Model comparison
Amazon Nova Pro vs Llama-3.3-70B-Instruct
Amazon Nova Pro and Llama-3.3-70B-Instruct score almost the same on the Noometry Index (31.0 vs 30.6), so choose on price, context window or the category you care about most.
Last verified . 29 shared benchmarks.
MetaSummary
- They share 29 benchmarks with published results for both. Amazon Nova Pro scores higher in 4 categories and Llama-3.3-70B-Instruct in 5 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Amazon Nova Pro leads 28.5 to 15.3.
- The biggest single-benchmark swing is LiveBench Reasoning: 32.6% for Amazon Nova Pro and 50.8% for Llama-3.3-70B-Instruct.
- Llama-3.3-70B-Instruct is cheaper at $0.10 / $0.32 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-3.3-70B-Instruct has downloadable open weights; the other is API-only.
Side by side
| Amazon Nova Pro | Llama-3.3-70B-Instruct | |
|---|---|---|
| Provider | Amazon | Meta |
| Noometry Index | 31.0 | 30.6 |
| Released | 2024-12-03 | 2024-12-06 |
| Weights | Proprietary | Open |
| Context window | 300K | 128K |
| Max output | 10K | 4K |
| Input $ / M tokens | $0.80 | $0.10 |
| Output $ / M tokens | $3.20 | $0.32 |
| 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-3.3-70B-Instruct: 31.0 (#290)
| Benchmark | Amazon Nova Pro | Llama-3.3-70B-Instruct |
|---|---|---|
| LiveBench Coding | 38.1% | 36.6% |
| LMArena Coding | 1270 | 1268 |
| SciCode | — | 26% |
| WeirdML | — | 14.4% |
| BigCodeBench Instruct | — | 46.9% |
| BigCodeBench Complete | — | 57.5% |
Agentic & Tool Use Llama-3.3-70B-Instruct leads
Amazon Nova Pro: 16.7 (#147), Llama-3.3-70B-Instruct: 25.8 (#105)
| Benchmark | Amazon Nova Pro | Llama-3.3-70B-Instruct |
|---|---|---|
| Berkeley Function Calling Leaderboard | 25% | 31.9% |
| TheAgentCompany | 1.7% | — |
| BALROG | — | 23% |
Reasoning Amazon Nova Pro leads
Amazon Nova Pro: 20.0 (#243), Llama-3.3-70B-Instruct: 14.1 (#327)
| Benchmark | Amazon Nova Pro | Llama-3.3-70B-Instruct |
|---|---|---|
| LiveBench Reasoning | 32.6% | 50.8% |
| LMArena Hard Prompts | 1246 | 1257 |
| LiveBench Data Analysis | 48.3% | 49.5% |
| Epoch Capabilities Index | 123.8 | 127.33 |
| LiveBench | 43.5% | 50.2% |
| SimpleBench | — | 19.9% |
| CritPt | — | 0% |
| DTBench | — | 59.5% |
| LMCA | — | 17.5% |
| ForecastBench | — | 58.6 |
Math Amazon Nova Pro leads
Amazon Nova Pro: 28.5 (#243), Llama-3.3-70B-Instruct: 15.3 (#298)
| Benchmark | Amazon Nova Pro | Llama-3.3-70B-Instruct |
|---|---|---|
| LiveBench Math | 38% | 42.2% |
| LMArena Math | 1252 | 1267 |
| OTIS Mock AIME 2024-2025 | — | 5.1% |
| Omni-MATH | 24.2% | — |
| MATH Level 5 | — | 41.6% |
Knowledge Llama-3.3-70B-Instruct leads
Amazon Nova Pro: 27.4 (#250), Llama-3.3-70B-Instruct: 30.6 (#226)
| Benchmark | Amazon Nova Pro | Llama-3.3-70B-Instruct |
|---|---|---|
| Confabulations | 30.1% | 22.8% |
| Vectara Hallucination Rate | 5.1% | 4.1% |
| LMArena Expert | 1211 | 1225 |
| MMLU | 82% | 86.3% |
| GPQA Diamond | — | 47.4% |
| Humanity's Last Exam | 4.4% | — |
| MMLU-Pro | 67.3% | — |
| GPQA (HELM) | 44.6% | — |
Multimodal Not comparable
Amazon Nova Pro: 25.0 (#126), Llama-3.3-70B-Instruct: —
| Benchmark | Amazon Nova Pro | Llama-3.3-70B-Instruct |
|---|---|---|
| LMArena Vision | 980 | — |
Multilingual Too close to call
Amazon Nova Pro: 39.7 (#223), Llama-3.3-70B-Instruct: 39.9 (#220)
| Benchmark | Amazon Nova Pro | Llama-3.3-70B-Instruct |
|---|---|---|
| LMArena Non-English | 1234 | 1236 |
| LMArena Chinese | 1244 | 1217 |
| LMArena French | 1271 | 1281 |
| LMArena German | 1243 | 1251 |
| LMArena Japanese | 1200 | 1150 |
| LMArena Korean | 1203 | 1143 |
| LMArena Russian | 1240 | 1252 |
| LMArena Spanish | 1182 | 1270 |
Instruction Following Llama-3.3-70B-Instruct leads
Amazon Nova Pro: 64.9 (#226), Llama-3.3-70B-Instruct: 71.1 (#157)
| Benchmark | Amazon Nova Pro | Llama-3.3-70B-Instruct |
|---|---|---|
| LiveBench Instruction Following | 67.1% | 82.7% |
| LMArena Instruction Following | 1235 | 1242 |
| IFEval | 81.5% | — |
Long Context Amazon Nova Pro leads
Amazon Nova Pro: 38.1 (#205), Llama-3.3-70B-Instruct: 26.4 (#295)
| Benchmark | Amazon Nova Pro | Llama-3.3-70B-Instruct |
|---|---|---|
| LMArena Longer Query | 1255 | 1256 |
| Fiction.LiveBench | — | 33.3% |
Writing & Preference Llama-3.3-70B-Instruct leads
Amazon Nova Pro: 43.9 (#226), Llama-3.3-70B-Instruct: 47.6 (#207)
| Benchmark | Amazon Nova Pro | Llama-3.3-70B-Instruct |
|---|---|---|
| LMArena Text | 1259 | 1274 |
| LMArena Creative Writing | 1212 | 1250 |
| LMArena Multi-Turn | 1246 | 1280 |
| LiveBench Language | 37% | 39.2% |
| Short-Story Creative Writing | 60.5% | — |
| WildBench | 77.7% | — |
Frequently asked questions
Is Amazon Nova Pro better than Llama-3.3-70B-Instruct?
Amazon Nova Pro and Llama-3.3-70B-Instruct score almost the same on the Noometry Index (31.0 vs 30.6), so choose on price, context window or the category you care about most.
Which is cheaper, Amazon Nova Pro or Llama-3.3-70B-Instruct?
Llama-3.3-70B-Instruct is cheaper. It lists at $0.10 per million input tokens and $0.32 per million output tokens; Amazon Nova Pro lists at $0.80 and $3.20.
Is Amazon Nova Pro or Llama-3.3-70B-Instruct better for coding?
Amazon Nova Pro scores higher on coding benchmarks: 35.1 versus 31.0 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-3.3-70B-Instruct share?
29 benchmarks have published results for both models. Amazon Nova Pro has 38 scored results on Noometry and Llama-3.3-70B-Instruct has 43.