Model comparison
Amazon Nova Lite vs Step 3
Step 3 is the stronger model overall, scoring 40.5 to 31.9 on the Noometry Index.
Last verified . 16 shared benchmarks.
StepFunSummary
- They share 16 benchmarks with published results for both. Amazon Nova Lite scores higher in 0 categories and Step 3 in 9 categories; 9 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Step 3 leads 54.3 to 42.1.
- Step 3 has downloadable open weights; the other is API-only.
Side by side
| Amazon Nova Lite | Step 3 | |
|---|---|---|
| Provider | Amazon | StepFun |
| Noometry Index | 31.9 | 40.5 |
| Released | 2024-12-03 | — |
| Weights | Proprietary | Open |
| Context window | 300K | — |
| Max output | 10K | — |
| Input $ / M tokens | $0.06 | — |
| Output $ / M tokens | $0.24 | — |
| Results tracked | 34 | 17 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Step 3 leads
Amazon Nova Lite: 32.5 (#270), Step 3: 40.1 (#147)
| Benchmark | Amazon Nova Lite | Step 3 |
|---|---|---|
| LMArena Coding | 1239 | 1367 |
| LiveBench Coding | 27.5% | — |
| ALE-Bench | 236.25 | — |
Reasoning Step 3 leads
Amazon Nova Lite: 19.3 (#260), Step 3: 28.4 (#105)
| Benchmark | Amazon Nova Lite | Step 3 |
|---|---|---|
| LMArena Hard Prompts | 1220 | 1355 |
| Kagi LLM Benchmark | — | 62.3% |
| LiveBench Reasoning | 36.7% | — |
| LiveBench Data Analysis | 37.2% | — |
| LiveBench | 36.4% | — |
Math Step 3 leads
Amazon Nova Lite: 27.8 (#247), Step 3: 37.6 (#148)
| Benchmark | Amazon Nova Lite | Step 3 |
|---|---|---|
| LMArena Math | 1227 | 1366 |
| Omni-MATH | 23.3% | — |
| LiveBench Math | 36.7% | — |
Knowledge Step 3 leads
Amazon Nova Lite: 26.3 (#259), Step 3: 36.8 (#164)
| Benchmark | Amazon Nova Lite | Step 3 |
|---|---|---|
| LMArena Expert | 1201 | 1333 |
| Humanity's Last Exam | 3.6% | — |
| MMLU-Pro | 60% | — |
| Vectara Hallucination Rate | 6.1% | — |
| GPQA (HELM) | 39.7% | — |
| MMLU | 77% | — |
Multimodal Step 3 leads
Amazon Nova Lite: 25.5 (#123), Step 3: 35.5 (#86)
| Benchmark | Amazon Nova Lite | Step 3 |
|---|---|---|
| LMArena Vision | 990 | 1177 |
Multilingual Step 3 leads
Amazon Nova Lite: 38.0 (#232), Step 3: 46.3 (#159)
| Benchmark | Amazon Nova Lite | Step 3 |
|---|---|---|
| LMArena Non-English | 1208 | 1327 |
| LMArena Chinese | 1225 | 1397 |
| LMArena German | 1229 | 1371 |
| LMArena Korean | 1153 | 1269 |
| LMArena Russian | 1216 | 1331 |
| LMArena Spanish | 1226 | 1371 |
| LMArena French | 1237 | — |
| LMArena Japanese | 1153 | — |
Instruction Following Step 3 leads
Amazon Nova Lite: 59.3 (#255), Step 3: 70.4 (#164)
| Benchmark | Amazon Nova Lite | Step 3 |
|---|---|---|
| LMArena Instruction Following | 1205 | 1332 |
| LiveBench Instruction Following | 54.1% | — |
| IFEval | 77.6% | — |
Long Context Step 3 leads
Amazon Nova Lite: 37.4 (#217), Step 3: 40.3 (#157)
| Benchmark | Amazon Nova Lite | Step 3 |
|---|---|---|
| LMArena Longer Query | 1234 | 1326 |
Writing & Preference Step 3 leads
Amazon Nova Lite: 42.1 (#237), Step 3: 54.3 (#151)
| Benchmark | Amazon Nova Lite | Step 3 |
|---|---|---|
| LMArena Text | 1229 | 1350 |
| LMArena Creative Writing | 1197 | 1321 |
| LMArena Multi-Turn | 1199 | 1341 |
| WildBench | 75% | — |
| LiveBench Language | 25.9% | — |
Frequently asked questions
Is Amazon Nova Lite better than Step 3?
Step 3 is the stronger model overall, scoring 40.5 to 31.9 on the Noometry Index.
Is Amazon Nova Lite or Step 3 better for coding?
Step 3 scores higher on coding benchmarks: 40.1 versus 32.5 in the Noometry coding category.
How many benchmarks do Amazon Nova Lite and Step 3 share?
16 benchmarks have published results for both models. Amazon Nova Lite has 34 scored results on Noometry and Step 3 has 17.