Model comparison
Llama 3.2 3B vs Step 2 16k Exp 202412
Step 2 16k Exp 202412 is the stronger model overall, scoring 39.2 to 28.9 on the Noometry Index.
Last verified . 12 shared benchmarks.
Meta
StepFunSummary
- They share 12 benchmarks with published results for both. Llama 3.2 3B scores higher in 0 categories and Step 2 16k Exp 202412 in 8 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Step 2 16k Exp 202412 leads 52.3 to 24.7.
- Llama 3.2 3B has downloadable open weights; the other is API-only.
Side by side
| Llama 3.2 3B | Step 2 16k Exp 202412 | |
|---|---|---|
| Provider | Meta | StepFun |
| Noometry Index | 28.9 | 39.2 |
| Released | 2024-09-24 | — |
| Weights | Open | Proprietary |
| Context window | 131K | — |
| Max output | 118K | — |
| Input $ / M tokens | $0.05 | — |
| Output $ / M tokens | $0.33 | — |
| Results tracked | 18 | 12 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Step 2 16k Exp 202412 leads
Llama 3.2 3B: 27.6 (#319), Step 2 16k Exp 202412: 38.5 (#174)
| Benchmark | Llama 3.2 3B | Step 2 16k Exp 202412 |
|---|---|---|
| LMArena Coding | 1098 | 1316 |
| BigCodeBench Instruct | 23.4% | — |
| BigCodeBench Complete | 28.3% | — |
Agentic & Tool Use Not comparable
Llama 3.2 3B: 20.1 (#143), Step 2 16k Exp 202412: —
| Benchmark | Llama 3.2 3B | Step 2 16k Exp 202412 |
|---|---|---|
| Berkeley Function Calling Leaderboard | 21.9% | — |
| BALROG | 10.1% | — |
Reasoning Step 2 16k Exp 202412 leads
Llama 3.2 3B: 21.0 (#228), Step 2 16k Exp 202412: 25.9 (#142)
| Benchmark | Llama 3.2 3B | Step 2 16k Exp 202412 |
|---|---|---|
| LMArena Hard Prompts | 1095 | 1299 |
Math Step 2 16k Exp 202412 leads
Llama 3.2 3B: 32.4 (#214), Step 2 16k Exp 202412: 36.3 (#169)
| Benchmark | Llama 3.2 3B | Step 2 16k Exp 202412 |
|---|---|---|
| LMArena Math | 1126 | 1304 |
Knowledge Step 2 16k Exp 202412 leads
Llama 3.2 3B: 29.7 (#235), Step 2 16k Exp 202412: 35.2 (#187)
| Benchmark | Llama 3.2 3B | Step 2 16k Exp 202412 |
|---|---|---|
| LMArena Expert | 1090 | 1279 |
Multilingual Step 2 16k Exp 202412 leads
Llama 3.2 3B: 26.2 (#281), Step 2 16k Exp 202412: 43.7 (#181)
| Benchmark | Llama 3.2 3B | Step 2 16k Exp 202412 |
|---|---|---|
| LMArena Non-English | 1019 | 1290 |
| LMArena Chinese | 1017 | 1331 |
| LMArena Russian | 949 | 1324 |
| LMArena German | 1056 | — |
Instruction Following Step 2 16k Exp 202412 leads
Llama 3.2 3B: 56.0 (#275), Step 2 16k Exp 202412: 67.9 (#192)
| Benchmark | Llama 3.2 3B | Step 2 16k Exp 202412 |
|---|---|---|
| LMArena Instruction Following | 1089 | 1287 |
Long Context Step 2 16k Exp 202412 leads
Llama 3.2 3B: 33.4 (#261), Step 2 16k Exp 202412: 39.7 (#170)
| Benchmark | Llama 3.2 3B | Step 2 16k Exp 202412 |
|---|---|---|
| LMArena Longer Query | 1100 | 1307 |
Writing & Preference Step 2 16k Exp 202412 leads
Llama 3.2 3B: 24.7 (#307), Step 2 16k Exp 202412: 52.3 (#173)
| Benchmark | Llama 3.2 3B | Step 2 16k Exp 202412 |
|---|---|---|
| LMArena Text | 1110 | 1321 |
| LMArena Creative Writing | 1094 | 1328 |
| LMArena Multi-Turn | 1105 | 1292 |
| EQ-Bench Creative Writing | 595 | — |
Frequently asked questions
Is Llama 3.2 3B better than Step 2 16k Exp 202412?
Step 2 16k Exp 202412 is the stronger model overall, scoring 39.2 to 28.9 on the Noometry Index.
Is Llama 3.2 3B or Step 2 16k Exp 202412 better for coding?
Step 2 16k Exp 202412 scores higher on coding benchmarks: 38.5 versus 27.6 in the Noometry coding category.
How many benchmarks do Llama 3.2 3B and Step 2 16k Exp 202412 share?
12 benchmarks have published results for both models. Llama 3.2 3B has 18 scored results on Noometry and Step 2 16k Exp 202412 has 12.