Model comparison
Gemma 2B vs Llama2 70b Steerlm Chat
Llama2 70b Steerlm Chat is the stronger model overall, scoring 31.8 to 29.6 on the Noometry Index.
Last verified . 9 shared benchmarks.
Google
NVIDIASummary
- They share 9 benchmarks with published results for both. Gemma 2B scores higher in 0 categories and Llama2 70b Steerlm Chat in 7 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Llama2 70b Steerlm Chat leads 31.6 to 24.0.
Side by side
| Gemma 2B | Llama2 70b Steerlm Chat | |
|---|---|---|
| Provider | NVIDIA | |
| Noometry Index | 29.6 | 31.8 |
| Released | 2024-02-21 | — |
| Weights | Open | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 23 | 9 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
Gemma 2B: 29.4 (#305), Llama2 70b Steerlm Chat: 29.9 (#300)
| Benchmark | Gemma 2B | Llama2 70b Steerlm Chat |
|---|---|---|
| LMArena Coding | 1010 | 1025 |
| HumanEval+ | 20.7% | — |
| MBPP+ | 34.1% | — |
Reasoning Llama2 70b Steerlm Chat leads
Gemma 2B: 18.8 (#275), Llama2 70b Steerlm Chat: 20.0 (#246)
| Benchmark | Gemma 2B | Llama2 70b Steerlm Chat |
|---|---|---|
| LMArena Hard Prompts | 989 | 1047 |
| BIG-Bench Hard | 35.2% | — |
| Epoch Capabilities Index | 94.2 | — |
| HellaSwag | 71.4% | — |
| PIQA | 77.3% | — |
| WinoGrande | 65.4% | — |
Math Llama2 70b Steerlm Chat leads
Gemma 2B: 30.0 (#239), Llama2 70b Steerlm Chat: 31.3 (#226)
| Benchmark | Gemma 2B | Llama2 70b Steerlm Chat |
|---|---|---|
| LMArena Math | 1009 | 1072 |
| GSM8K | 17.7% | — |
Knowledge Not comparable
Gemma 2B: —, Llama2 70b Steerlm Chat: —
| Benchmark | Gemma 2B | Llama2 70b Steerlm Chat |
|---|---|---|
| ARC (AI2) Challenge | 42.1% | — |
| BoolQ | 69.4% | — |
| MMLU | 42.3% | — |
| TriviaQA | 53.2% | — |
Multilingual Llama2 70b Steerlm Chat leads
Gemma 2B: 23.0 (#294), Llama2 70b Steerlm Chat: 28.8 (#270)
| Benchmark | Gemma 2B | Llama2 70b Steerlm Chat |
|---|---|---|
| LMArena Non-English | 958 | 1063 |
| LMArena Chinese | 986 | — |
| LMArena Russian | 937 | — |
Instruction Following Llama2 70b Steerlm Chat leads
Gemma 2B: 48.5 (#302), Llama2 70b Steerlm Chat: 54.2 (#279)
| Benchmark | Gemma 2B | Llama2 70b Steerlm Chat |
|---|---|---|
| LMArena Instruction Following | 970 | 1060 |
Long Context Too close to call
Gemma 2B: 29.9 (#291), Llama2 70b Steerlm Chat: 30.4 (#288)
| Benchmark | Gemma 2B | Llama2 70b Steerlm Chat |
|---|---|---|
| LMArena Longer Query | 981 | 998 |
Writing & Preference Llama2 70b Steerlm Chat leads
Gemma 2B: 24.0 (#308), Llama2 70b Steerlm Chat: 31.6 (#283)
| Benchmark | Gemma 2B | Llama2 70b Steerlm Chat |
|---|---|---|
| LMArena Text | 1002 | 1098 |
| LMArena Creative Writing | 987 | 1091 |
| LMArena Multi-Turn | 945 | 1058 |
Frequently asked questions
Is Gemma 2B better than Llama2 70b Steerlm Chat?
Llama2 70b Steerlm Chat is the stronger model overall, scoring 31.8 to 29.6 on the Noometry Index.
Is Gemma 2B or Llama2 70b Steerlm Chat better for coding?
They score almost the same on coding (29.4 vs 29.9); test both on your own repository before choosing.
How many benchmarks do Gemma 2B and Llama2 70b Steerlm Chat share?
9 benchmarks have published results for both models. Gemma 2B has 23 scored results on Noometry and Llama2 70b Steerlm Chat has 9.