Model comparison
Amazon Nova Experimental Chat 10 09 vs Llama 2-70B
Amazon Nova Experimental Chat 10 09 is the stronger model overall, scoring 41.4 to 24.1 on the Noometry Index.
Last verified . 9 shared benchmarks.
MetaSummary
- They share 9 benchmarks with published results for both. Amazon Nova Experimental Chat 10 09 scores higher in 6 categories and Llama 2-70B in 0 categories; 6 gaps are clear of the uncertainty.
- The widest gap is in writing & preference, where Amazon Nova Experimental Chat 10 09 leads 55.0 to 32.5.
- Llama 2-70B has downloadable open weights; the other is API-only.
Side by side
| Amazon Nova Experimental Chat 10 09 | Llama 2-70B | |
|---|---|---|
| Provider | Amazon | Meta |
| Noometry Index | 41.4 | 24.1 |
| Released | — | 2023-07-18 |
| Weights | Proprietary | Open |
| Context window | — | — |
| Max output | — | — |
| Input $ / M tokens | — | — |
| Output $ / M tokens | — | — |
| Results tracked | 9 | 35 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Amazon Nova Experimental Chat 10 09 leads
Amazon Nova Experimental Chat 10 09: 39.6 (#142), Llama 2-70B: 30.8 (#281)
| Benchmark | Amazon Nova Experimental Chat 10 09 | Llama 2-70B |
|---|---|---|
| LMArena Coding | 1371 | 1079 |
Reasoning Amazon Nova Experimental Chat 10 09 leads
Amazon Nova Experimental Chat 10 09: 26.2 (#122), Llama 2-70B: 13.7 (#324)
| Benchmark | Amazon Nova Experimental Chat 10 09 | Llama 2-70B |
|---|---|---|
| LMArena Hard Prompts | 1356 | 1073 |
| DTBench | — | 41.6% |
| BIG-Bench Hard | — | 64.9% |
| CommonsenseQA 2.0 | — | 50% |
| Epoch Capabilities Index | — | 113.59 |
| ForecastBench | — | 51.4 |
| HellaSwag | — | 85.3% |
| LAMBADA | — | 78.9% |
| PIQA | — | 82.8% |
| WinoGrande | — | 80.2% |
Math Not comparable
Amazon Nova Experimental Chat 10 09: —, Llama 2-70B: 7.5 (#320)
| Benchmark | Amazon Nova Experimental Chat 10 09 | Llama 2-70B |
|---|---|---|
| OTIS Mock AIME 2024-2025 | — | 0% |
| LMArena Math | — | 1091 |
| MATH Level 5 | — | 3.3% |
| GSM8K | — | 69.6% |
Knowledge Not comparable
Amazon Nova Experimental Chat 10 09: —, Llama 2-70B: 7.4 (#305)
| Benchmark | Amazon Nova Experimental Chat 10 09 | Llama 2-70B |
|---|---|---|
| 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 Amazon Nova Experimental Chat 10 09 leads
Amazon Nova Experimental Chat 10 09: 47.5 (#145), Llama 2-70B: 27.9 (#269)
| Benchmark | Amazon Nova Experimental Chat 10 09 | Llama 2-70B |
|---|---|---|
| LMArena Non-English | 1341 | 1045 |
| LMArena Chinese | 1345 | 994 |
| LMArena French | — | 1089 |
| LMArena German | — | 1041 |
| LMArena Japanese | — | 927 |
| LMArena Korean | — | 964 |
| LMArena Russian | — | 1083 |
| LMArena Spanish | — | 1142 |
Instruction Following Amazon Nova Experimental Chat 10 09 leads
Amazon Nova Experimental Chat 10 09: 69.7 (#167), Llama 2-70B: 55.1 (#273)
| Benchmark | Amazon Nova Experimental Chat 10 09 | Llama 2-70B |
|---|---|---|
| LMArena Instruction Following | 1316 | 1071 |
Long Context Amazon Nova Experimental Chat 10 09 leads
Amazon Nova Experimental Chat 10 09: 40.6 (#146), Llama 2-70B: 32.2 (#265)
| Benchmark | Amazon Nova Experimental Chat 10 09 | Llama 2-70B |
|---|---|---|
| LMArena Longer Query | 1334 | 1062 |
Writing & Preference Amazon Nova Experimental Chat 10 09 leads
Amazon Nova Experimental Chat 10 09: 55.0 (#144), Llama 2-70B: 32.5 (#274)
| Benchmark | Amazon Nova Experimental Chat 10 09 | Llama 2-70B |
|---|---|---|
| LMArena Text | 1365 | 1115 |
| LMArena Creative Writing | 1307 | 1075 |
| LMArena Multi-Turn | 1354 | 1088 |
Frequently asked questions
Is Amazon Nova Experimental Chat 10 09 better than Llama 2-70B?
Amazon Nova Experimental Chat 10 09 is the stronger model overall, scoring 41.4 to 24.1 on the Noometry Index.
Is Amazon Nova Experimental Chat 10 09 or Llama 2-70B better for coding?
Amazon Nova Experimental Chat 10 09 scores higher on coding benchmarks: 39.6 versus 30.8 in the Noometry coding category.
How many benchmarks do Amazon Nova Experimental Chat 10 09 and Llama 2-70B share?
9 benchmarks have published results for both models. Amazon Nova Experimental Chat 10 09 has 9 scored results on Noometry and Llama 2-70B has 35.