Model comparison
GPT-5.3 Chat vs Step 3
GPT-5.3 Chat is the stronger model overall, scoring 42.8 to 40.5 on the Noometry Index.
Last verified . 15 shared benchmarks.
StepFunSummary
- They share 15 benchmarks with published results for both. GPT-5.3 Chat scores higher in 8 categories and Step 3 in 0 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where GPT-5.3 Chat leads 63.1 to 54.3.
- Step 3 has downloadable open weights; the other is API-only.
Side by side
| GPT-5.3 Chat | Step 3 | |
|---|---|---|
| Provider | OpenAI | StepFun |
| Noometry Index | 42.8 | 40.5 |
| Released | 2026-03-03 | — |
| Weights | Proprietary | Open |
| Context window | 128K | — |
| Max output | 16K | — |
| Input $ / M tokens | $1.75 | — |
| Output $ / M tokens | $14 | — |
| Results tracked | 18 | 17 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-5.3 Chat leads
GPT-5.3 Chat: 41.4 (#124), Step 3: 40.1 (#147)
| Benchmark | GPT-5.3 Chat | Step 3 |
|---|---|---|
| LMArena Coding | 1408 | 1367 |
Reasoning Too close to call
GPT-5.3 Chat: 28.5 (#102), Step 3: 28.4 (#105)
| Benchmark | GPT-5.3 Chat | Step 3 |
|---|---|---|
| LMArena Hard Prompts | 1399 | 1355 |
| Kagi LLM Benchmark | — | 62.3% |
Math Too close to call
GPT-5.3 Chat: 38.2 (#142), Step 3: 37.6 (#148)
| Benchmark | GPT-5.3 Chat | Step 3 |
|---|---|---|
| LMArena Math | 1389 | 1366 |
Knowledge GPT-5.3 Chat leads
GPT-5.3 Chat: 38.8 (#140), Step 3: 36.8 (#164)
| Benchmark | GPT-5.3 Chat | Step 3 |
|---|---|---|
| LMArena Expert | 1397 | 1333 |
Multimodal Not comparable
GPT-5.3 Chat: —, Step 3: 35.5 (#86)
| Benchmark | GPT-5.3 Chat | Step 3 |
|---|---|---|
| LMArena Vision | — | 1177 |
Multilingual GPT-5.3 Chat leads
GPT-5.3 Chat: 50.3 (#124), Step 3: 46.3 (#159)
| Benchmark | GPT-5.3 Chat | Step 3 |
|---|---|---|
| LMArena Non-English | 1382 | 1327 |
| LMArena Chinese | 1432 | 1397 |
| LMArena German | 1384 | 1371 |
| LMArena Korean | 1346 | 1269 |
| LMArena Russian | 1400 | 1331 |
| LMArena Spanish | 1371 | 1371 |
| LMArena French | 1397 | — |
| LMArena Japanese | 1352 | — |
Instruction Following GPT-5.3 Chat leads
GPT-5.3 Chat: 72.8 (#129), Step 3: 70.4 (#164)
| Benchmark | GPT-5.3 Chat | Step 3 |
|---|---|---|
| LMArena Instruction Following | 1378 | 1332 |
Long Context GPT-5.3 Chat leads
GPT-5.3 Chat: 42.6 (#120), Step 3: 40.3 (#157)
| Benchmark | GPT-5.3 Chat | Step 3 |
|---|---|---|
| LMArena Longer Query | 1396 | 1326 |
Writing & Preference GPT-5.3 Chat leads
GPT-5.3 Chat: 63.1 (#68), Step 3: 54.3 (#151)
| Benchmark | GPT-5.3 Chat | Step 3 |
|---|---|---|
| LMArena Text | 1389 | 1350 |
| LMArena Creative Writing | 1355 | 1321 |
| LMArena Multi-Turn | 1412 | 1341 |
| EQ-Bench Creative Writing | 1690 | — |
Frequently asked questions
Is GPT-5.3 Chat better than Step 3?
GPT-5.3 Chat is the stronger model overall, scoring 42.8 to 40.5 on the Noometry Index.
Is GPT-5.3 Chat or Step 3 better for coding?
GPT-5.3 Chat scores higher on coding benchmarks: 41.4 versus 40.1 in the Noometry coding category.
How many benchmarks do GPT-5.3 Chat and Step 3 share?
15 benchmarks have published results for both models. GPT-5.3 Chat has 18 scored results on Noometry and Step 3 has 17.