Model comparison
Amazon Nova Pro vs Llama 3.1-8B
Amazon Nova Pro is the stronger model overall, scoring 31.0 to 23.0 on the Noometry Index. Llama 3.1-8B costs 24× less per token, which makes it the better buy when Amazon Nova Pro's lead doesn't matter for your workload.
Last verified . 25 shared benchmarks.
MetaSummary
- They share 25 benchmarks with published results for both. Amazon Nova Pro scores higher in 8 categories and Llama 3.1-8B in 1 category; 9 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where Amazon Nova Pro leads 27.4 to 8.0.
- The biggest single-benchmark swing is MMLU-Pro: 67.3% for Amazon Nova Pro and 40.6% for Llama 3.1-8B.
- Llama 3.1-8B is cheaper at $0.05 / $0.08 per million input/output tokens, against $0.80 / $3.20 for Amazon Nova Pro.
- Amazon Nova Pro accepts more context: 300K tokens versus 128K.
- Llama 3.1-8B has downloadable open weights; the other is API-only.
Side by side
| Amazon Nova Pro | Llama 3.1-8B | |
|---|---|---|
| Provider | Amazon | Meta |
| Noometry Index | 31.0 | 23.0 |
| Released | 2024-12-03 | 2024-07-23 |
| Weights | Proprietary | Open |
| Context window | 300K | 128K |
| Max output | 10K | 4K |
| Input $ / M tokens | $0.80 | $0.05 |
| Output $ / M tokens | $3.20 | $0.08 |
| Results tracked | 38 | 43 |
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 3.1-8B: 20.2 (#340)
| Benchmark | Amazon Nova Pro | Llama 3.1-8B |
|---|---|---|
| LMArena Coding | 1270 | 1195 |
| SciCode | — | 13.2% |
| WeirdML | — | 1.7% |
| BigCodeBench Instruct | — | 32.8% |
| LiveBench Coding | 38.1% | — |
| BigCodeBench Complete | — | 40.5% |
| HumanEval+ | — | 62.8% |
| MBPP+ | — | 55.6% |
Agentic & Tool Use Llama 3.1-8B leads
Amazon Nova Pro: 16.7 (#147), Llama 3.1-8B: 22.5 (#131)
| Benchmark | Amazon Nova Pro | Llama 3.1-8B |
|---|---|---|
| Berkeley Function Calling Leaderboard | 25% | 25.8% |
| TheAgentCompany | 1.7% | — |
| BALROG | — | 15.1% |
Reasoning Amazon Nova Pro leads
Amazon Nova Pro: 20.0 (#243), Llama 3.1-8B: 14.9 (#321)
| Benchmark | Amazon Nova Pro | Llama 3.1-8B |
|---|---|---|
| LMArena Hard Prompts | 1246 | 1175 |
| Epoch Capabilities Index | 123.8 | 116.57 |
| CritPt | — | 0% |
| Chess Puzzles | — | 0% |
| LiveBench Reasoning | 32.6% | — |
| DTBench | — | 50.9% |
| LiveBench Data Analysis | 48.3% | — |
| LMCA | — | 5.4% |
| LiveBench | 43.5% | — |
| PIQA | — | 81.2% |
Math Amazon Nova Pro leads
Amazon Nova Pro: 28.5 (#243), Llama 3.1-8B: 10.2 (#317)
| Benchmark | Amazon Nova Pro | Llama 3.1-8B |
|---|---|---|
| Omni-MATH | 24.2% | 13.7% |
| LMArena Math | 1252 | 1179 |
| OTIS Mock AIME 2024-2025 | — | 1.7% |
| LiveBench Math | 38% | — |
| MATH Level 5 | — | 22.9% |
| GSM8K | — | 82.4% |
Knowledge Amazon Nova Pro leads
Amazon Nova Pro: 27.4 (#250), Llama 3.1-8B: 8.0 (#307)
| Benchmark | Amazon Nova Pro | Llama 3.1-8B |
|---|---|---|
| MMLU-Pro | 67.3% | 40.6% |
| GPQA (HELM) | 44.6% | 24.7% |
| LMArena Expert | 1211 | 1144 |
| MMLU | 82% | 56.1% |
| GPQA Diamond | — | 27% |
| Humanity's Last Exam | 4.4% | — |
| Confabulations | 30.1% | — |
| Vectara Hallucination Rate | 5.1% | — |
| BoolQ | — | 82.8% |
Multimodal Not comparable
Amazon Nova Pro: 25.0 (#126), Llama 3.1-8B: —
| Benchmark | Amazon Nova Pro | Llama 3.1-8B |
|---|---|---|
| LMArena Vision | 980 | — |
Multilingual Amazon Nova Pro leads
Amazon Nova Pro: 39.7 (#223), Llama 3.1-8B: 34.0 (#249)
| Benchmark | Amazon Nova Pro | Llama 3.1-8B |
|---|---|---|
| LMArena Non-English | 1234 | 1148 |
| LMArena Chinese | 1244 | 1151 |
| LMArena French | 1271 | 1177 |
| LMArena German | 1243 | 1144 |
| LMArena Japanese | 1200 | 1061 |
| LMArena Korean | 1203 | 1053 |
| LMArena Russian | 1240 | 1158 |
| LMArena Spanish | 1182 | 1169 |
Instruction Following Amazon Nova Pro leads
Amazon Nova Pro: 64.9 (#226), Llama 3.1-8B: 58.9 (#258)
| Benchmark | Amazon Nova Pro | Llama 3.1-8B |
|---|---|---|
| IFEval | 81.5% | 74.3% |
| LMArena Instruction Following | 1235 | 1159 |
| LiveBench Instruction Following | 67.1% | — |
Long Context Amazon Nova Pro leads
Amazon Nova Pro: 38.1 (#205), Llama 3.1-8B: 35.8 (#238)
| Benchmark | Amazon Nova Pro | Llama 3.1-8B |
|---|---|---|
| LMArena Longer Query | 1255 | 1182 |
Writing & Preference Amazon Nova Pro leads
Amazon Nova Pro: 43.9 (#226), Llama 3.1-8B: 29.7 (#290)
| Benchmark | Amazon Nova Pro | Llama 3.1-8B |
|---|---|---|
| LMArena Text | 1259 | 1187 |
| LMArena Creative Writing | 1212 | 1154 |
| WildBench | 77.7% | 68.7% |
| LMArena Multi-Turn | 1246 | 1172 |
| Short-Story Creative Writing | 60.5% | — |
| EQ-Bench Creative Writing | — | 713 |
| LiveBench Language | 37% | — |
Frequently asked questions
Is Amazon Nova Pro better than Llama 3.1-8B?
Amazon Nova Pro is the stronger model overall, scoring 31.0 to 23.0 on the Noometry Index. Llama 3.1-8B costs 24× less per token, which makes it the better buy when Amazon Nova Pro's lead doesn't matter for your workload.
Which is cheaper, Amazon Nova Pro or Llama 3.1-8B?
Llama 3.1-8B is cheaper. It lists at $0.05 per million input tokens and $0.08 per million output tokens; Amazon Nova Pro lists at $0.80 and $3.20.
Is Amazon Nova Pro or Llama 3.1-8B better for coding?
Amazon Nova Pro scores higher on coding benchmarks: 35.1 versus 20.2 in the Noometry coding category.
Which has the bigger context window?
Amazon Nova Pro does, with 300K tokens against 128K.
How many benchmarks do Amazon Nova Pro and Llama 3.1-8B share?
25 benchmarks have published results for both models. Amazon Nova Pro has 38 scored results on Noometry and Llama 3.1-8B has 43.