Model comparison
Grok-3 mini vs Step 3.5 Flash
Grok-3 mini and Step 3.5 Flash score almost the same on the Noometry Index (41.0 vs 41.7), so choose on price, context window or the category you care about most.
Last verified . 17 shared benchmarks.
StepFunSummary
- They share 17 benchmarks with published results for both. Grok-3 mini scores higher in 2 categories and Step 3.5 Flash in 6 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Step 3.5 Flash leads 21.2 to 13.8.
- Step 3.5 Flash has downloadable open weights; the other is API-only.
Side by side
| Grok-3 mini | Step 3.5 Flash | |
|---|---|---|
| Provider | xAI | StepFun |
| Noometry Index | 41.0 | 41.7 |
| Released | 2025-04-09 | 2026-01-29 |
| Weights | Proprietary | Open |
| Context window | — | 256K |
| Max output | — | 256K |
| Input $ / M tokens | — | $0.10 |
| Output $ / M tokens | — | $0.30 |
| Results tracked | 35 | 19 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Step 3.5 Flash leads
Grok-3 mini: 40.4 (#126), Step 3.5 Flash: 41.7 (#106)
| Benchmark | Grok-3 mini | Step 3.5 Flash |
|---|---|---|
| LMArena Coding | 1380 | 1436 |
| Aider Polyglot | 49.3% | — |
| WeirdML | 42.6% | — |
Reasoning Step 3.5 Flash leads
Grok-3 mini: 13.8 (#323), Step 3.5 Flash: 21.2 (#202)
| Benchmark | Grok-3 mini | Step 3.5 Flash |
|---|---|---|
| LMArena Hard Prompts | 1374 | 1411 |
| ARC-AGI-2 | 0.4% | — |
| Kagi LLM Benchmark | 61.3% | — |
| NYT Connections (extended) | — | 28.4% |
| ARC-AGI-1 | 16.5% | — |
| Epoch Capabilities Index | 140.35 | — |
Math Too close to call
Grok-3 mini: 40.3 (#78), Step 3.5 Flash: 40.6 (#77)
| Benchmark | Grok-3 mini | Step 3.5 Flash |
|---|---|---|
| LMArena Math | 1386 | 1408 |
| MathArena Final-Answer Competitions | — | 66.8% |
| OTIS Mock AIME 2024-2025 | 77.8% | — |
| Omni-MATH | 31.8% | — |
| MATH Level 5 | 90.9% | — |
| FrontierMath (Feb 2025 set) | 5.9% | — |
Knowledge Grok-3 mini leads
Grok-3 mini: 46.3 (#75), Step 3.5 Flash: 39.0 (#127)
| Benchmark | Grok-3 mini | Step 3.5 Flash |
|---|---|---|
| LMArena Expert | 1395 | 1422 |
| GPQA Diamond | 76.3% | — |
| MMLU-Pro | 79.9% | — |
| Confabulations | 10.8% | — |
| GPQA (HELM) | 67.5% | — |
Multilingual Step 3.5 Flash leads
Grok-3 mini: 48.3 (#141), Step 3.5 Flash: 50.7 (#115)
| Benchmark | Grok-3 mini | Step 3.5 Flash |
|---|---|---|
| LMArena Non-English | 1352 | 1386 |
| LMArena Chinese | 1387 | 1448 |
| LMArena French | 1357 | 1421 |
| LMArena German | 1350 | 1404 |
| LMArena Japanese | 1343 | 1353 |
| LMArena Korean | 1336 | 1350 |
| LMArena Russian | 1352 | 1385 |
| LMArena Spanish | 1379 | 1419 |
Instruction Following Grok-3 mini leads
Grok-3 mini: 78.7 (#8), Step 3.5 Flash: 73.3 (#119)
| Benchmark | Grok-3 mini | Step 3.5 Flash |
|---|---|---|
| LMArena Instruction Following | 1356 | 1385 |
| IFEval | 95.1% | — |
Long Context Step 3.5 Flash leads
Grok-3 mini: 41.0 (#142), Step 3.5 Flash: 42.8 (#112)
| Benchmark | Grok-3 mini | Step 3.5 Flash |
|---|---|---|
| LMArena Longer Query | 1372 | 1402 |
| Fiction.LiveBench | 66.7% | — |
Writing & Preference Step 3.5 Flash leads
Grok-3 mini: 52.7 (#163), Step 3.5 Flash: 59.0 (#108)
| Benchmark | Grok-3 mini | Step 3.5 Flash |
|---|---|---|
| LMArena Text | 1370 | 1403 |
| LMArena Creative Writing | 1342 | 1357 |
| LMArena Multi-Turn | 1355 | 1405 |
| Short-Story Creative Writing | 73.5% | — |
| WildBench | 65.1% | — |
Frequently asked questions
Is Grok-3 mini better than Step 3.5 Flash?
Grok-3 mini and Step 3.5 Flash score almost the same on the Noometry Index (41.0 vs 41.7), so choose on price, context window or the category you care about most.
Is Grok-3 mini or Step 3.5 Flash better for coding?
Step 3.5 Flash scores higher on coding benchmarks: 41.7 versus 40.4 in the Noometry coding category.
How many benchmarks do Grok-3 mini and Step 3.5 Flash share?
17 benchmarks have published results for both models. Grok-3 mini has 35 scored results on Noometry and Step 3.5 Flash has 19.