Model comparison
Llama 3-8B vs Palm 2
Palm 2 is the stronger model overall, scoring 29.4 to 25.3 on the Noometry Index.
Last verified . 10 shared benchmarks.
Meta
GoogleSummary
- They share 10 benchmarks with published results for both. Llama 3-8B 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 28.4 to 8.3.
- Llama 3-8B has downloadable open weights; the other is API-only.
Side by side
| Llama 3-8B | Palm 2 | |
|---|---|---|
| Provider | Meta | |
| Noometry Index | 25.3 | 29.4 |
| Released | 2024-04-18 | — |
| Weights | Open | Proprietary |
| Context window | 8K | — |
| Max output | 8K | — |
| Input $ / M tokens | $0.14 | — |
| Output $ / M tokens | $0.14 | — |
| Results tracked | 34 | 10 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Llama 3-8B leads
Llama 3-8B: 30.5 (#285), Palm 2: 28.5 (#306)
| Benchmark | Llama 3-8B | Palm 2 |
|---|---|---|
| LMArena Coding | 1152 | 995 |
| BigCodeBench Instruct | 31.9% | — |
| BigCodeBench Complete | 36.9% | — |
| HumanEval+ | 56.7% | — |
| MBPP+ | 54.8% | — |
Reasoning Palm 2 leads
Llama 3-8B: 13.8 (#321), Palm 2: 18.2 (#270)
| Benchmark | Llama 3-8B | Palm 2 |
|---|---|---|
| LMArena Hard Prompts | 1133 | 1005 |
| Chess Puzzles | 0% | — |
| DTBench | 43.9% | — |
| Adversarial NLI | 57.3% | — |
| Epoch Capabilities Index | 116.33 | — |
| ForecastBench | 58.6 | — |
| WinoGrande | 75.7% | — |
Math Palm 2 leads
Llama 3-8B: 8.3 (#317), Palm 2: 28.4 (#229)
| Benchmark | Llama 3-8B | Palm 2 |
|---|---|---|
| LMArena Math | 1151 | 1049 |
| OTIS Mock AIME 2024-2025 | 1.9% | — |
| MATH Level 5 | 6.1% | — |
Knowledge Not comparable
Llama 3-8B: 7.8 (#303), Palm 2: —
| Benchmark | Llama 3-8B | Palm 2 |
|---|---|---|
| GPQA Diamond | 26.1% | — |
| LMArena Expert | 1113 | — |
| ARC (AI2) Challenge | 82.8% | — |
| MMLU | 68.8% | — |
| OpenBookQA | 82.6% | — |
| TriviaQA | 67.7% | — |
Multilingual Llama 3-8B leads
Llama 3-8B: 31.0 (#256), Palm 2: 21.1 (#290)
| Benchmark | Llama 3-8B | Palm 2 |
|---|---|---|
| LMArena Non-English | 1098 | 916 |
| LMArena Chinese | 1076 | 887 |
| LMArena French | 1158 | — |
| LMArena German | 1104 | — |
| LMArena Japanese | 967 | — |
| LMArena Korean | 1003 | — |
| LMArena Russian | 1109 | — |
| LMArena Spanish | 1172 | — |
Instruction Following Llama 3-8B leads
Llama 3-8B: 58.7 (#255), Palm 2: 51.3 (#291)
| Benchmark | Llama 3-8B | Palm 2 |
|---|---|---|
| LMArena Instruction Following | 1127 | 1010 |
Long Context Llama 3-8B leads
Llama 3-8B: 34.2 (#246), Palm 2: 30.7 (#280)
| Benchmark | Llama 3-8B | Palm 2 |
|---|---|---|
| LMArena Longer Query | 1128 | 1010 |
Writing & Preference Llama 3-8B leads
Llama 3-8B: 37.7 (#251), Palm 2: 25.7 (#299)
| Benchmark | Llama 3-8B | Palm 2 |
|---|---|---|
| LMArena Text | 1166 | 1027 |
| LMArena Creative Writing | 1150 | 991 |
| LMArena Multi-Turn | 1152 | 994 |
Frequently asked questions
Is Llama 3-8B better than Palm 2?
Palm 2 is the stronger model overall, scoring 29.4 to 25.3 on the Noometry Index.
Is Llama 3-8B or Palm 2 better for coding?
Llama 3-8B scores higher on coding benchmarks: 30.5 versus 28.5 in the Noometry coding category.
How many benchmarks do Llama 3-8B and Palm 2 share?
10 benchmarks have published results for both models. Llama 3-8B has 34 scored results on Noometry and Palm 2 has 10.