Model comparison
Llama 2-13B vs Step 2 16k Exp 202412
Step 2 16k Exp 202412 is the stronger model overall, scoring 38.6 to 29.1 on the Noometry Index.
Last verified . 12 shared benchmarks.
Meta
StepFunSummary
- They share 12 benchmarks with published results for both. Llama 2-13B 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 52.5 to 30.0.
- Llama 2-13B has downloadable open weights; the other is API-only.
Side by side
| Llama 2-13B | Step 2 16k Exp 202412 | |
|---|---|---|
| Provider | Meta | StepFun |
| Noometry Index | 29.1 | 38.6 |
| Released | 2023-07-18 | — |
| Weights | Open | Proprietary |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 32 | 12 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Step 2 16k Exp 202412 leads
Llama 2-13B: 30.4 (#287), Step 2 16k Exp 202412: 37.9 (#170)
| Benchmark | Llama 2-13B | Step 2 16k Exp 202412 |
|---|---|---|
| LMArena Coding | 1062 | 1316 |
Reasoning Step 2 16k Exp 202412 leads
Llama 2-13B: 12.3 (#333), Step 2 16k Exp 202412: 24.8 (#140)
| Benchmark | Llama 2-13B | Step 2 16k Exp 202412 |
|---|---|---|
| LMArena Hard Prompts | 1051 | 1299 |
| Chess Puzzles | 0% | — |
| DTBench | 42.2% | — |
| BIG-Bench Hard | 58.2% | — |
| Epoch Capabilities Index | 105.8 | — |
| HellaSwag | 80.7% | — |
| LAMBADA | 76.5% | — |
| PIQA | 80.8% | — |
| WinoGrande | 72.8% | — |
Math Step 2 16k Exp 202412 leads
Llama 2-13B: 28.7 (#226), Step 2 16k Exp 202412: 33.6 (#171)
| Benchmark | Llama 2-13B | Step 2 16k Exp 202412 |
|---|---|---|
| LMArena Math | 1065 | 1305 |
| GSM8K | 36.9% | — |
Knowledge Step 2 16k Exp 202412 leads
Llama 2-13B: 27.5 (#244), Step 2 16k Exp 202412: 34.6 (#187)
| Benchmark | Llama 2-13B | Step 2 16k Exp 202412 |
|---|---|---|
| LMArena Expert | 1030 | 1279 |
| ARC (AI2) Challenge | 60.3% | — |
| BoolQ | 82.4% | — |
| MMLU | 55.6% | — |
| OpenBookQA | 57% | — |
| TriviaQA | 79.6% | — |
Multimodal Not comparable
Llama 2-13B: —, Step 2 16k Exp 202412: —
| Benchmark | Llama 2-13B | Step 2 16k Exp 202412 |
|---|---|---|
| ScienceQA | 55.8% | — |
Multilingual Step 2 16k Exp 202412 leads
Llama 2-13B: 26.7 (#274), Step 2 16k Exp 202412: 43.9 (#176)
| Benchmark | Llama 2-13B | Step 2 16k Exp 202412 |
|---|---|---|
| LMArena Non-English | 1024 | 1290 |
| LMArena Chinese | 1001 | 1331 |
| LMArena Russian | 1055 | 1324 |
| LMArena French | 1043 | — |
| LMArena German | 1009 | — |
| LMArena Japanese | 894 | — |
| LMArena Korean | 953 | — |
| LMArena Spanish | 1086 | — |
Instruction Following Step 2 16k Exp 202412 leads
Llama 2-13B: 53.5 (#282), Step 2 16k Exp 202412: 68.1 (#187)
| Benchmark | Llama 2-13B | Step 2 16k Exp 202412 |
|---|---|---|
| LMArena Instruction Following | 1046 | 1287 |
Long Context Step 2 16k Exp 202412 leads
Llama 2-13B: 32.3 (#264), Step 2 16k Exp 202412: 39.7 (#165)
| Benchmark | Llama 2-13B | Step 2 16k Exp 202412 |
|---|---|---|
| LMArena Longer Query | 1064 | 1307 |
Writing & Preference Step 2 16k Exp 202412 leads
Llama 2-13B: 30.0 (#284), Step 2 16k Exp 202412: 52.5 (#168)
| Benchmark | Llama 2-13B | Step 2 16k Exp 202412 |
|---|---|---|
| LMArena Text | 1085 | 1321 |
| LMArena Creative Writing | 1047 | 1328 |
| LMArena Multi-Turn | 1050 | 1292 |
Frequently asked questions
Is Llama 2-13B better than Step 2 16k Exp 202412?
Step 2 16k Exp 202412 is the stronger model overall, scoring 38.6 to 29.1 on the Noometry Index.
Is Llama 2-13B or Step 2 16k Exp 202412 better for coding?
Step 2 16k Exp 202412 scores higher on coding benchmarks: 37.9 versus 30.4 in the Noometry coding category.
How many benchmarks do Llama 2-13B and Step 2 16k Exp 202412 share?
12 benchmarks have published results for both models. Llama 2-13B has 32 scored results on Noometry and Step 2 16k Exp 202412 has 12.