Model comparison
Llama 2-70B vs Palm 2
Palm 2 is the stronger model overall, scoring 30.0 to 24.4 on the Noometry Index.
Last verified . 10 shared benchmarks.
Meta
GoogleSummary
- They share 10 benchmarks with published results for both. Llama 2-70B scores higher in 5 categories and Palm 2 in 2 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in math, where Palm 2 leads 30.8 to 8.1.
- Llama 2-70B has downloadable open weights; the other is API-only.
Side by side
| Llama 2-70B | Palm 2 | |
|---|---|---|
| Provider | Meta | |
| Noometry Index | 24.4 | 30.0 |
| Released | 2023-07-18 | — |
| Weights | Open | Proprietary |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 35 | 10 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Llama 2-70B leads
Llama 2-70B: 31.4 (#286), Palm 2: 29.0 (#311)
| Benchmark | Llama 2-70B | Palm 2 |
|---|---|---|
| LMArena Coding | 1079 | 994 |
Reasoning Palm 2 leads
Llama 2-70B: 14.4 (#325), Palm 2: 19.1 (#271)
| Benchmark | Llama 2-70B | Palm 2 |
|---|---|---|
| LMArena Hard Prompts | 1073 | 1005 |
| DTBench | 41.6% | — |
| BIG-Bench Hard | 64.9% | — |
| CommonsenseQA 2.0 | 50% | — |
| Epoch Capabilities Index | 113.79 | — |
| ForecastBench | 51.4 | — |
| HellaSwag | 85.3% | — |
| LAMBADA | 78.9% | — |
| PIQA | 82.8% | — |
| WinoGrande | 80.2% | — |
Math Palm 2 leads
Llama 2-70B: 8.1 (#326), Palm 2: 30.8 (#231)
| Benchmark | Llama 2-70B | Palm 2 |
|---|---|---|
| LMArena Math | 1091 | 1049 |
| OTIS Mock AIME 2024-2025 | 0% | — |
| MATH Level 5 | 3.3% | — |
| GSM8K | 69.6% | — |
Knowledge Not comparable
Llama 2-70B: 7.4 (#310), Palm 2: —
| Benchmark | Llama 2-70B | Palm 2 |
|---|---|---|
| GPQA Diamond | 26.3% | — |
| LMArena Expert | 1039 | — |
| ARC (AI2) Challenge | 78.3% | — |
| BoolQ | 88.6% | — |
| MMLU | 69.9% | — |
| OpenBookQA | 60.2% | — |
| TriviaQA | 87.6% | — |
Multilingual Llama 2-70B leads
Llama 2-70B: 27.7 (#274), Palm 2: 20.9 (#295)
| Benchmark | Llama 2-70B | Palm 2 |
|---|---|---|
| LMArena Non-English | 1045 | 916 |
| LMArena Chinese | 995 | 887 |
| LMArena French | 1090 | — |
| LMArena German | 1041 | — |
| LMArena Japanese | 927 | — |
| LMArena Korean | 964 | — |
| LMArena Russian | 1083 | — |
| LMArena Spanish | 1143 | — |
Instruction Following Llama 2-70B leads
Llama 2-70B: 54.9 (#278), Palm 2: 51.0 (#296)
| Benchmark | Llama 2-70B | Palm 2 |
|---|---|---|
| LMArena Instruction Following | 1071 | 1010 |
Long Context Llama 2-70B leads
Llama 2-70B: 32.3 (#270), Palm 2: 30.8 (#285)
| Benchmark | Llama 2-70B | Palm 2 |
|---|---|---|
| LMArena Longer Query | 1062 | 1010 |
Writing & Preference Llama 2-70B leads
Llama 2-70B: 32.3 (#279), Palm 2: 25.6 (#304)
| Benchmark | Llama 2-70B | Palm 2 |
|---|---|---|
| LMArena Text | 1115 | 1027 |
| LMArena Creative Writing | 1075 | 991 |
| LMArena Multi-Turn | 1088 | 994 |
Frequently asked questions
Is Llama 2-70B better than Palm 2?
Palm 2 is the stronger model overall, scoring 30.0 to 24.4 on the Noometry Index.
Is Llama 2-70B or Palm 2 better for coding?
Llama 2-70B scores higher on coding benchmarks: 31.4 versus 29.0 in the Noometry coding category.
How many benchmarks do Llama 2-70B and Palm 2 share?
10 benchmarks have published results for both models. Llama 2-70B has 35 scored results on Noometry and Palm 2 has 10.