Model comparison
StarCoder 2 3B vs Step 5 Preview
Step 5 Preview has enough public results to be ranked (#58); StarCoder 2 3B does not yet, so treat this comparison as directional.
Last verified . 0 shared benchmarks.
NVIDIA
StepFunSummary
- The widest gap is in coding, where Step 5 Preview leads 51.8 to 33.5.
- StarCoder 2 3B has downloadable open weights; the other is API-only.
Side by side
| StarCoder 2 3B | Step 5 Preview | |
|---|---|---|
| Provider | NVIDIA | StepFun |
| Noometry Index | 36.3 | 47.9 |
| Released | 2024-02-22 | 2026-09-16 |
| Weights | Open | Proprietary |
| Context window | — | 1.02M |
| Max output | — | 66K |
| Input $ / M tokens | — | $1 |
| Output $ / M tokens | — | $2.70 |
| Results tracked | 7 | 18 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Step 5 Preview leads
StarCoder 2 3B: 33.5, Step 5 Preview: 51.8 (#36)
| Benchmark | StarCoder 2 3B | Step 5 Preview |
|---|---|---|
| LMArena WebDev | — | 1564 |
| SciCode | — | 58.9% |
| LMArena Coding | — | 1480 |
| BigCodeBench Complete | 21.4% | — |
| HumanEval+ | 27.4% | — |
Reasoning Not comparable
StarCoder 2 3B: —, Step 5 Preview: 40.0 (#57)
| Benchmark | StarCoder 2 3B | Step 5 Preview |
|---|---|---|
| CritPt | — | 20.9% |
| LMArena Hard Prompts | — | 1465 |
| Epoch Capabilities Index | 88.76 | — |
| WinoGrande | 57.1% | — |
Math Not comparable
StarCoder 2 3B: —, Step 5 Preview: 46.1 (#72)
| Benchmark | StarCoder 2 3B | Step 5 Preview |
|---|---|---|
| ProofBench | — | 42% |
| LMArena Math | — | 1470 |
| GSM8K | 21.6% | — |
Knowledge Not comparable
StarCoder 2 3B: —, Step 5 Preview: 41.2 (#112)
| Benchmark | StarCoder 2 3B | Step 5 Preview |
|---|---|---|
| LMArena Expert | — | 1470 |
| ARC (AI2) Challenge | 34.2% | — |
| MMLU | 36.6% | — |
Multimodal Not comparable
StarCoder 2 3B: —, Step 5 Preview: 41.0 (#41)
| Benchmark | StarCoder 2 3B | Step 5 Preview |
|---|---|---|
| LMArena Vision | — | 1267 |
Multilingual Not comparable
StarCoder 2 3B: —, Step 5 Preview: 53.8 (#54)
| Benchmark | StarCoder 2 3B | Step 5 Preview |
|---|---|---|
| LMArena Non-English | — | 1432 |
| LMArena Chinese | — | 1519 |
| LMArena Russian | — | 1436 |
| LMArena Spanish | — | 1439 |
Instruction Following Not comparable
StarCoder 2 3B: —, Step 5 Preview: 76.0 (#50)
| Benchmark | StarCoder 2 3B | Step 5 Preview |
|---|---|---|
| LMArena Instruction Following | — | 1444 |
Long Context Not comparable
StarCoder 2 3B: —, Step 5 Preview: 44.5 (#64)
| Benchmark | StarCoder 2 3B | Step 5 Preview |
|---|---|---|
| LMArena Longer Query | — | 1455 |
Writing & Preference Not comparable
StarCoder 2 3B: —, Step 5 Preview: 62.8 (#71)
| Benchmark | StarCoder 2 3B | Step 5 Preview |
|---|---|---|
| LMArena Text | — | 1442 |
| LMArena Creative Writing | — | 1410 |
| LMArena Multi-Turn | — | 1447 |
Frequently asked questions
Is StarCoder 2 3B better than Step 5 Preview?
Step 5 Preview has enough public results to be ranked (#58); StarCoder 2 3B does not yet, so treat this comparison as directional.
Is StarCoder 2 3B or Step 5 Preview better for coding?
Step 5 Preview scores higher on coding benchmarks: 51.8 versus 33.5 in the Noometry coding category.
How many benchmarks do StarCoder 2 3B and Step 5 Preview share?
0 benchmarks have published results for both models. StarCoder 2 3B has 7 scored results on Noometry and Step 5 Preview has 18.