Model comparison
Grok 4.7 vs Step 3
Grok 4.7 is the stronger model overall, scoring 53.1 to 40.5 on the Noometry Index.
Last verified . 14 shared benchmarks.
StepFunSummary
- They share 14 benchmarks with published results for both. Grok 4.7 scores higher in 8 categories and Step 3 in 1 category; 8 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Grok 4.7 leads 62.8 to 36.8.
- Step 3 has downloadable open weights; the other is API-only.
Side by side
| Grok 4.7 | Step 3 | |
|---|---|---|
| Provider | xAI | StepFun |
| Noometry Index | 53.1 | 40.5 |
| Released | 2026-09-21 | — |
| Weights | Proprietary | Open |
| Context window | 500K | — |
| Max output | 500K | — |
| Input $ / M tokens | $2 | — |
| Output $ / M tokens | $6 | — |
| Results tracked | 39 | 17 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Grok 4.7 leads
Grok 4.7: 58.0 (#18), Step 3: 40.1 (#147)
| Benchmark | Grok 4.7 | Step 3 |
|---|---|---|
| LMArena Coding | 1427 | 1367 |
| FrontierCode | 47.6% | — |
| CursorBench | 46.3% | — |
| LMArena WebDev | 1639 | — |
| FrontierSWE | 29.5% | — |
| SciCode | 57.8% | — |
Agentic & Tool Use Not comparable
Grok 4.7: 36.7 (#37), Step 3: —
| Benchmark | Grok 4.7 | Step 3 |
|---|---|---|
| APEX-Agents | 54.6% | — |
| GDP.pdf | 22.8% | — |
| Vending-Bench 2 | 10,537 | — |
Reasoning Grok 4.7 leads
Grok 4.7: 49.1 (#40), Step 3: 28.4 (#105)
| Benchmark | Grok 4.7 | Step 3 |
|---|---|---|
| LMArena Hard Prompts | 1413 | 1355 |
| Kagi LLM Benchmark | — | 62.3% |
| NYT Connections (extended) | 76.8% | — |
| CritPt | 18% | — |
| Chess Puzzles | 38% | — |
| Mystery Game Puzzles | 29% | — |
| DTBench | 96% | — |
| LMCA | 49.4% | — |
| Epoch Capabilities Index | 153.53 | — |
Math Grok 4.7 leads
Grok 4.7: 57.8 (#39), Step 3: 37.6 (#148)
| Benchmark | Grok 4.7 | Step 3 |
|---|---|---|
| LMArena Math | 1407 | 1366 |
| FrontierMath (Tiers 1-3) | 53% | — |
| FrontierMath Tier 4 | 17.1% | — |
| OTIS Mock AIME 2024-2025 | 98.1% | — |
| ProofBench | 34% | — |
Knowledge Grok 4.7 leads
Grok 4.7: 62.8 (#22), Step 3: 36.8 (#164)
| Benchmark | Grok 4.7 | Step 3 |
|---|---|---|
| LMArena Expert | 1422 | 1333 |
| GPQA Diamond | 92.7% | — |
| SimpleQA Verified | 56% | — |
Multimodal Too close to call
Grok 4.7: 35.5 (#87), Step 3: 35.5 (#86)
| Benchmark | Grok 4.7 | Step 3 |
|---|---|---|
| LMArena Vision | 1228 | 1177 |
| Blueprint-Bench 2 | 32.5% | — |
| Furniture Assembly | 20.8% | — |
Multilingual Grok 4.7 leads
Grok 4.7: 50.8 (#116), Step 3: 46.3 (#159)
| Benchmark | Grok 4.7 | Step 3 |
|---|---|---|
| LMArena Non-English | 1389 | 1327 |
| LMArena Chinese | 1455 | 1397 |
| LMArena Russian | 1397 | 1331 |
| LMArena Spanish | 1400 | 1371 |
| LMArena French | 1455 | — |
| LMArena German | — | 1371 |
| LMArena Korean | — | 1269 |
Instruction Following Grok 4.7 leads
Grok 4.7: 74.1 (#105), Step 3: 70.4 (#164)
| Benchmark | Grok 4.7 | Step 3 |
|---|---|---|
| LMArena Instruction Following | 1404 | 1332 |
Long Context Grok 4.7 leads
Grok 4.7: 43.1 (#104), Step 3: 40.3 (#157)
| Benchmark | Grok 4.7 | Step 3 |
|---|---|---|
| LMArena Longer Query | 1413 | 1326 |
Writing & Preference Grok 4.7 leads
Grok 4.7: 70.0 (#24), Step 3: 54.3 (#151)
| Benchmark | Grok 4.7 | Step 3 |
|---|---|---|
| LMArena Text | 1399 | 1350 |
| LMArena Creative Writing | 1391 | 1321 |
| LMArena Multi-Turn | 1393 | 1341 |
| EQ-Bench Creative Writing | 2007 | — |
Frequently asked questions
Is Grok 4.7 better than Step 3?
Grok 4.7 is the stronger model overall, scoring 53.1 to 40.5 on the Noometry Index.
Is Grok 4.7 or Step 3 better for coding?
Grok 4.7 scores higher on coding benchmarks: 58.0 versus 40.1 in the Noometry coding category.
How many benchmarks do Grok 4.7 and Step 3 share?
14 benchmarks have published results for both models. Grok 4.7 has 39 scored results on Noometry and Step 3 has 17.