Model comparison
Grok-3 mini vs Step 3.7 Flash
Grok-3 mini is the stronger model overall, scoring 41.2 to 37.3 on the Noometry Index.
Last verified . 0 shared benchmarks.
StepFunSummary
- The widest gap is in reasoning, where Step 3.7 Flash leads 21.6 to 13.6.
- Step 3.7 Flash has downloadable open weights; the other is API-only.
Side by side
| Grok-3 mini | Step 3.7 Flash | |
|---|---|---|
| Provider | xAI | StepFun |
| Noometry Index | 41.2 | 37.3 |
| Released | 2025-04-09 | 2026-05-29 |
| Weights | Proprietary | Open |
| Context window | — | 256K |
| Max output | — | 256K |
| Input $ / M tokens | — | $0.18 |
| Output $ / M tokens | — | $1.11 |
| Results tracked | 35 | 5 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
Grok-3 mini: 40.8 (#131), Step 3.7 Flash: 40.0 (#150)
| Benchmark | Grok-3 mini | Step 3.7 Flash |
|---|---|---|
| Aider Polyglot | 49.3% | — |
| SciCode | — | 40% |
| WeirdML | 42.6% | — |
| LMArena Coding | 1379 | — |
| ALE-Bench | — | 694.12 |
Reasoning Step 3.7 Flash leads
Grok-3 mini: 13.6 (#334), Step 3.7 Flash: 21.6 (#219)
| Benchmark | Grok-3 mini | Step 3.7 Flash |
|---|---|---|
| ARC-AGI-2 | 0.4% | — |
| Kagi LLM Benchmark | 61.3% | — |
| NYT Connections (extended) | — | 39.7% |
| ARC-AGI-1 | 16.5% | — |
| CritPt | — | 2.3% |
| LMArena Hard Prompts | 1375 | — |
| Epoch Capabilities Index | 140.35 | — |
Math Too close to call
Grok-3 mini: 42.1 (#85), Step 3.7 Flash: 42.9 (#82)
| Benchmark | Grok-3 mini | Step 3.7 Flash |
|---|---|---|
| MathArena Final-Answer Competitions | — | 68.5% |
| OTIS Mock AIME 2024-2025 | 77.8% | — |
| Omni-MATH | 31.8% | — |
| LMArena Math | 1386 | — |
| MATH Level 5 | 90.9% | — |
| FrontierMath (Feb 2025 set) | 5.9% | — |
Knowledge Not comparable
Grok-3 mini: 46.4 (#81), Step 3.7 Flash: —
| Benchmark | Grok-3 mini | Step 3.7 Flash |
|---|---|---|
| GPQA Diamond | 76.3% | — |
| MMLU-Pro | 79.9% | — |
| Confabulations | 10.8% | — |
| GPQA (HELM) | 67.5% | — |
| LMArena Expert | 1395 | — |
Multilingual Not comparable
Grok-3 mini: 48.1 (#145), Step 3.7 Flash: —
| Benchmark | Grok-3 mini | Step 3.7 Flash |
|---|---|---|
| LMArena Non-English | 1352 | — |
| LMArena Chinese | 1387 | — |
| LMArena French | 1357 | — |
| LMArena German | 1349 | — |
| LMArena Japanese | 1342 | — |
| LMArena Korean | 1335 | — |
| LMArena Russian | 1353 | — |
| LMArena Spanish | 1381 | — |
Instruction Following Not comparable
Grok-3 mini: 78.5 (#9), Step 3.7 Flash: —
| Benchmark | Grok-3 mini | Step 3.7 Flash |
|---|---|---|
| IFEval | 95.1% | — |
| LMArena Instruction Following | 1357 | — |
Long Context Not comparable
Grok-3 mini: 41.0 (#147), Step 3.7 Flash: —
| Benchmark | Grok-3 mini | Step 3.7 Flash |
|---|---|---|
| Fiction.LiveBench | 66.7% | — |
| LMArena Longer Query | 1372 | — |
Writing & Preference Not comparable
Grok-3 mini: 52.5 (#169), Step 3.7 Flash: —
| Benchmark | Grok-3 mini | Step 3.7 Flash |
|---|---|---|
| LMArena Text | 1370 | — |
| LMArena Creative Writing | 1342 | — |
| Short-Story Creative Writing | 73.5% | — |
| WildBench | 65.1% | — |
| LMArena Multi-Turn | 1355 | — |
Frequently asked questions
Is Grok-3 mini better than Step 3.7 Flash?
Grok-3 mini is the stronger model overall, scoring 41.2 to 37.3 on the Noometry Index.
Is Grok-3 mini or Step 3.7 Flash better for coding?
They score almost the same on coding (40.8 vs 40.0); test both on your own repository before choosing.
How many benchmarks do Grok-3 mini and Step 3.7 Flash share?
0 benchmarks have published results for both models. Grok-3 mini has 35 scored results on Noometry and Step 3.7 Flash has 5.