Model comparison
Llama 13b vs Palm 2
Palm 2 is the stronger model overall, scoring 30.0 to 24.4 on the Noometry Index.
Last verified . 8 shared benchmarks.
Meta
GoogleSummary
- They share 8 benchmarks with published results for both. Llama 13b scores higher in 0 categories and Palm 2 in 6 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in instruction following, where Palm 2 leads 51.0 to 36.7.
- Llama 13b has downloadable open weights; the other is API-only.
Side by side
| Llama 13b | Palm 2 | |
|---|---|---|
| Provider | Meta | |
| Noometry Index | 24.4 | 30.0 |
| Released | 2023-02-24 | — |
| Weights | Open | Proprietary |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 21 | 10 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Palm 2 leads
Llama 13b: 21.4 (#337), Palm 2: 29.0 (#311)
| Benchmark | Llama 13b | Palm 2 |
|---|---|---|
| LMArena Coding | 683 | 994 |
Reasoning Palm 2 leads
Llama 13b: 14.0 (#329), Palm 2: 19.1 (#271)
| Benchmark | Llama 13b | Palm 2 |
|---|---|---|
| LMArena Hard Prompts | 728 | 1005 |
| BIG-Bench Hard | 37.9% | — |
| Epoch Capabilities Index | 100.58 | — |
| HellaSwag | 79.2% | — |
| LAMBADA | 75.2% | — |
| PIQA | 80.1% | — |
| WinoGrande | 73% | — |
Math Palm 2 leads
Llama 13b: 26.7 (#256), Palm 2: 30.8 (#231)
| Benchmark | Llama 13b | Palm 2 |
|---|---|---|
| LMArena Math | 838 | 1049 |
| GSM8K | 20.6% | — |
Knowledge Not comparable
Llama 13b: —, Palm 2: —
| Benchmark | Llama 13b | Palm 2 |
|---|---|---|
| ARC (AI2) Challenge | 52.7% | — |
| BoolQ | 78.7% | — |
| MMLU | 47.7% | — |
| OpenBookQA | 56.4% | — |
| TriviaQA | 77.9% | — |
Multimodal Not comparable
Llama 13b: —, Palm 2: —
| Benchmark | Llama 13b | Palm 2 |
|---|---|---|
| ScienceQA | 43.3% | — |
Multilingual Palm 2 leads
Llama 13b: 16.6 (#297), Palm 2: 20.9 (#295)
| Benchmark | Llama 13b | Palm 2 |
|---|---|---|
| LMArena Non-English | 819 | 916 |
| LMArena Chinese | — | 887 |
Instruction Following Palm 2 leads
Llama 13b: 36.7 (#305), Palm 2: 51.0 (#296)
| Benchmark | Llama 13b | Palm 2 |
|---|---|---|
| LMArena Instruction Following | 781 | 1010 |
Long Context Not comparable
Llama 13b: —, Palm 2: 30.8 (#285)
| Benchmark | Llama 13b | Palm 2 |
|---|---|---|
| LMArena Longer Query | — | 1010 |
Writing & Preference Palm 2 leads
Llama 13b: 13.8 (#312), Palm 2: 25.6 (#304)
| Benchmark | Llama 13b | Palm 2 |
|---|---|---|
| LMArena Text | 834 | 1027 |
| LMArena Creative Writing | 794 | 991 |
| LMArena Multi-Turn | 753 | 994 |
Frequently asked questions
Is Llama 13b better than Palm 2?
Palm 2 is the stronger model overall, scoring 30.0 to 24.4 on the Noometry Index.
Is Llama 13b or Palm 2 better for coding?
Palm 2 scores higher on coding benchmarks: 29.0 versus 21.4 in the Noometry coding category.
How many benchmarks do Llama 13b and Palm 2 share?
8 benchmarks have published results for both models. Llama 13b has 21 scored results on Noometry and Palm 2 has 10.