Model comparison
Grok 4.7 vs Step 5 Preview
Grok 4.7 is the stronger model overall, scoring 53.1 to 47.9 on the Noometry Index. Step 5 Preview costs 2.1× less per token, which makes it the better buy when Grok 4.7's lead doesn't matter for your workload.
Last verified . 18 shared benchmarks.
StepFunSummary
- They share 18 benchmarks with published results for both. Grok 4.7 scores higher in 5 categories and Step 5 Preview in 4 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Grok 4.7 leads 62.8 to 41.2.
- The biggest single-benchmark swing is ProofBench: 34% for Grok 4.7 and 42% for Step 5 Preview.
- Step 5 Preview is cheaper at $1 / $2.70 per million input/output tokens, against $2 / $6 for Grok 4.7.
- Step 5 Preview accepts more context: 1.02M tokens versus 500K.
Side by side
| Grok 4.7 | Step 5 Preview | |
|---|---|---|
| Provider | xAI | StepFun |
| Noometry Index | 53.1 | 47.9 |
| Released | 2026-09-21 | 2026-09-16 |
| Weights | Proprietary | Proprietary |
| Context window | 500K | 1.02M |
| Max output | 500K | 66K |
| Input $ / M tokens | $2 | $1 |
| Output $ / M tokens | $6 | $2.70 |
| Results tracked | 39 | 18 |
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 5 Preview: 51.8 (#36)
| Benchmark | Grok 4.7 | Step 5 Preview |
|---|---|---|
| LMArena WebDev | 1639 | 1564 |
| SciCode | 57.8% | 58.9% |
| LMArena Coding | 1427 | 1480 |
| FrontierCode | 47.6% | — |
| CursorBench | 46.3% | — |
| FrontierSWE | 29.5% | — |
Agentic & Tool Use Not comparable
Grok 4.7: 36.7 (#37), Step 5 Preview: —
| Benchmark | Grok 4.7 | Step 5 Preview |
|---|---|---|
| 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 5 Preview: 40.0 (#57)
| Benchmark | Grok 4.7 | Step 5 Preview |
|---|---|---|
| CritPt | 18% | 20.9% |
| LMArena Hard Prompts | 1413 | 1465 |
| NYT Connections (extended) | 76.8% | — |
| 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 5 Preview: 46.1 (#72)
| Benchmark | Grok 4.7 | Step 5 Preview |
|---|---|---|
| ProofBench | 34% | 42% |
| LMArena Math | 1407 | 1470 |
| FrontierMath (Tiers 1-3) | 53% | — |
| FrontierMath Tier 4 | 17.1% | — |
| OTIS Mock AIME 2024-2025 | 98.1% | — |
Knowledge Grok 4.7 leads
Grok 4.7: 62.8 (#22), Step 5 Preview: 41.2 (#112)
| Benchmark | Grok 4.7 | Step 5 Preview |
|---|---|---|
| LMArena Expert | 1422 | 1470 |
| GPQA Diamond | 92.7% | — |
| SimpleQA Verified | 56% | — |
Multimodal Step 5 Preview leads
Grok 4.7: 35.5 (#87), Step 5 Preview: 41.0 (#41)
| Benchmark | Grok 4.7 | Step 5 Preview |
|---|---|---|
| LMArena Vision | 1228 | 1267 |
| Blueprint-Bench 2 | 32.5% | — |
| Furniture Assembly | 20.8% | — |
Multilingual Step 5 Preview leads
Grok 4.7: 50.8 (#116), Step 5 Preview: 53.8 (#54)
| Benchmark | Grok 4.7 | Step 5 Preview |
|---|---|---|
| LMArena Non-English | 1389 | 1432 |
| LMArena Chinese | 1455 | 1519 |
| LMArena Russian | 1397 | 1436 |
| LMArena Spanish | 1400 | 1439 |
| LMArena French | 1455 | — |
Instruction Following Step 5 Preview leads
Grok 4.7: 74.1 (#105), Step 5 Preview: 76.0 (#50)
| Benchmark | Grok 4.7 | Step 5 Preview |
|---|---|---|
| LMArena Instruction Following | 1404 | 1444 |
Long Context Step 5 Preview leads
Grok 4.7: 43.1 (#104), Step 5 Preview: 44.5 (#64)
| Benchmark | Grok 4.7 | Step 5 Preview |
|---|---|---|
| LMArena Longer Query | 1413 | 1455 |
Writing & Preference Grok 4.7 leads
Grok 4.7: 70.0 (#24), Step 5 Preview: 62.8 (#71)
| Benchmark | Grok 4.7 | Step 5 Preview |
|---|---|---|
| LMArena Text | 1399 | 1442 |
| LMArena Creative Writing | 1391 | 1410 |
| LMArena Multi-Turn | 1393 | 1447 |
| EQ-Bench Creative Writing | 2007 | — |
Frequently asked questions
Is Grok 4.7 better than Step 5 Preview?
Grok 4.7 is the stronger model overall, scoring 53.1 to 47.9 on the Noometry Index. Step 5 Preview costs 2.1× less per token, which makes it the better buy when Grok 4.7's lead doesn't matter for your workload.
Which is cheaper, Grok 4.7 or Step 5 Preview?
Step 5 Preview is cheaper. It lists at $1 per million input tokens and $2.70 per million output tokens; Grok 4.7 lists at $2 and $6.
Is Grok 4.7 or Step 5 Preview better for coding?
Grok 4.7 scores higher on coding benchmarks: 58.0 versus 51.8 in the Noometry coding category.
Which has the bigger context window?
Step 5 Preview does, with 1.02M tokens against 500K.
How many benchmarks do Grok 4.7 and Step 5 Preview share?
18 benchmarks have published results for both models. Grok 4.7 has 39 scored results on Noometry and Step 5 Preview has 18.