Model comparison
Grok-3 mini vs Step 2 16k Exp 202412
Grok-3 mini is the stronger model overall, scoring 41.2 to 39.2 on the Noometry Index.
Last verified . 12 shared benchmarks.
StepFunSummary
- They share 12 benchmarks with published results for both. Grok-3 mini scores higher in 7 categories and Step 2 16k Exp 202412 in 1 category; 7 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Step 2 16k Exp 202412 leads 25.9 to 13.6.
Side by side
| Grok-3 mini | Step 2 16k Exp 202412 | |
|---|---|---|
| Provider | xAI | StepFun |
| Noometry Index | 41.2 | 39.2 |
| Released | 2025-04-09 | — |
| Weights | Proprietary | Proprietary |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 35 | 12 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Grok-3 mini leads
Grok-3 mini: 40.8 (#131), Step 2 16k Exp 202412: 38.5 (#174)
| Benchmark | Grok-3 mini | Step 2 16k Exp 202412 |
|---|---|---|
| LMArena Coding | 1379 | 1316 |
| Aider Polyglot | 49.3% | — |
| WeirdML | 42.6% | — |
Reasoning Step 2 16k Exp 202412 leads
Grok-3 mini: 13.6 (#334), Step 2 16k Exp 202412: 25.9 (#142)
| Benchmark | Grok-3 mini | Step 2 16k Exp 202412 |
|---|---|---|
| LMArena Hard Prompts | 1375 | 1299 |
| ARC-AGI-2 | 0.4% | — |
| Kagi LLM Benchmark | 61.3% | — |
| ARC-AGI-1 | 16.5% | — |
| Epoch Capabilities Index | 140.35 | — |
Math Grok-3 mini leads
Grok-3 mini: 42.1 (#85), Step 2 16k Exp 202412: 36.3 (#169)
| Benchmark | Grok-3 mini | Step 2 16k Exp 202412 |
|---|---|---|
| LMArena Math | 1386 | 1304 |
| 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: 46.4 (#81), Step 2 16k Exp 202412: 35.2 (#187)
| Benchmark | Grok-3 mini | Step 2 16k Exp 202412 |
|---|---|---|
| LMArena Expert | 1395 | 1279 |
| GPQA Diamond | 76.3% | — |
| MMLU-Pro | 79.9% | — |
| Confabulations | 10.8% | — |
| GPQA (HELM) | 67.5% | — |
Multilingual Grok-3 mini leads
Grok-3 mini: 48.1 (#145), Step 2 16k Exp 202412: 43.7 (#181)
| Benchmark | Grok-3 mini | Step 2 16k Exp 202412 |
|---|---|---|
| LMArena Non-English | 1352 | 1290 |
| LMArena Chinese | 1387 | 1331 |
| LMArena Russian | 1353 | 1324 |
| LMArena French | 1357 | — |
| LMArena German | 1349 | — |
| LMArena Japanese | 1342 | — |
| LMArena Korean | 1335 | — |
| LMArena Spanish | 1381 | — |
Instruction Following Grok-3 mini leads
Grok-3 mini: 78.5 (#9), Step 2 16k Exp 202412: 67.9 (#192)
| Benchmark | Grok-3 mini | Step 2 16k Exp 202412 |
|---|---|---|
| LMArena Instruction Following | 1357 | 1287 |
| IFEval | 95.1% | — |
Long Context Grok-3 mini leads
Grok-3 mini: 41.0 (#147), Step 2 16k Exp 202412: 39.7 (#170)
| Benchmark | Grok-3 mini | Step 2 16k Exp 202412 |
|---|---|---|
| LMArena Longer Query | 1372 | 1307 |
| Fiction.LiveBench | 66.7% | — |
Writing & Preference Too close to call
Grok-3 mini: 52.5 (#169), Step 2 16k Exp 202412: 52.3 (#173)
| Benchmark | Grok-3 mini | Step 2 16k Exp 202412 |
|---|---|---|
| LMArena Text | 1370 | 1321 |
| LMArena Creative Writing | 1342 | 1328 |
| LMArena Multi-Turn | 1355 | 1292 |
| Short-Story Creative Writing | 73.5% | — |
| WildBench | 65.1% | — |
Frequently asked questions
Is Grok-3 mini better than Step 2 16k Exp 202412?
Grok-3 mini is the stronger model overall, scoring 41.2 to 39.2 on the Noometry Index.
Is Grok-3 mini or Step 2 16k Exp 202412 better for coding?
Grok-3 mini scores higher on coding benchmarks: 40.8 versus 38.5 in the Noometry coding category.
How many benchmarks do Grok-3 mini and Step 2 16k Exp 202412 share?
12 benchmarks have published results for both models. Grok-3 mini has 35 scored results on Noometry and Step 2 16k Exp 202412 has 12.