Model comparison
Amazon Nova Pro vs Llama 2-7B
Amazon Nova Pro is the stronger model overall, scoring 30.5 to 28.6 on the Noometry Index.
Last verified . 17 shared benchmarks.
MetaSummary
- They share 17 benchmarks with published results for both. Amazon Nova Pro scores higher in 6 categories and Llama 2-7B in 2 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in multilingual, where Amazon Nova Pro leads 39.9 to 23.9.
- Llama 2-7B has downloadable open weights; the other is API-only.
Side by side
| Amazon Nova Pro | Llama 2-7B | |
|---|---|---|
| Provider | Amazon | Meta |
| Noometry Index | 30.5 | 28.6 |
| 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 | 29 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Amazon Nova Pro leads
Amazon Nova Pro: 34.6 (#224), Llama 2-7B: 28.7 (#302)
| Benchmark | Amazon Nova Pro | Llama 2-7B |
|---|---|---|
| LMArena Coding | 1270 | 1002 |
| LiveBench Coding | 38.1% | — |
Agentic & Tool Use Not comparable
Amazon Nova Pro: 16.6 (#139), Llama 2-7B: —
| Benchmark | Amazon Nova Pro | Llama 2-7B |
|---|---|---|
| Berkeley Function Calling Leaderboard | 25% | — |
| TheAgentCompany | 1.7% | — |
Reasoning Amazon Nova Pro leads
Amazon Nova Pro: 19.2 (#240), Llama 2-7B: 15.1 (#309)
| Benchmark | Amazon Nova Pro | Llama 2-7B |
|---|---|---|
| LMArena Hard Prompts | 1246 | 1009 |
| Epoch Capabilities Index | 123.75 | 98.54 |
| Chess Puzzles | — | 0% |
| LiveBench Reasoning | 32.6% | — |
| LiveBench Data Analysis | 48.3% | — |
| BIG-Bench Hard | — | 39.2% |
| HellaSwag | — | 77.2% |
| LAMBADA | — | 73.3% |
| LiveBench | 43.5% | — |
| PIQA | — | 78.8% |
| WinoGrande | — | 69.2% |
Math Llama 2-7B leads
Amazon Nova Pro: 26.4 (#240), Llama 2-7B: 28.2 (#231)
| Benchmark | Amazon Nova Pro | Llama 2-7B |
|---|---|---|
| LMArena Math | 1252 | 1042 |
| Omni-MATH | 24.2% | — |
| LiveBench Math | 38% | — |
| GSM8K | — | 16.7% |
Knowledge Too close to call
Amazon Nova Pro: 27.1 (#246), Llama 2-7B: 27.7 (#243)
| Benchmark | Amazon Nova Pro | Llama 2-7B |
|---|---|---|
| LMArena Expert | 1211 | 1036 |
| MMLU | 82% | 45.8% |
| 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 | — | 45.9% |
| BoolQ | — | 77.9% |
| OpenBookQA | — | 58.6% |
| TriviaQA | — | 73.7% |
Multimodal Not comparable
Amazon Nova Pro: 24.5 (#121), Llama 2-7B: —
| Benchmark | Amazon Nova Pro | Llama 2-7B |
|---|---|---|
| LMArena Vision | 980 | — |
| ScienceQA | — | 43.1% |
Multilingual Amazon Nova Pro leads
Amazon Nova Pro: 39.9 (#218), Llama 2-7B: 23.9 (#288)
| Benchmark | Amazon Nova Pro | Llama 2-7B |
|---|---|---|
| LMArena Non-English | 1234 | 973 |
| LMArena Chinese | 1244 | 973 |
| LMArena French | 1270 | 969 |
| LMArena German | 1243 | 978 |
| LMArena Russian | 1240 | 995 |
| LMArena Spanish | 1182 | 1007 |
| LMArena Japanese | 1200 | — |
| LMArena Korean | 1203 | — |
Instruction Following Amazon Nova Pro leads
Amazon Nova Pro: 65.1 (#221), Llama 2-7B: 51.0 (#293)
| Benchmark | Amazon Nova Pro | Llama 2-7B |
|---|---|---|
| LMArena Instruction Following | 1235 | 1006 |
| LiveBench Instruction Following | 67.1% | — |
| IFEval | 81.5% | — |
Long Context Amazon Nova Pro leads
Amazon Nova Pro: 38.1 (#199), Llama 2-7B: 30.4 (#282)
| Benchmark | Amazon Nova Pro | Llama 2-7B |
|---|---|---|
| LMArena Longer Query | 1255 | 999 |
Writing & Preference Amazon Nova Pro leads
Amazon Nova Pro: 44.1 (#221), Llama 2-7B: 28.1 (#293)
| Benchmark | Amazon Nova Pro | Llama 2-7B |
|---|---|---|
| LMArena Text | 1259 | 1053 |
| LMArena Creative Writing | 1212 | 1033 |
| LMArena Multi-Turn | 1245 | 1029 |
| Short-Story Creative Writing | 60.5% | — |
| WildBench | 77.7% | — |
| LiveBench Language | 37% | — |
Frequently asked questions
Is Amazon Nova Pro better than Llama 2-7B?
Amazon Nova Pro is the stronger model overall, scoring 30.5 to 28.6 on the Noometry Index.
Is Amazon Nova Pro or Llama 2-7B better for coding?
Amazon Nova Pro scores higher on coding benchmarks: 34.6 versus 28.7 in the Noometry coding category.
How many benchmarks do Amazon Nova Pro and Llama 2-7B share?
17 benchmarks have published results for both models. Amazon Nova Pro has 38 scored results on Noometry and Llama 2-7B has 29.