Model comparison
Amazon Nova Pro vs Llama 2-13B
Amazon Nova Pro is the stronger model overall, scoring 31.0 to 29.6 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 6 categories and Llama 2-13B in 2 categories; 7 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Amazon Nova Pro leads 43.9 to 29.8.
- Llama 2-13B has downloadable open weights; the other is API-only.
Side by side
| Amazon Nova Pro | Llama 2-13B | |
|---|---|---|
| Provider | Amazon | Meta |
| Noometry Index | 31.0 | 29.6 |
| 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 | 32 |
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 2-13B: 30.9 (#291)
| Benchmark | Amazon Nova Pro | Llama 2-13B |
|---|---|---|
| LMArena Coding | 1270 | 1062 |
| LiveBench Coding | 38.1% | — |
Agentic & Tool Use Not comparable
Amazon Nova Pro: 16.7 (#147), Llama 2-13B: —
| Benchmark | Amazon Nova Pro | Llama 2-13B |
|---|---|---|
| Berkeley Function Calling Leaderboard | 25% | — |
| TheAgentCompany | 1.7% | — |
Reasoning Amazon Nova Pro leads
Amazon Nova Pro: 20.0 (#243), Llama 2-13B: 12.8 (#337)
| Benchmark | Amazon Nova Pro | Llama 2-13B |
|---|---|---|
| LMArena Hard Prompts | 1246 | 1051 |
| Epoch Capabilities Index | 123.8 | 106.17 |
| Chess Puzzles | — | 0% |
| LiveBench Reasoning | 32.6% | — |
| DTBench | — | 42.2% |
| LiveBench Data Analysis | 48.3% | — |
| BIG-Bench Hard | — | 58.2% |
| HellaSwag | — | 80.7% |
| LAMBADA | — | 76.5% |
| LiveBench | 43.5% | — |
| PIQA | — | 80.8% |
| WinoGrande | — | 72.8% |
Math Llama 2-13B leads
Amazon Nova Pro: 28.5 (#243), Llama 2-13B: 31.1 (#229)
| Benchmark | Amazon Nova Pro | Llama 2-13B |
|---|---|---|
| LMArena Math | 1252 | 1065 |
| Omni-MATH | 24.2% | — |
| LiveBench Math | 38% | — |
| GSM8K | — | 36.9% |
Knowledge Too close to call
Amazon Nova Pro: 27.4 (#250), Llama 2-13B: 28.1 (#249)
| Benchmark | Amazon Nova Pro | Llama 2-13B |
|---|---|---|
| LMArena Expert | 1211 | 1030 |
| MMLU | 82% | 55.6% |
| 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 | — | 60.3% |
| BoolQ | — | 82.4% |
| OpenBookQA | — | 57% |
| TriviaQA | — | 79.6% |
Multimodal Not comparable
Amazon Nova Pro: 25.0 (#126), Llama 2-13B: —
| Benchmark | Amazon Nova Pro | Llama 2-13B |
|---|---|---|
| LMArena Vision | 980 | — |
| ScienceQA | — | 55.8% |
Multilingual Amazon Nova Pro leads
Amazon Nova Pro: 39.7 (#223), Llama 2-13B: 26.5 (#279)
| Benchmark | Amazon Nova Pro | Llama 2-13B |
|---|---|---|
| LMArena Non-English | 1234 | 1024 |
| LMArena Chinese | 1244 | 1001 |
| LMArena French | 1271 | 1044 |
| LMArena German | 1243 | 1009 |
| LMArena Japanese | 1200 | 894 |
| LMArena Korean | 1203 | 953 |
| LMArena Russian | 1240 | 1055 |
| LMArena Spanish | 1182 | 1087 |
Instruction Following Amazon Nova Pro leads
Amazon Nova Pro: 64.9 (#226), Llama 2-13B: 53.3 (#287)
| Benchmark | Amazon Nova Pro | Llama 2-13B |
|---|---|---|
| LMArena Instruction Following | 1235 | 1045 |
| LiveBench Instruction Following | 67.1% | — |
| IFEval | 81.5% | — |
Long Context Amazon Nova Pro leads
Amazon Nova Pro: 38.1 (#205), Llama 2-13B: 32.3 (#269)
| Benchmark | Amazon Nova Pro | Llama 2-13B |
|---|---|---|
| LMArena Longer Query | 1255 | 1064 |
Writing & Preference Amazon Nova Pro leads
Amazon Nova Pro: 43.9 (#226), Llama 2-13B: 29.8 (#289)
| Benchmark | Amazon Nova Pro | Llama 2-13B |
|---|---|---|
| LMArena Text | 1259 | 1084 |
| LMArena Creative Writing | 1212 | 1047 |
| LMArena Multi-Turn | 1246 | 1050 |
| Short-Story Creative Writing | 60.5% | — |
| WildBench | 77.7% | — |
| LiveBench Language | 37% | — |
Frequently asked questions
Is Amazon Nova Pro better than Llama 2-13B?
Amazon Nova Pro is the stronger model overall, scoring 31.0 to 29.6 on the Noometry Index.
Is Amazon Nova Pro or Llama 2-13B better for coding?
Amazon Nova Pro scores higher on coding benchmarks: 35.1 versus 30.9 in the Noometry coding category.
How many benchmarks do Amazon Nova Pro and Llama 2-13B share?
19 benchmarks have published results for both models. Amazon Nova Pro has 38 scored results on Noometry and Llama 2-13B has 32.