Model comparison
Grok 4.1 vs Step 3
Grok 4.1 is the stronger model overall, scoring 41.5 to 40.5 on the Noometry Index.
Last verified . 15 shared benchmarks.
StepFunSummary
- They share 15 benchmarks with published results for both. Grok 4.1 scores higher in 7 categories and Step 3 in 1 category; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Grok 4.1 leads 62.4 to 54.3.
- Step 3 has downloadable open weights; the other is API-only.
Side by side
| Grok 4.1 | Step 3 | |
|---|---|---|
| Provider | xAI | StepFun |
| Noometry Index | 41.5 | 40.5 |
| Released | 2025-11-17 | — |
| Weights | Proprietary | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 19 | 17 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Step 3 leads
Grok 4.1: 33.7 (#253), Step 3: 40.1 (#147)
| Benchmark | Grok 4.1 | Step 3 |
|---|---|---|
| LMArena Coding | 1445 | 1367 |
| LMArena WebDev | 1214 | — |
Agentic & Tool Use Not comparable
Grok 4.1: 34.1 (#49), Step 3: —
| Benchmark | Grok 4.1 | Step 3 |
|---|---|---|
| Cybench | 39% | — |
Reasoning Grok 4.1 leads
Grok 4.1: 29.5 (#91), Step 3: 28.4 (#105)
| Benchmark | Grok 4.1 | Step 3 |
|---|---|---|
| LMArena Hard Prompts | 1435 | 1355 |
| Kagi LLM Benchmark | — | 62.3% |
Math Grok 4.1 leads
Grok 4.1: 38.9 (#120), Step 3: 37.6 (#148)
| Benchmark | Grok 4.1 | Step 3 |
|---|---|---|
| LMArena Math | 1422 | 1366 |
Knowledge Grok 4.1 leads
Grok 4.1: 39.5 (#133), Step 3: 36.8 (#164)
| Benchmark | Grok 4.1 | Step 3 |
|---|---|---|
| LMArena Expert | 1417 | 1333 |
Multimodal Not comparable
Grok 4.1: —, Step 3: 35.5 (#86)
| Benchmark | Grok 4.1 | Step 3 |
|---|---|---|
| LMArena Vision | — | 1177 |
Multilingual Grok 4.1 leads
Grok 4.1: 53.4 (#68), Step 3: 46.3 (#159)
| Benchmark | Grok 4.1 | Step 3 |
|---|---|---|
| LMArena Non-English | 1425 | 1327 |
| LMArena Chinese | 1465 | 1397 |
| LMArena German | 1446 | 1371 |
| LMArena Korean | 1407 | 1269 |
| LMArena Russian | 1434 | 1331 |
| LMArena Spanish | 1438 | 1371 |
| LMArena French | 1448 | — |
| LMArena Japanese | 1397 | — |
Instruction Following Grok 4.1 leads
Grok 4.1: 73.8 (#111), Step 3: 70.4 (#164)
| Benchmark | Grok 4.1 | Step 3 |
|---|---|---|
| LMArena Instruction Following | 1400 | 1332 |
Long Context Grok 4.1 leads
Grok 4.1: 43.2 (#100), Step 3: 40.3 (#157)
| Benchmark | Grok 4.1 | Step 3 |
|---|---|---|
| LMArena Longer Query | 1416 | 1326 |
Writing & Preference Grok 4.1 leads
Grok 4.1: 62.4 (#75), Step 3: 54.3 (#151)
| Benchmark | Grok 4.1 | Step 3 |
|---|---|---|
| LMArena Text | 1437 | 1350 |
| LMArena Creative Writing | 1411 | 1321 |
| LMArena Multi-Turn | 1437 | 1341 |
Frequently asked questions
Is Grok 4.1 better than Step 3?
Grok 4.1 is the stronger model overall, scoring 41.5 to 40.5 on the Noometry Index.
Is Grok 4.1 or Step 3 better for coding?
Step 3 scores higher on coding benchmarks: 40.1 versus 33.7 in the Noometry coding category.
How many benchmarks do Grok 4.1 and Step 3 share?
15 benchmarks have published results for both models. Grok 4.1 has 19 scored results on Noometry and Step 3 has 17.