Model comparison
Amazon Nova Pro vs Llama 2-70B
Amazon Nova Pro is the stronger model overall, scoring 31.0 to 24.4 on the Noometry Index.
Last verified . 19 shared benchmarks.
MetaSummary
- They share 19 benchmarks with published results for both. Amazon Nova Pro scores higher in 8 categories and Llama 2-70B in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Amazon Nova Pro leads 28.5 to 8.1.
- Llama 2-70B has downloadable open weights; the other is API-only.
Side by side
| Amazon Nova Pro | Llama 2-70B | |
|---|---|---|
| Provider | Amazon | Meta |
| Noometry Index | 31.0 | 24.4 |
| Released | 2024-12-03 | 2023-07-18 |
| Weights | Proprietary | Open |
| Context window | 300K | — |
| Max output | 10K | — |
| Input $ / M tokens | $0.80 | — |
| Output $ / M tokens | $3.20 | — |
| Results tracked | 38 | 35 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Amazon Nova Pro leads
Amazon Nova Pro: 35.1 (#229), Llama 2-70B: 31.4 (#286)
| Benchmark | Amazon Nova Pro | Llama 2-70B |
|---|---|---|
| LMArena Coding | 1270 | 1079 |
| LiveBench Coding | 38.1% | — |
Agentic & Tool Use Not comparable
Amazon Nova Pro: 16.7 (#147), Llama 2-70B: —
| Benchmark | Amazon Nova Pro | Llama 2-70B |
|---|---|---|
| Berkeley Function Calling Leaderboard | 25% | — |
| TheAgentCompany | 1.7% | — |
Reasoning Amazon Nova Pro leads
Amazon Nova Pro: 20.0 (#243), Llama 2-70B: 14.4 (#325)
| Benchmark | Amazon Nova Pro | Llama 2-70B |
|---|---|---|
| LMArena Hard Prompts | 1246 | 1073 |
| Epoch Capabilities Index | 123.8 | 113.79 |
| LiveBench Reasoning | 32.6% | — |
| DTBench | — | 41.6% |
| LiveBench Data Analysis | 48.3% | — |
| BIG-Bench Hard | — | 64.9% |
| CommonsenseQA 2.0 | — | 50% |
| ForecastBench | — | 51.4 |
| HellaSwag | — | 85.3% |
| LAMBADA | — | 78.9% |
| LiveBench | 43.5% | — |
| PIQA | — | 82.8% |
| WinoGrande | — | 80.2% |
Math Amazon Nova Pro leads
Amazon Nova Pro: 28.5 (#243), Llama 2-70B: 8.1 (#326)
| Benchmark | Amazon Nova Pro | Llama 2-70B |
|---|---|---|
| LMArena Math | 1252 | 1091 |
| OTIS Mock AIME 2024-2025 | — | 0% |
| Omni-MATH | 24.2% | — |
| LiveBench Math | 38% | — |
| MATH Level 5 | — | 3.3% |
| GSM8K | — | 69.6% |
Knowledge Amazon Nova Pro leads
Amazon Nova Pro: 27.4 (#250), Llama 2-70B: 7.4 (#310)
| Benchmark | Amazon Nova Pro | Llama 2-70B |
|---|---|---|
| LMArena Expert | 1211 | 1039 |
| MMLU | 82% | 69.9% |
| GPQA Diamond | — | 26.3% |
| Humanity's Last Exam | 4.4% | — |
| MMLU-Pro | 67.3% | — |
| Confabulations | 30.1% | — |
| Vectara Hallucination Rate | 5.1% | — |
| GPQA (HELM) | 44.6% | — |
| ARC (AI2) Challenge | — | 78.3% |
| BoolQ | — | 88.6% |
| OpenBookQA | — | 60.2% |
| TriviaQA | — | 87.6% |
Multimodal Not comparable
Amazon Nova Pro: 25.0 (#126), Llama 2-70B: —
| Benchmark | Amazon Nova Pro | Llama 2-70B |
|---|---|---|
| LMArena Vision | 980 | — |
Multilingual Amazon Nova Pro leads
Amazon Nova Pro: 39.7 (#223), Llama 2-70B: 27.7 (#274)
| Benchmark | Amazon Nova Pro | Llama 2-70B |
|---|---|---|
| LMArena Non-English | 1234 | 1045 |
| LMArena Chinese | 1244 | 995 |
| LMArena French | 1271 | 1090 |
| LMArena German | 1243 | 1041 |
| LMArena Japanese | 1200 | 927 |
| LMArena Korean | 1203 | 964 |
| LMArena Russian | 1240 | 1083 |
| LMArena Spanish | 1182 | 1143 |
Instruction Following Amazon Nova Pro leads
Amazon Nova Pro: 64.9 (#226), Llama 2-70B: 54.9 (#278)
| Benchmark | Amazon Nova Pro | Llama 2-70B |
|---|---|---|
| LMArena Instruction Following | 1235 | 1071 |
| LiveBench Instruction Following | 67.1% | — |
| IFEval | 81.5% | — |
Long Context Amazon Nova Pro leads
Amazon Nova Pro: 38.1 (#205), Llama 2-70B: 32.3 (#270)
| Benchmark | Amazon Nova Pro | Llama 2-70B |
|---|---|---|
| LMArena Longer Query | 1255 | 1062 |
Writing & Preference Amazon Nova Pro leads
Amazon Nova Pro: 43.9 (#226), Llama 2-70B: 32.3 (#279)
| Benchmark | Amazon Nova Pro | Llama 2-70B |
|---|---|---|
| LMArena Text | 1259 | 1115 |
| LMArena Creative Writing | 1212 | 1075 |
| LMArena Multi-Turn | 1246 | 1088 |
| Short-Story Creative Writing | 60.5% | — |
| WildBench | 77.7% | — |
| LiveBench Language | 37% | — |
Frequently asked questions
Is Amazon Nova Pro better than Llama 2-70B?
Amazon Nova Pro is the stronger model overall, scoring 31.0 to 24.4 on the Noometry Index.
Is Amazon Nova Pro or Llama 2-70B better for coding?
Amazon Nova Pro scores higher on coding benchmarks: 35.1 versus 31.4 in the Noometry coding category.
How many benchmarks do Amazon Nova Pro and Llama 2-70B share?
19 benchmarks have published results for both models. Amazon Nova Pro has 38 scored results on Noometry and Llama 2-70B has 35.