Model comparison
Grok 4.20 (Non-Reasoning) vs Step 5 Preview
Grok 4.20 (Non-Reasoning) and Step 5 Preview score almost the same on the Noometry Index (48.6 vs 47.9), so choose on price, context window or the category you care about most.
Last verified . 16 shared benchmarks.
StepFunSummary
- They share 16 benchmarks with published results for both. Grok 4.20 (Non-Reasoning) scores higher in 6 categories and Step 5 Preview in 3 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Grok 4.20 (Non-Reasoning) leads 52.3 to 40.0.
- The biggest single-benchmark swing is ProofBench: 14% for Grok 4.20 (Non-Reasoning) and 42% for Step 5 Preview.
- Step 5 Preview is cheaper at $1 / $2.70 per million input/output tokens, against $1.25 / $2.50 for Grok 4.20 (Non-Reasoning).
- Step 5 Preview accepts more context: 1.02M tokens versus 1M.
Side by side
| Grok 4.20 (Non-Reasoning) | Step 5 Preview | |
|---|---|---|
| Provider | xAI | StepFun |
| Noometry Index | 48.6 | 47.9 |
| Released | 2026-02-17 | 2026-09-16 |
| Weights | Proprietary | Proprietary |
| Context window | 1M | 1.02M |
| Max output | 30K | 66K |
| Input $ / M tokens | $1.25 | $1 |
| Output $ / M tokens | $2.50 | $2.70 |
| Results tracked | 46 | 18 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Step 5 Preview leads
Grok 4.20 (Non-Reasoning): 42.1 (#112), Step 5 Preview: 51.8 (#36)
| Benchmark | Grok 4.20 (Non-Reasoning) | Step 5 Preview |
|---|---|---|
| LMArena WebDev | 1375 | 1564 |
| LMArena Coding | 1459 | 1480 |
| SciCode | — | 58.9% |
| WeirdML | 52.3% | — |
| ALE-Bench | 1,150 | — |
Agentic & Tool Use Not comparable
Grok 4.20 (Non-Reasoning): 34.4 (#46), Step 5 Preview: —
| Benchmark | Grok 4.20 (Non-Reasoning) | Step 5 Preview |
|---|---|---|
| Terminal-Bench | 57.3% | — |
| τ²-bench Banking | 18% | — |
| LMArena Search | 1189 | — |
| Vending-Bench 2 | 4,663 | — |
Reasoning Grok 4.20 (Non-Reasoning) leads
Grok 4.20 (Non-Reasoning): 52.3 (#32), Step 5 Preview: 40.0 (#57)
| Benchmark | Grok 4.20 (Non-Reasoning) | Step 5 Preview |
|---|---|---|
| LMArena Hard Prompts | 1451 | 1465 |
| ARC-AGI-2 | 65.1% | — |
| Kagi LLM Benchmark | 75% | — |
| NYT Connections (extended) | 85.4% | — |
| ARC-AGI-1 | 89.5% | — |
| CritPt | — | 20.9% |
| Chess Puzzles | 24% | — |
| Thematic Generalization | 63.8% | — |
| DTBench | 90.1% | — |
| LMCA | 38.7% | — |
| Epoch Capabilities Index | 151.98 | — |
| ForecastBench | 61.4 | — |
Math Grok 4.20 (Non-Reasoning) leads
Grok 4.20 (Non-Reasoning): 48.2 (#65), Step 5 Preview: 46.1 (#72)
| Benchmark | Grok 4.20 (Non-Reasoning) | Step 5 Preview |
|---|---|---|
| ProofBench | 14% | 42% |
| LMArena Math | 1455 | 1470 |
| FrontierMath (Tiers 1-3) | 44.9% | — |
| FrontierMath Tier 4 | 17.1% | — |
| OTIS Mock AIME 2024-2025 | 92.2% | — |
Knowledge Grok 4.20 (Non-Reasoning) leads
Grok 4.20 (Non-Reasoning): 52.8 (#60), Step 5 Preview: 41.2 (#112)
| Benchmark | Grok 4.20 (Non-Reasoning) | Step 5 Preview |
|---|---|---|
| LMArena Expert | 1439 | 1470 |
| GPQA Diamond | 89.3% | — |
| SimpleQA Verified | 30.2% | — |
Multimodal Step 5 Preview leads
Grok 4.20 (Non-Reasoning): 33.3 (#98), Step 5 Preview: 41.0 (#41)
| Benchmark | Grok 4.20 (Non-Reasoning) | Step 5 Preview |
|---|---|---|
| LMArena Vision | 1263 | 1267 |
| Blueprint-Bench 2 | 0% | — |
| LMArena Document | 1416 | — |
Multilingual Too close to call
Grok 4.20 (Non-Reasoning): 54.5 (#40), Step 5 Preview: 53.8 (#54)
| Benchmark | Grok 4.20 (Non-Reasoning) | Step 5 Preview |
|---|---|---|
| LMArena Non-English | 1441 | 1432 |
| LMArena Chinese | 1481 | 1519 |
| LMArena Russian | 1458 | 1436 |
| LMArena Spanish | 1443 | 1439 |
| LMArena French | 1476 | — |
| LMArena German | 1465 | — |
| LMArena Japanese | 1449 | — |
| LMArena Korean | 1417 | — |
Instruction Following Step 5 Preview leads
Grok 4.20 (Non-Reasoning): 74.8 (#83), Step 5 Preview: 76.0 (#50)
| Benchmark | Grok 4.20 (Non-Reasoning) | Step 5 Preview |
|---|---|---|
| LMArena Instruction Following | 1420 | 1444 |
Long Context Too close to call
Grok 4.20 (Non-Reasoning): 45.5 (#34), Step 5 Preview: 44.5 (#64)
| Benchmark | Grok 4.20 (Non-Reasoning) | Step 5 Preview |
|---|---|---|
| LMArena Longer Query | 1437 | 1455 |
| CL-bench | 22.2% | — |
| CL-bench Life | 11.9% | — |
Writing & Preference Grok 4.20 (Non-Reasoning) leads
Grok 4.20 (Non-Reasoning): 65.7 (#44), Step 5 Preview: 62.8 (#71)
| Benchmark | Grok 4.20 (Non-Reasoning) | Step 5 Preview |
|---|---|---|
| LMArena Text | 1451 | 1442 |
| LMArena Creative Writing | 1438 | 1410 |
| LMArena Multi-Turn | 1456 | 1447 |
| EQ-Bench Creative Writing | 1574 | — |
Frequently asked questions
Is Grok 4.20 (Non-Reasoning) better than Step 5 Preview?
Grok 4.20 (Non-Reasoning) and Step 5 Preview score almost the same on the Noometry Index (48.6 vs 47.9), so choose on price, context window or the category you care about most.
Which is cheaper, Grok 4.20 (Non-Reasoning) 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 4.20 (Non-Reasoning) lists at $1.25 and $2.50.
Is Grok 4.20 (Non-Reasoning) or Step 5 Preview better for coding?
Step 5 Preview scores higher on coding benchmarks: 51.8 versus 42.1 in the Noometry coding category.
Which has the bigger context window?
Step 5 Preview does, with 1.02M tokens against 1M.
How many benchmarks do Grok 4.20 (Non-Reasoning) and Step 5 Preview share?
16 benchmarks have published results for both models. Grok 4.20 (Non-Reasoning) has 46 scored results on Noometry and Step 5 Preview has 18.