Model comparison
Grok 3 vs Step 3.5 Flash
Step 3.5 Flash is the stronger model overall, scoring 41.7 to 39.6 on the Noometry Index.
Last verified . 17 shared benchmarks.
StepFunSummary
- They share 17 benchmarks with published results for both. Grok 3 scores higher in 3 categories and Step 3.5 Flash in 5 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 | Step 3.5 Flash | |
|---|---|---|
| Provider | xAI | StepFun |
| Noometry Index | 39.6 | 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 | 40 | 19 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
Grok 3: 41.5 (#113), Step 3.5 Flash: 41.7 (#106)
| Benchmark | Grok 3 | Step 3.5 Flash |
|---|---|---|
| LMArena Coding | 1432 | 1436 |
| Aider Polyglot | 53.3% | — |
| WeirdML | 37.2% | — |
Agentic & Tool Use Not comparable
Grok 3: 30.2 (#69), Step 3.5 Flash: —
| Benchmark | Grok 3 | Step 3.5 Flash |
|---|---|---|
| BALROG | 29.5% | — |
Reasoning Step 3.5 Flash leads
Grok 3: 13.8 (#322), Step 3.5 Flash: 21.2 (#202)
| Benchmark | Grok 3 | Step 3.5 Flash |
|---|---|---|
| LMArena Hard Prompts | 1433 | 1411 |
| ARC-AGI-2 | 0% | — |
| SimpleBench | 36.1% | — |
| Kagi LLM Benchmark | 61.3% | — |
| NYT Connections (extended) | — | 28.4% |
| ARC-AGI-1 | 5.5% | — |
| Epoch Capabilities Index | 138.34 | — |
Math Step 3.5 Flash leads
Grok 3: 36.2 (#122), Step 3.5 Flash: 40.6 (#77)
| Benchmark | Grok 3 | Step 3.5 Flash |
|---|---|---|
| LMArena Math | 1390 | 1408 |
| MathArena Final-Answer Competitions | — | 66.8% |
| OTIS Mock AIME 2024-2025 | 55.6% | — |
| Omni-MATH | 46.4% | — |
| MATH Level 5 | 88.7% | — |
| FrontierMath (Feb 2025 set) | 3.8% | — |
| FrontierMath Tier 4 (v1) | 0% | — |
Knowledge Grok 3 leads
Grok 3: 46.0 (#76), Step 3.5 Flash: 39.0 (#127)
| Benchmark | Grok 3 | Step 3.5 Flash |
|---|---|---|
| LMArena Expert | 1420 | 1422 |
| GPQA Diamond | 75.8% | — |
| MMLU-Pro | 78.8% | — |
| Confabulations | 14.2% | — |
| Vectara Hallucination Rate | 5.8% | — |
| GPQA (HELM) | 65% | — |
Multilingual Grok 3 leads
Grok 3: 52.5 (#81), Step 3.5 Flash: 50.7 (#115)
| Benchmark | Grok 3 | Step 3.5 Flash |
|---|---|---|
| LMArena Non-English | 1411 | 1386 |
| LMArena Chinese | 1448 | 1448 |
| LMArena French | 1460 | 1421 |
| LMArena German | 1431 | 1404 |
| LMArena Japanese | 1389 | 1353 |
| LMArena Korean | 1374 | 1350 |
| LMArena Russian | 1416 | 1385 |
| LMArena Spanish | 1417 | 1419 |
Instruction Following Grok 3 leads
Grok 3: 75.2 (#69), Step 3.5 Flash: 73.3 (#119)
| Benchmark | Grok 3 | Step 3.5 Flash |
|---|---|---|
| LMArena Instruction Following | 1409 | 1385 |
| IFEval | 88.4% | — |
Long Context Step 3.5 Flash leads
Grok 3: 38.7 (#187), Step 3.5 Flash: 42.8 (#112)
| Benchmark | Grok 3 | Step 3.5 Flash |
|---|---|---|
| LMArena Longer Query | 1439 | 1402 |
| Fiction.LiveBench | 58.3% | — |
Writing & Preference Step 3.5 Flash leads
Grok 3: 56.0 (#136), Step 3.5 Flash: 59.0 (#108)
| Benchmark | Grok 3 | Step 3.5 Flash |
|---|---|---|
| LMArena Text | 1426 | 1403 |
| LMArena Creative Writing | 1414 | 1357 |
| LMArena Multi-Turn | 1424 | 1405 |
| Short-Story Creative Writing | 76.4% | — |
| EQ-Bench Creative Writing | 1186 | — |
| WildBench | 84.9% | — |
Frequently asked questions
Is Grok 3 better than Step 3.5 Flash?
Step 3.5 Flash is the stronger model overall, scoring 41.7 to 39.6 on the Noometry Index.
Is Grok 3 or Step 3.5 Flash better for coding?
They score almost the same on coding (41.5 vs 41.7); test both on your own repository before choosing.
How many benchmarks do Grok 3 and Step 3.5 Flash share?
17 benchmarks have published results for both models. Grok 3 has 40 scored results on Noometry and Step 3.5 Flash has 19.