Model comparison
Grok-2 (Dec 2024) vs Step 3
Step 3 is the stronger model overall, scoring 40.5 to 33.7 on the Noometry Index.
Last verified . 15 shared benchmarks.
StepFunSummary
- They share 15 benchmarks with published results for both. Grok-2 (Dec 2024) scores higher in 0 categories and Step 3 in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Step 3 leads 37.6 to 20.8.
- Step 3 has downloadable open weights; the other is API-only.
Side by side
| Grok-2 (Dec 2024) | Step 3 | |
|---|---|---|
| Provider | xAI | StepFun |
| Noometry Index | 33.7 | 40.5 |
| Released | 2024-08-13 | — |
| Weights | Proprietary | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 34 | 17 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Step 3 leads
Grok-2 (Dec 2024): 33.3 (#258), Step 3: 40.1 (#147)
| Benchmark | Grok-2 (Dec 2024) | Step 3 |
|---|---|---|
| LMArena Coding | 1287 | 1367 |
| WeirdML | 22.2% | — |
| LiveBench Coding | 46.4% | — |
Reasoning Step 3 leads
Grok-2 (Dec 2024): 16.9 (#299), Step 3: 28.4 (#105)
| Benchmark | Grok-2 (Dec 2024) | Step 3 |
|---|---|---|
| LMArena Hard Prompts | 1272 | 1355 |
| SimpleBench | 22.7% | — |
| Kagi LLM Benchmark | — | 62.3% |
| LiveBench Reasoning | 54.8% | — |
| DTBench | 65.2% | — |
| LiveBench Data Analysis | 54.5% | — |
| Epoch Capabilities Index | 130.48 | — |
| LiveBench | 54.3% | — |
Math Step 3 leads
Grok-2 (Dec 2024): 20.8 (#284), Step 3: 37.6 (#148)
| Benchmark | Grok-2 (Dec 2024) | Step 3 |
|---|---|---|
| LMArena Math | 1283 | 1366 |
| OTIS Mock AIME 2024-2025 | 11.5% | — |
| LiveBench Math | 54.9% | — |
| MATH Level 5 | 63.5% | — |
| FrontierMath (Feb 2025 set) | 0.7% | — |
Knowledge Step 3 leads
Grok-2 (Dec 2024): 29.8 (#233), Step 3: 36.8 (#164)
| Benchmark | Grok-2 (Dec 2024) | Step 3 |
|---|---|---|
| LMArena Expert | 1254 | 1333 |
| GPQA Diamond | 53.8% | — |
| Confabulations | 20.1% | — |
Multimodal Not comparable
Grok-2 (Dec 2024): —, Step 3: 35.5 (#86)
| Benchmark | Grok-2 (Dec 2024) | Step 3 |
|---|---|---|
| LMArena Vision | — | 1177 |
Multilingual Step 3 leads
Grok-2 (Dec 2024): 43.1 (#188), Step 3: 46.3 (#159)
| Benchmark | Grok-2 (Dec 2024) | Step 3 |
|---|---|---|
| LMArena Non-English | 1282 | 1327 |
| LMArena Chinese | 1289 | 1397 |
| LMArena German | 1287 | 1371 |
| LMArena Korean | 1237 | 1269 |
| LMArena Russian | 1286 | 1331 |
| LMArena Spanish | 1281 | 1371 |
| LMArena French | 1318 | — |
| LMArena Japanese | 1244 | — |
Instruction Following Step 3 leads
Grok-2 (Dec 2024): 66.9 (#202), Step 3: 70.4 (#164)
| Benchmark | Grok-2 (Dec 2024) | Step 3 |
|---|---|---|
| LMArena Instruction Following | 1270 | 1332 |
| LiveBench Instruction Following | 69.6% | — |
Long Context Step 3 leads
Grok-2 (Dec 2024): 38.8 (#190), Step 3: 40.3 (#157)
| Benchmark | Grok-2 (Dec 2024) | Step 3 |
|---|---|---|
| LMArena Longer Query | 1276 | 1326 |
Writing & Preference Step 3 leads
Grok-2 (Dec 2024): 48.6 (#198), Step 3: 54.3 (#151)
| Benchmark | Grok-2 (Dec 2024) | Step 3 |
|---|---|---|
| LMArena Text | 1305 | 1350 |
| LMArena Creative Writing | 1284 | 1321 |
| LMArena Multi-Turn | 1290 | 1341 |
| Short-Story Creative Writing | 63.6% | — |
| LiveBench Language | 45.6% | — |
Frequently asked questions
Is Grok-2 (Dec 2024) better than Step 3?
Step 3 is the stronger model overall, scoring 40.5 to 33.7 on the Noometry Index.
Is Grok-2 (Dec 2024) or Step 3 better for coding?
Step 3 scores higher on coding benchmarks: 40.1 versus 33.3 in the Noometry coding category.
How many benchmarks do Grok-2 (Dec 2024) and Step 3 share?
15 benchmarks have published results for both models. Grok-2 (Dec 2024) has 34 scored results on Noometry and Step 3 has 17.