |
|---|---|---|
| LMArena Hard Prompts | 1424 | 1465 |
| Kagi LLM Benchmark | 75% | — |
| CritPt | — | 20.9% |
Math Step 5 Preview leads
Chatgpt 4o Latest 20250326: 38.6 (#134), Step 5 Preview: 46.1 (#72)
| Benchmark | Chatgpt 4o Latest 20250326 | Step 5 Preview |
|---|---|---|
| LMArena Math | 1407 | 1470 |
| ProofBench | — | 42% |
Knowledge Step 5 Preview leads
Chatgpt 4o Latest 20250326: 39.2 (#137), Step 5 Preview: 41.2 (#112)
| Benchmark | Chatgpt 4o Latest 20250326 | Step 5 Preview |
|---|---|---|
| LMArena Expert | 1401 | 1470 |
| Confabulations | 16.6% | — |
Multimodal Step 5 Preview leads
Chatgpt 4o Latest 20250326: 39.6 (#58), Step 5 Preview: 41.0 (#41)
| Benchmark | Chatgpt 4o Latest 20250326 | Step 5 Preview |
|---|---|---|
| LMArena Vision | 1243 | 1267 |
Multilingual Too close to call
Chatgpt 4o Latest 20250326: 52.9 (#76), Step 5 Preview: 53.8 (#54)
| Benchmark | Chatgpt 4o Latest 20250326 | Step 5 Preview |
|---|---|---|
| LMArena Non-English | 1419 | 1432 |
| LMArena Chinese | 1457 | 1519 |
| LMArena Russian | 1429 | 1436 |
| LMArena Spanish | 1434 | 1439 |
| LMArena French | 1446 | — |
| LMArena German | 1423 | — |
| LMArena Japanese | 1405 | — |
| LMArena Korean | 1396 | — |
Instruction Following Step 5 Preview leads
Chatgpt 4o Latest 20250326: 74.0 (#107), Step 5 Preview: 76.0 (#50)
| Benchmark | Chatgpt 4o Latest 20250326 | Step 5 Preview |
|---|---|---|
| LMArena Instruction Following | 1403 | 1444 |
Long Context Step 5 Preview leads
Chatgpt 4o Latest 20250326: 43.1 (#107), Step 5 Preview: 44.5 (#64)
| Benchmark | Chatgpt 4o Latest 20250326 | Step 5 Preview |
|---|---|---|
| LMArena Longer Query | 1413 | 1455 |
Writing & Preference Too close to call
Chatgpt 4o Latest 20250326: 62.6 (#72), Step 5 Preview: 62.8 (#71)
| Benchmark | Chatgpt 4o Latest 20250326 | Step 5 Preview |
|---|---|---|
| LMArena Text | 1429 | 1442 |
| LMArena Creative Writing | 1405 | 1410 |
| LMArena Multi-Turn | 1454 | 1447 |
| EQ-Bench Creative Writing | 1501 | — |
Frequently asked questions
Is Chatgpt 4o Latest 20250326 better than Step 5 Preview?
Step 5 Preview is the stronger model overall, scoring 47.9 to 43.8 on the Noometry Index.
Is Chatgpt 4o Latest 20250326 or Step 5 Preview better for coding?
Step 5 Preview scores higher on coding benchmarks: 51.8 versus 41.6 in the Noometry coding category.
How many benchmarks do Chatgpt 4o Latest 20250326 and Step 5 Preview share?
14 benchmarks have published results for both models. Chatgpt 4o Latest 20250326 has 21 scored results on Noometry and Step 5 Preview has 18.