Model comparison
Grok 4.1 Fast vs Step 3.7 Flash
Grok 4.1 Fast is the stronger model overall, scoring 41.4 to 37.3 on the Noometry Index.
Last verified . 3 shared benchmarks.
StepFunSummary
- They share 3 benchmarks with published results for both. Grok 4.1 Fast scores higher in 1 category and Step 3.7 Flash in 2 categories; 3 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Grok 4.1 Fast leads 43.4 to 21.6.
- The biggest single-benchmark swing is NYT Connections (extended): 87.4% for Grok 4.1 Fast and 39.7% for Step 3.7 Flash.
- Grok 4.1 Fast is cheaper at $0.20 / $0.50 per million input/output tokens, against $0.18 / $1.11 for Step 3.7 Flash.
- Step 3.7 Flash accepts more context: 256K tokens versus 128K.
- Step 3.7 Flash has downloadable open weights; the other is API-only.
Side by side
| Grok 4.1 Fast | Step 3.7 Flash | |
|---|---|---|
| Provider | xAI | StepFun |
| Noometry Index | 41.4 | 37.3 |
| Released | 2025-06-27 | 2026-05-29 |
| Weights | Proprietary | Open |
| Context window | 128K | 256K |
| Max output | 30K | 256K |
| Input $ / M tokens | $0.20 | $0.18 |
| Output $ / M tokens | $0.50 | $1.11 |
| Results tracked | 32 | 5 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Step 3.7 Flash leads
Grok 4.1 Fast: 34.1 (#245), Step 3.7 Flash: 40.0 (#150)
| Benchmark | Grok 4.1 Fast | Step 3.7 Flash |
|---|---|---|
| ALE-Bench | 394.93 | 694.12 |
| LMArena WebDev | 1242 | — |
| SciCode | — | 40% |
| LMArena Coding | 1411 | — |
Agentic & Tool Use Not comparable
Grok 4.1 Fast: 36.3 (#39), Step 3.7 Flash: —
| Benchmark | Grok 4.1 Fast | Step 3.7 Flash |
|---|---|---|
| Berkeley Function Calling Leaderboard | 69.6% | — |
| τ²-bench Banking | 13.1% | — |
| LMArena Search | 1171 | — |
| Vending-Bench 2 | 1,107 | — |
Reasoning Grok 4.1 Fast leads
Grok 4.1 Fast: 43.4 (#49), Step 3.7 Flash: 21.6 (#219)
| Benchmark | Grok 4.1 Fast | Step 3.7 Flash |
|---|---|---|
| NYT Connections (extended) | 87.4% | 39.7% |
| SimpleBench | 56% | — |
| CritPt | — | 2.3% |
| LMArena Hard Prompts | 1407 | — |
| DTBench | 87.7% | — |
| ForecastBench | 61 | — |
Math Step 3.7 Flash leads
Grok 4.1 Fast: 31.9 (#221), Step 3.7 Flash: 42.9 (#82)
| Benchmark | Grok 4.1 Fast | Step 3.7 Flash |
|---|---|---|
| MathArena Final-Answer Competitions | 60.9% | 68.5% |
| ProofBench | 4% | — |
| LMArena Math | 1408 | — |
Knowledge Not comparable
Grok 4.1 Fast: 33.1 (#207), Step 3.7 Flash: —
| Benchmark | Grok 4.1 Fast | Step 3.7 Flash |
|---|---|---|
| Vectara Hallucination Rate | 17.8% | — |
| LMArena Expert | 1399 | — |
Multimodal Not comparable
Grok 4.1 Fast: 37.0 (#76), Step 3.7 Flash: —
| Benchmark | Grok 4.1 Fast | Step 3.7 Flash |
|---|---|---|
| LMArena Vision | 1201 | — |
Multilingual Not comparable
Grok 4.1 Fast: 51.0 (#114), Step 3.7 Flash: —
| Benchmark | Grok 4.1 Fast | Step 3.7 Flash |
|---|---|---|
| LMArena Non-English | 1391 | — |
| LMArena Chinese | 1441 | — |
| LMArena French | 1415 | — |
| LMArena German | 1404 | — |
| LMArena Japanese | 1349 | — |
| LMArena Korean | 1361 | — |
| LMArena Russian | 1387 | — |
| LMArena Spanish | 1413 | — |
Instruction Following Not comparable
Grok 4.1 Fast: 72.7 (#133), Step 3.7 Flash: —
| Benchmark | Grok 4.1 Fast | Step 3.7 Flash |
|---|---|---|
| LMArena Instruction Following | 1376 | — |
Long Context Not comparable
Grok 4.1 Fast: 42.4 (#126), Step 3.7 Flash: —
| Benchmark | Grok 4.1 Fast | Step 3.7 Flash |
|---|---|---|
| LMArena Longer Query | 1390 | — |
Writing & Preference Not comparable
Grok 4.1 Fast: 57.2 (#131), Step 3.7 Flash: —
| Benchmark | Grok 4.1 Fast | Step 3.7 Flash |
|---|---|---|
| LMArena Text | 1408 | — |
| LMArena Creative Writing | 1394 | — |
| EQ-Bench Creative Writing | 1327 | — |
| LMArena Multi-Turn | 1389 | — |
Frequently asked questions
Is Grok 4.1 Fast better than Step 3.7 Flash?
Grok 4.1 Fast is the stronger model overall, scoring 41.4 to 37.3 on the Noometry Index.
Which is cheaper, Grok 4.1 Fast or Step 3.7 Flash?
Grok 4.1 Fast is cheaper. It lists at $0.20 per million input tokens and $0.50 per million output tokens; Step 3.7 Flash lists at $0.18 and $1.11.
Is Grok 4.1 Fast or Step 3.7 Flash better for coding?
Step 3.7 Flash scores higher on coding benchmarks: 40.0 versus 34.1 in the Noometry coding category.
Which has the bigger context window?
Step 3.7 Flash does, with 256K tokens against 128K.
How many benchmarks do Grok 4.1 Fast and Step 3.7 Flash share?
3 benchmarks have published results for both models. Grok 4.1 Fast has 32 scored results on Noometry and Step 3.7 Flash has 5.