Model comparison
Grok Build 0.1 vs Step 3
Step 3 is the stronger model overall, scoring 39.9 to 35.8 on the Noometry Index.
Last verified . 0 shared benchmarks.
StepFunSummary
- The widest gap is in reasoning, where Grok Build 0.1 leads 31.3 to 27.6.
- Step 3 has downloadable open weights; the other is API-only.
Side by side
| Grok Build 0.1 | Step 3 | |
|---|---|---|
| Provider | xAI | StepFun |
| Noometry Index | 35.8 | 39.9 |
| Released | 2026-04-16 | — |
| Weights | Proprietary | Open |
| Context window | 256K | — |
| Max output | 256K | — |
| Input $ / M tokens | $1 | — |
| Output $ / M tokens | $2 | — |
| Results tracked | 3 | 17 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Grok Build 0.1 leads
Grok Build 0.1: 42.5 (#90), Step 3: 39.5 (#144)
| Benchmark | Grok Build 0.1 | Step 3 |
|---|---|---|
| SciCode | 50.2% | — |
| LMArena Coding | — | 1367 |
Agentic & Tool Use Not comparable
Grok Build 0.1: 22.5 (#122), Step 3: —
| Benchmark | Grok Build 0.1 | Step 3 |
|---|---|---|
| GBAEval | 2.4% | — |
Reasoning Grok Build 0.1 leads
Grok Build 0.1: 31.3 (#73), Step 3: 27.6 (#102)
| Benchmark | Grok Build 0.1 | Step 3 |
|---|---|---|
| Kagi LLM Benchmark | — | 62.3% |
| CritPt | 9.1% | — |
| LMArena Hard Prompts | — | 1355 |
Math Not comparable
Grok Build 0.1: —, Step 3: 34.9 (#148)
| Benchmark | Grok Build 0.1 | Step 3 |
|---|---|---|
| LMArena Math | — | 1366 |
Knowledge Not comparable
Grok Build 0.1: —, Step 3: 36.2 (#161)
| Benchmark | Grok Build 0.1 | Step 3 |
|---|---|---|
| LMArena Expert | — | 1333 |
Multimodal Not comparable
Grok Build 0.1: —, Step 3: 34.9 (#81)
| Benchmark | Grok Build 0.1 | Step 3 |
|---|---|---|
| LMArena Vision | — | 1176 |
Multilingual Not comparable
Grok Build 0.1: —, Step 3: 46.5 (#154)
| Benchmark | Grok Build 0.1 | Step 3 |
|---|---|---|
| LMArena Non-English | — | 1327 |
| LMArena Chinese | — | 1396 |
| LMArena German | — | 1371 |
| LMArena Korean | — | 1271 |
| LMArena Russian | — | 1331 |
| LMArena Spanish | — | 1372 |
Instruction Following Not comparable
Grok Build 0.1: —, Step 3: 70.6 (#159)
| Benchmark | Grok Build 0.1 | Step 3 |
|---|---|---|
| LMArena Instruction Following | — | 1332 |
Long Context Not comparable
Grok Build 0.1: —, Step 3: 40.3 (#152)
| Benchmark | Grok Build 0.1 | Step 3 |
|---|---|---|
| LMArena Longer Query | — | 1326 |
Writing & Preference Not comparable
Grok Build 0.1: —, Step 3: 54.5 (#146)
| Benchmark | Grok Build 0.1 | Step 3 |
|---|---|---|
| LMArena Text | — | 1351 |
| LMArena Creative Writing | — | 1322 |
| LMArena Multi-Turn | — | 1340 |
Frequently asked questions
Is Grok Build 0.1 better than Step 3?
Step 3 is the stronger model overall, scoring 39.9 to 35.8 on the Noometry Index.
Is Grok Build 0.1 or Step 3 better for coding?
Grok Build 0.1 scores higher on coding benchmarks: 42.5 versus 39.5 in the Noometry coding category.
How many benchmarks do Grok Build 0.1 and Step 3 share?
0 benchmarks have published results for both models. Grok Build 0.1 has 3 scored results on Noometry and Step 3 has 17.