Model comparison
Step 2 16k Exp 202412 vs Step 3
Step 3 is the stronger model overall, scoring 40.5 to 39.2 on the Noometry Index.
Last verified . 12 shared benchmarks.
StepFunSummary
- They share 12 benchmarks with published results for both. Step 2 16k Exp 202412 scores higher in 0 categories and Step 3 in 8 categories; 7 gaps are clear of the uncertainty.
- Step 3 has downloadable open weights; the other is API-only.
Side by side
| Step 2 16k Exp 202412 | Step 3 | |
|---|---|---|
| Provider | StepFun | StepFun |
| Noometry Index | 39.2 | 40.5 |
| Released | — | — |
| Weights | Proprietary | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 12 | 17 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Step 3 leads
Step 2 16k Exp 202412: 38.5 (#174), Step 3: 40.1 (#147)
| Benchmark | Step 2 16k Exp 202412 | Step 3 |
|---|---|---|
| LMArena Coding | 1316 | 1367 |
Reasoning Step 3 leads
Step 2 16k Exp 202412: 25.9 (#142), Step 3: 28.4 (#105)
| Benchmark | Step 2 16k Exp 202412 | Step 3 |
|---|---|---|
| LMArena Hard Prompts | 1299 | 1355 |
| Kagi LLM Benchmark | — | 62.3% |
Math Step 3 leads
Step 2 16k Exp 202412: 36.3 (#169), Step 3: 37.6 (#148)
| Benchmark | Step 2 16k Exp 202412 | Step 3 |
|---|---|---|
| LMArena Math | 1304 | 1366 |
Knowledge Step 3 leads
Step 2 16k Exp 202412: 35.2 (#187), Step 3: 36.8 (#164)
| Benchmark | Step 2 16k Exp 202412 | Step 3 |
|---|---|---|
| LMArena Expert | 1279 | 1333 |
Multimodal Not comparable
Step 2 16k Exp 202412: —, Step 3: 35.5 (#86)
| Benchmark | Step 2 16k Exp 202412 | Step 3 |
|---|---|---|
| LMArena Vision | — | 1177 |
Multilingual Step 3 leads
Step 2 16k Exp 202412: 43.7 (#181), Step 3: 46.3 (#159)
| Benchmark | Step 2 16k Exp 202412 | Step 3 |
|---|---|---|
| LMArena Non-English | 1290 | 1327 |
| LMArena Chinese | 1331 | 1397 |
| LMArena Russian | 1324 | 1331 |
| LMArena German | — | 1371 |
| LMArena Korean | — | 1269 |
| LMArena Spanish | — | 1371 |
Instruction Following Step 3 leads
Step 2 16k Exp 202412: 67.9 (#192), Step 3: 70.4 (#164)
| Benchmark | Step 2 16k Exp 202412 | Step 3 |
|---|---|---|
| LMArena Instruction Following | 1287 | 1332 |
Long Context Too close to call
Step 2 16k Exp 202412: 39.7 (#170), Step 3: 40.3 (#157)
| Benchmark | Step 2 16k Exp 202412 | Step 3 |
|---|---|---|
| LMArena Longer Query | 1307 | 1326 |
Writing & Preference Step 3 leads
Step 2 16k Exp 202412: 52.3 (#173), Step 3: 54.3 (#151)
| Benchmark | Step 2 16k Exp 202412 | Step 3 |
|---|---|---|
| LMArena Text | 1321 | 1350 |
| LMArena Creative Writing | 1328 | 1321 |
| LMArena Multi-Turn | 1292 | 1341 |
Frequently asked questions
Is Step 2 16k Exp 202412 better than Step 3?
Step 3 is the stronger model overall, scoring 40.5 to 39.2 on the Noometry Index.
Is Step 2 16k Exp 202412 or Step 3 better for coding?
Step 3 scores higher on coding benchmarks: 40.1 versus 38.5 in the Noometry coding category.
How many benchmarks do Step 2 16k Exp 202412 and Step 3 share?
12 benchmarks have published results for both models. Step 2 16k Exp 202412 has 12 scored results on Noometry and Step 3 has 17.