Model comparison
Llama 2-7B vs Palm 2
Llama 2-7B and Palm 2 score almost the same on the Noometry Index (29.1 vs 30.0), so choose on price, context window or the category you care about most.
Last verified . 10 shared benchmarks.
Meta
GoogleSummary
- They share 10 benchmarks with published results for both. Llama 2-7B scores higher in 3 categories and Palm 2 in 4 categories; 3 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Palm 2 leads 19.1 to 15.7.
- Llama 2-7B has downloadable open weights; the other is API-only.
Side by side
| Llama 2-7B | Palm 2 | |
|---|---|---|
| Provider | Meta | |
| Noometry Index | 29.1 | 30.0 |
| Released | 2023-07-18 | — |
| Weights | Open | Proprietary |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 29 | 10 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
Llama 2-7B: 29.2 (#307), Palm 2: 29.0 (#311)
| Benchmark | Llama 2-7B | Palm 2 |
|---|---|---|
| LMArena Coding | 1002 | 994 |
Reasoning Palm 2 leads
Llama 2-7B: 15.7 (#312), Palm 2: 19.1 (#271)
| Benchmark | Llama 2-7B | Palm 2 |
|---|---|---|
| LMArena Hard Prompts | 1009 | 1005 |
| Chess Puzzles | 0% | — |
| BIG-Bench Hard | 39.2% | — |
| Epoch Capabilities Index | 99.06 | — |
| HellaSwag | 77.2% | — |
| LAMBADA | 73.3% | — |
| PIQA | 78.8% | — |
| WinoGrande | 69.2% | — |
Math Too close to call
Llama 2-7B: 30.7 (#233), Palm 2: 30.8 (#231)
| Benchmark | Llama 2-7B | Palm 2 |
|---|---|---|
| LMArena Math | 1042 | 1049 |
| GSM8K | 16.7% | — |
Knowledge Not comparable
Llama 2-7B: 28.2 (#248), Palm 2: —
| Benchmark | Llama 2-7B | Palm 2 |
|---|---|---|
| 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: —, Palm 2: —
| Benchmark | Llama 2-7B | Palm 2 |
|---|---|---|
| ScienceQA | 43.1% | — |
Multilingual Llama 2-7B leads
Llama 2-7B: 23.8 (#293), Palm 2: 20.9 (#295)
| Benchmark | Llama 2-7B | Palm 2 |
|---|---|---|
| LMArena Non-English | 973 | 916 |
| LMArena Chinese | 973 | 887 |
| LMArena French | 970 | — |
| LMArena German | 978 | — |
| LMArena Russian | 995 | — |
| LMArena Spanish | 1007 | — |
Instruction Following Too close to call
Llama 2-7B: 50.8 (#298), Palm 2: 51.0 (#296)
| Benchmark | Llama 2-7B | Palm 2 |
|---|---|---|
| LMArena Instruction Following | 1006 | 1010 |
Long Context Too close to call
Llama 2-7B: 30.4 (#287), Palm 2: 30.8 (#285)
| Benchmark | Llama 2-7B | Palm 2 |
|---|---|---|
| LMArena Longer Query | 999 | 1010 |
Writing & Preference Llama 2-7B leads
Llama 2-7B: 28.0 (#298), Palm 2: 25.6 (#304)
| Benchmark | Llama 2-7B | Palm 2 |
|---|---|---|
| LMArena Text | 1053 | 1027 |
| LMArena Creative Writing | 1033 | 991 |
| LMArena Multi-Turn | 1029 | 994 |
Frequently asked questions
Is Llama 2-7B better than Palm 2?
Llama 2-7B and Palm 2 score almost the same on the Noometry Index (29.1 vs 30.0), so choose on price, context window or the category you care about most.
Is Llama 2-7B or Palm 2 better for coding?
They score almost the same on coding (29.2 vs 29.0); test both on your own repository before choosing.
How many benchmarks do Llama 2-7B and Palm 2 share?
10 benchmarks have published results for both models. Llama 2-7B has 29 scored results on Noometry and Palm 2 has 10.