Model comparison
Llama 2-7B vs Llama2 70b Steerlm Chat
Llama2 70b Steerlm Chat is the stronger model overall, scoring 31.2 to 28.6 on the Noometry Index.
Last verified . 9 shared benchmarks.
Meta
NVIDIASummary
- They share 9 benchmarks with published results for both. Llama 2-7B scores higher in 1 category and Llama2 70b Steerlm Chat in 6 categories; 4 gaps are clear of the uncertainty.
- The widest gap is in multilingual, where Llama2 70b Steerlm Chat leads 28.9 to 23.9.
Side by side
| Llama 2-7B | Llama2 70b Steerlm Chat | |
|---|---|---|
| Provider | Meta | NVIDIA |
| Noometry Index | 28.6 | 31.2 |
| Released | 2023-07-18 | — |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 29 | 9 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
Llama 2-7B: 28.7 (#302), Llama2 70b Steerlm Chat: 29.3 (#295)
| Benchmark | Llama 2-7B | Llama2 70b Steerlm Chat |
|---|---|---|
| LMArena Coding | 1002 | 1025 |
Reasoning Llama2 70b Steerlm Chat leads
Llama 2-7B: 15.1 (#309), Llama2 70b Steerlm Chat: 19.1 (#245)
| Benchmark | Llama 2-7B | Llama2 70b Steerlm Chat |
|---|---|---|
| LMArena Hard Prompts | 1009 | 1047 |
| Chess Puzzles | 0% | — |
| BIG-Bench Hard | 39.2% | — |
| Epoch Capabilities Index | 98.54 | — |
| HellaSwag | 77.2% | — |
| LAMBADA | 73.3% | — |
| PIQA | 78.8% | — |
| WinoGrande | 69.2% | — |
Math Too close to call
Llama 2-7B: 28.2 (#231), Llama2 70b Steerlm Chat: 28.8 (#223)
| Benchmark | Llama 2-7B | Llama2 70b Steerlm Chat |
|---|---|---|
| LMArena Math | 1042 | 1072 |
| GSM8K | 16.7% | — |
Knowledge Not comparable
Llama 2-7B: 27.7 (#243), Llama2 70b Steerlm Chat: —
| Benchmark | Llama 2-7B | Llama2 70b Steerlm Chat |
|---|---|---|
| LMArena Expert | 1036 | — |
| ARC (AI2) Challenge | 45.9% | — |
| BoolQ | 77.9% | — |
| MMLU | 45.8% | — |
| OpenBookQA | 58.6% | — |
| TriviaQA | 73.7% | — |
Multimodal Not comparable
Llama 2-7B: —, Llama2 70b Steerlm Chat: —
| Benchmark | Llama 2-7B | Llama2 70b Steerlm Chat |
|---|---|---|
| ScienceQA | 43.1% | — |
Multilingual Llama2 70b Steerlm Chat leads
Llama 2-7B: 23.9 (#288), Llama2 70b Steerlm Chat: 28.9 (#265)
| Benchmark | Llama 2-7B | Llama2 70b Steerlm Chat |
|---|---|---|
| LMArena Non-English | 973 | 1064 |
| LMArena Chinese | 973 | — |
| LMArena French | 969 | — |
| LMArena German | 978 | — |
| LMArena Russian | 995 | — |
| LMArena Spanish | 1007 | — |
Instruction Following Llama2 70b Steerlm Chat leads
Llama 2-7B: 51.0 (#293), Llama2 70b Steerlm Chat: 54.5 (#274)
| Benchmark | Llama 2-7B | Llama2 70b Steerlm Chat |
|---|---|---|
| LMArena Instruction Following | 1006 | 1061 |
Long Context Too close to call
Llama 2-7B: 30.4 (#282), Llama2 70b Steerlm Chat: 30.4 (#283)
| Benchmark | Llama 2-7B | Llama2 70b Steerlm Chat |
|---|---|---|
| LMArena Longer Query | 999 | 998 |
Writing & Preference Llama2 70b Steerlm Chat leads
Llama 2-7B: 28.1 (#293), Llama2 70b Steerlm Chat: 31.8 (#278)
| Benchmark | Llama 2-7B | Llama2 70b Steerlm Chat |
|---|---|---|
| LMArena Text | 1053 | 1098 |
| LMArena Creative Writing | 1033 | 1091 |
| LMArena Multi-Turn | 1029 | 1058 |
Frequently asked questions
Is Llama 2-7B better than Llama2 70b Steerlm Chat?
Llama2 70b Steerlm Chat is the stronger model overall, scoring 31.2 to 28.6 on the Noometry Index.
Is Llama 2-7B or Llama2 70b Steerlm Chat better for coding?
They score almost the same on coding (28.7 vs 29.3); test both on your own repository before choosing.
How many benchmarks do Llama 2-7B and Llama2 70b Steerlm Chat share?
9 benchmarks have published results for both models. Llama 2-7B has 29 scored results on Noometry and Llama2 70b Steerlm Chat has 9.