Model comparison
Llama 3.2 3B vs Step 3
Step 3 is the stronger model overall, scoring 40.5 to 28.9 on the Noometry Index.
Last verified . 13 shared benchmarks.
Meta
StepFunSummary
- They share 13 benchmarks with published results for both. Llama 3.2 3B scores higher in 0 categories and Step 3 in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Step 3 leads 54.3 to 24.7.
Side by side
| Llama 3.2 3B | Step 3 | |
|---|---|---|
| Provider | Meta | StepFun |
| Noometry Index | 28.9 | 40.5 |
| Released | 2024-09-24 | — |
| Weights | Open | Open |
| Context window | 131K | — |
| Max output | 118K | — |
| Input $ / M tokens | $0.05 | — |
| Output $ / M tokens | $0.33 | — |
| Results tracked | 18 | 17 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Step 3 leads
Llama 3.2 3B: 27.6 (#319), Step 3: 40.1 (#147)
| Benchmark | Llama 3.2 3B | Step 3 |
|---|---|---|
| LMArena Coding | 1098 | 1367 |
| BigCodeBench Instruct | 23.4% | — |
| BigCodeBench Complete | 28.3% | — |
Agentic & Tool Use Not comparable
Llama 3.2 3B: 20.1 (#143), Step 3: —
| Benchmark | Llama 3.2 3B | Step 3 |
|---|---|---|
| Berkeley Function Calling Leaderboard | 21.9% | — |
| BALROG | 10.1% | — |
Reasoning Step 3 leads
Llama 3.2 3B: 21.0 (#228), Step 3: 28.4 (#105)
| Benchmark | Llama 3.2 3B | Step 3 |
|---|---|---|
| LMArena Hard Prompts | 1095 | 1355 |
| Kagi LLM Benchmark | — | 62.3% |
Math Step 3 leads
Llama 3.2 3B: 32.4 (#214), Step 3: 37.6 (#148)
| Benchmark | Llama 3.2 3B | Step 3 |
|---|---|---|
| LMArena Math | 1126 | 1366 |
Knowledge Step 3 leads
Llama 3.2 3B: 29.7 (#235), Step 3: 36.8 (#164)
| Benchmark | Llama 3.2 3B | Step 3 |
|---|---|---|
| LMArena Expert | 1090 | 1333 |
Multimodal Not comparable
Llama 3.2 3B: —, Step 3: 35.5 (#86)
| Benchmark | Llama 3.2 3B | Step 3 |
|---|---|---|
| LMArena Vision | — | 1177 |
Multilingual Step 3 leads
Llama 3.2 3B: 26.2 (#281), Step 3: 46.3 (#159)
| Benchmark | Llama 3.2 3B | Step 3 |
|---|---|---|
| LMArena Non-English | 1019 | 1327 |
| LMArena Chinese | 1017 | 1397 |
| LMArena German | 1056 | 1371 |
| LMArena Russian | 949 | 1331 |
| LMArena Korean | — | 1269 |
| LMArena Spanish | — | 1371 |
Instruction Following Step 3 leads
Llama 3.2 3B: 56.0 (#275), Step 3: 70.4 (#164)
| Benchmark | Llama 3.2 3B | Step 3 |
|---|---|---|
| LMArena Instruction Following | 1089 | 1332 |
Long Context Step 3 leads
Llama 3.2 3B: 33.4 (#261), Step 3: 40.3 (#157)
| Benchmark | Llama 3.2 3B | Step 3 |
|---|---|---|
| LMArena Longer Query | 1100 | 1326 |
Writing & Preference Step 3 leads
Llama 3.2 3B: 24.7 (#307), Step 3: 54.3 (#151)
| Benchmark | Llama 3.2 3B | Step 3 |
|---|---|---|
| LMArena Text | 1110 | 1350 |
| LMArena Creative Writing | 1094 | 1321 |
| LMArena Multi-Turn | 1105 | 1341 |
| EQ-Bench Creative Writing | 595 | — |
Frequently asked questions
Is Llama 3.2 3B better than Step 3?
Step 3 is the stronger model overall, scoring 40.5 to 28.9 on the Noometry Index.
Is Llama 3.2 3B or Step 3 better for coding?
Step 3 scores higher on coding benchmarks: 40.1 versus 27.6 in the Noometry coding category.
How many benchmarks do Llama 3.2 3B and Step 3 share?
13 benchmarks have published results for both models. Llama 3.2 3B has 18 scored results on Noometry and Step 3 has 17.