Model comparison
Llama 2-70B vs Step 2 16k Exp 202412
Step 2 16k Exp 202412 is the stronger model overall, scoring 38.6 to 24.1 on the Noometry Index.
Last verified . 12 shared benchmarks.
Meta
StepFunSummary
- They share 12 benchmarks with published results for both. Llama 2-70B 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 knowledge, where Step 2 16k Exp 202412 leads 34.6 to 7.4.
- Llama 2-70B has downloadable open weights; the other is API-only.
Side by side
| Llama 2-70B | Step 2 16k Exp 202412 | |
|---|---|---|
| Provider | Meta | StepFun |
| Noometry Index | 24.1 | 38.6 |
| Released | 2023-07-18 | — |
| Weights | Open | Proprietary |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 35 | 12 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Step 2 16k Exp 202412 leads
Llama 2-70B: 30.8 (#281), Step 2 16k Exp 202412: 37.9 (#170)
| Benchmark | Llama 2-70B | Step 2 16k Exp 202412 |
|---|---|---|
| LMArena Coding | 1079 | 1316 |
Reasoning Step 2 16k Exp 202412 leads
Llama 2-70B: 13.7 (#324), Step 2 16k Exp 202412: 24.8 (#140)
| Benchmark | Llama 2-70B | Step 2 16k Exp 202412 |
|---|---|---|
| LMArena Hard Prompts | 1073 | 1299 |
| DTBench | 41.6% | — |
| BIG-Bench Hard | 64.9% | — |
| CommonsenseQA 2.0 | 50% | — |
| Epoch Capabilities Index | 113.59 | — |
| ForecastBench | 51.4 | — |
| HellaSwag | 85.3% | — |
| LAMBADA | 78.9% | — |
| PIQA | 82.8% | — |
| WinoGrande | 80.2% | — |
Math Step 2 16k Exp 202412 leads
Llama 2-70B: 7.5 (#320), Step 2 16k Exp 202412: 33.6 (#171)
| Benchmark | Llama 2-70B | Step 2 16k Exp 202412 |
|---|---|---|
| LMArena Math | 1091 | 1305 |
| OTIS Mock AIME 2024-2025 | 0% | — |
| MATH Level 5 | 3.3% | — |
| GSM8K | 69.6% | — |
Knowledge Step 2 16k Exp 202412 leads
Llama 2-70B: 7.4 (#305), Step 2 16k Exp 202412: 34.6 (#187)
| Benchmark | Llama 2-70B | Step 2 16k Exp 202412 |
|---|---|---|
| LMArena Expert | 1039 | 1279 |
| GPQA Diamond | 26.3% | — |
| ARC (AI2) Challenge | 78.3% | — |
| BoolQ | 88.6% | — |
| MMLU | 69.9% | — |
| OpenBookQA | 60.2% | — |
| TriviaQA | 87.6% | — |
Multilingual Step 2 16k Exp 202412 leads
Llama 2-70B: 27.9 (#269), Step 2 16k Exp 202412: 43.9 (#176)
| Benchmark | Llama 2-70B | Step 2 16k Exp 202412 |
|---|---|---|
| LMArena Non-English | 1045 | 1290 |
| LMArena Chinese | 994 | 1331 |
| LMArena Russian | 1083 | 1324 |
| LMArena French | 1089 | — |
| LMArena German | 1041 | — |
| LMArena Japanese | 927 | — |
| LMArena Korean | 964 | — |
| LMArena Spanish | 1142 | — |
Instruction Following Step 2 16k Exp 202412 leads
Llama 2-70B: 55.1 (#273), Step 2 16k Exp 202412: 68.1 (#187)
| Benchmark | Llama 2-70B | Step 2 16k Exp 202412 |
|---|---|---|
| LMArena Instruction Following | 1071 | 1287 |
Long Context Step 2 16k Exp 202412 leads
Llama 2-70B: 32.2 (#265), Step 2 16k Exp 202412: 39.7 (#165)
| Benchmark | Llama 2-70B | Step 2 16k Exp 202412 |
|---|---|---|
| LMArena Longer Query | 1062 | 1307 |
Writing & Preference Step 2 16k Exp 202412 leads
Llama 2-70B: 32.5 (#274), Step 2 16k Exp 202412: 52.5 (#168)
| Benchmark | Llama 2-70B | Step 2 16k Exp 202412 |
|---|---|---|
| LMArena Text | 1115 | 1321 |
| LMArena Creative Writing | 1075 | 1328 |
| LMArena Multi-Turn | 1088 | 1292 |
Frequently asked questions
Is Llama 2-70B better than Step 2 16k Exp 202412?
Step 2 16k Exp 202412 is the stronger model overall, scoring 38.6 to 24.1 on the Noometry Index.
Is Llama 2-70B or Step 2 16k Exp 202412 better for coding?
Step 2 16k Exp 202412 scores higher on coding benchmarks: 37.9 versus 30.8 in the Noometry coding category.
How many benchmarks do Llama 2-70B and Step 2 16k Exp 202412 share?
12 benchmarks have published results for both models. Llama 2-70B has 35 scored results on Noometry and Step 2 16k Exp 202412 has 12.