Model comparison
Llama 2-13B vs Llama2 70b Steerlm Chat
Llama2 70b Steerlm Chat is the stronger model overall, scoring 31.2 to 29.1 on the Noometry Index.
Last verified . 9 shared benchmarks.
Meta
NVIDIASummary
- They share 9 benchmarks with published results for both. Llama 2-13B scores higher in 2 categories and Llama2 70b Steerlm Chat in 5 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Llama2 70b Steerlm Chat leads 19.1 to 12.3.
Side by side
| Llama 2-13B | Llama2 70b Steerlm Chat | |
|---|---|---|
| Provider | Meta | NVIDIA |
| Noometry Index | 29.1 | 31.2 |
| Released | 2023-07-18 | — |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 32 | 9 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Llama 2-13B leads
Llama 2-13B: 30.4 (#287), Llama2 70b Steerlm Chat: 29.3 (#295)
| Benchmark | Llama 2-13B | Llama2 70b Steerlm Chat |
|---|---|---|
| LMArena Coding | 1062 | 1025 |
Reasoning Llama2 70b Steerlm Chat leads
Llama 2-13B: 12.3 (#333), Llama2 70b Steerlm Chat: 19.1 (#245)
| Benchmark | Llama 2-13B | Llama2 70b Steerlm Chat |
|---|---|---|
| LMArena Hard Prompts | 1051 | 1047 |
| 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 Too close to call
Llama 2-13B: 28.7 (#226), Llama2 70b Steerlm Chat: 28.8 (#223)
| Benchmark | Llama 2-13B | Llama2 70b Steerlm Chat |
|---|---|---|
| LMArena Math | 1065 | 1072 |
| GSM8K | 36.9% | — |
Knowledge Not comparable
Llama 2-13B: 27.5 (#244), Llama2 70b Steerlm Chat: —
| Benchmark | Llama 2-13B | Llama2 70b Steerlm Chat |
|---|---|---|
| LMArena Expert | 1030 | — |
| ARC (AI2) Challenge | 60.3% | — |
| BoolQ | 82.4% | — |
| MMLU | 55.6% | — |
| OpenBookQA | 57% | — |
| TriviaQA | 79.6% | — |
Multimodal Not comparable
Llama 2-13B: —, Llama2 70b Steerlm Chat: —
| Benchmark | Llama 2-13B | Llama2 70b Steerlm Chat |
|---|---|---|
| ScienceQA | 55.8% | — |
Multilingual Llama2 70b Steerlm Chat leads
Llama 2-13B: 26.7 (#274), Llama2 70b Steerlm Chat: 28.9 (#265)
| Benchmark | Llama 2-13B | Llama2 70b Steerlm Chat |
|---|---|---|
| LMArena Non-English | 1024 | 1064 |
| LMArena Chinese | 1001 | — |
| LMArena French | 1043 | — |
| LMArena German | 1009 | — |
| LMArena Japanese | 894 | — |
| LMArena Korean | 953 | — |
| LMArena Russian | 1055 | — |
| LMArena Spanish | 1086 | — |
Instruction Following Too close to call
Llama 2-13B: 53.5 (#282), Llama2 70b Steerlm Chat: 54.5 (#274)
| Benchmark | Llama 2-13B | Llama2 70b Steerlm Chat |
|---|---|---|
| LMArena Instruction Following | 1046 | 1061 |
Long Context Llama 2-13B leads
Llama 2-13B: 32.3 (#264), Llama2 70b Steerlm Chat: 30.4 (#283)
| Benchmark | Llama 2-13B | Llama2 70b Steerlm Chat |
|---|---|---|
| LMArena Longer Query | 1064 | 998 |
Writing & Preference Llama2 70b Steerlm Chat leads
Llama 2-13B: 30.0 (#284), Llama2 70b Steerlm Chat: 31.8 (#278)
| Benchmark | Llama 2-13B | Llama2 70b Steerlm Chat |
|---|---|---|
| LMArena Text | 1085 | 1098 |
| LMArena Creative Writing | 1047 | 1091 |
| LMArena Multi-Turn | 1050 | 1058 |
Frequently asked questions
Is Llama 2-13B better than Llama2 70b Steerlm Chat?
Llama2 70b Steerlm Chat is the stronger model overall, scoring 31.2 to 29.1 on the Noometry Index.
Is Llama 2-13B or Llama2 70b Steerlm Chat better for coding?
Llama 2-13B scores higher on coding benchmarks: 30.4 versus 29.3 in the Noometry coding category.
How many benchmarks do Llama 2-13B and Llama2 70b Steerlm Chat share?
9 benchmarks have published results for both models. Llama 2-13B has 32 scored results on Noometry and Llama2 70b Steerlm Chat has 9.