Model comparison
Amazon Nova Micro vs Llama-3.3-70B-Instruct
Amazon Nova Micro and Llama-3.3-70B-Instruct score almost the same on the Noometry Index (30.4 vs 30.6), so choose on price, context window or the category you care about most.
Last verified . 27 shared benchmarks.
MetaSummary
- They share 27 benchmarks with published results for both. Amazon Nova Micro scores higher in 3 categories and Llama-3.3-70B-Instruct in 6 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in instruction following, where Llama-3.3-70B-Instruct leads 71.1 to 56.3.
- The biggest single-benchmark swing is LiveBench Instruction Following: 48% for Amazon Nova Micro and 82.7% for Llama-3.3-70B-Instruct.
- Amazon Nova Micro is cheaper at $0.035 / $0.14 per million input/output tokens, against $0.10 / $0.32 for Llama-3.3-70B-Instruct.
- Llama-3.3-70B-Instruct has downloadable open weights; the other is API-only.
Side by side
| Amazon Nova Micro | Llama-3.3-70B-Instruct | |
|---|---|---|
| Provider | Amazon | Meta |
| Noometry Index | 30.4 | 30.6 |
| Released | 2024-12-03 | 2024-12-06 |
| Weights | Proprietary | Open |
| Context window | 128K | 128K |
| Max output | 10K | 4K |
| Input $ / M tokens | $0.035 | $0.10 |
| Output $ / M tokens | $0.14 | $0.32 |
| Results tracked | 32 | 43 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Too close to call
Amazon Nova Micro: 30.5 (#295), Llama-3.3-70B-Instruct: 31.0 (#290)
| Benchmark | Amazon Nova Micro | Llama-3.3-70B-Instruct |
|---|---|---|
| LiveBench Coding | 20.2% | 36.6% |
| LMArena Coding | 1218 | 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 Micro: 22.1 (#132), Llama-3.3-70B-Instruct: 25.8 (#105)
| Benchmark | Amazon Nova Micro | Llama-3.3-70B-Instruct |
|---|---|---|
| Berkeley Function Calling Leaderboard | 22.3% | 31.9% |
| BALROG | — | 23% |
Reasoning Amazon Nova Micro leads
Amazon Nova Micro: 17.4 (#294), Llama-3.3-70B-Instruct: 14.1 (#327)
| Benchmark | Amazon Nova Micro | Llama-3.3-70B-Instruct |
|---|---|---|
| LiveBench Reasoning | 25.1% | 50.8% |
| LMArena Hard Prompts | 1191 | 1257 |
| LiveBench Data Analysis | 34% | 49.5% |
| LiveBench | 29.6% | 50.2% |
| SimpleBench | — | 19.9% |
| CritPt | — | 0% |
| DTBench | — | 59.5% |
| LMCA | — | 17.5% |
| Epoch Capabilities Index | — | 127.33 |
| ForecastBench | — | 58.6 |
Math Amazon Nova Micro leads
Amazon Nova Micro: 26.9 (#254), Llama-3.3-70B-Instruct: 15.3 (#298)
| Benchmark | Amazon Nova Micro | Llama-3.3-70B-Instruct |
|---|---|---|
| LiveBench Math | 34.5% | 42.2% |
| LMArena Math | 1206 | 1267 |
| OTIS Mock AIME 2024-2025 | — | 5.1% |
| Omni-MATH | 21.4% | — |
| MATH Level 5 | — | 41.6% |
Knowledge Llama-3.3-70B-Instruct leads
Amazon Nova Micro: 29.6 (#237), Llama-3.3-70B-Instruct: 30.6 (#226)
| Benchmark | Amazon Nova Micro | Llama-3.3-70B-Instruct |
|---|---|---|
| Vectara Hallucination Rate | 5.5% | 4.1% |
| LMArena Expert | 1184 | 1225 |
| MMLU | 70.8% | 86.3% |
| GPQA Diamond | — | 47.4% |
| MMLU-Pro | 51.1% | — |
| Confabulations | — | 22.8% |
| GPQA (HELM) | 38.3% | — |
Multilingual Llama-3.3-70B-Instruct leads
Amazon Nova Micro: 36.5 (#239), Llama-3.3-70B-Instruct: 39.9 (#220)
| Benchmark | Amazon Nova Micro | Llama-3.3-70B-Instruct |
|---|---|---|
| LMArena Non-English | 1186 | 1236 |
| LMArena Chinese | 1209 | 1217 |
| LMArena French | 1238 | 1281 |
| LMArena German | 1192 | 1251 |
| LMArena Japanese | 1154 | 1150 |
| LMArena Korean | 1150 | 1143 |
| LMArena Russian | 1185 | 1252 |
| LMArena Spanish | 1225 | 1270 |
Instruction Following Llama-3.3-70B-Instruct leads
Amazon Nova Micro: 56.3 (#272), Llama-3.3-70B-Instruct: 71.1 (#157)
| Benchmark | Amazon Nova Micro | Llama-3.3-70B-Instruct |
|---|---|---|
| LiveBench Instruction Following | 48% | 82.7% |
| LMArena Instruction Following | 1174 | 1242 |
| IFEval | 76% | — |
Long Context Amazon Nova Micro leads
Amazon Nova Micro: 36.5 (#229), Llama-3.3-70B-Instruct: 26.4 (#295)
| Benchmark | Amazon Nova Micro | Llama-3.3-70B-Instruct |
|---|---|---|
| LMArena Longer Query | 1205 | 1256 |
| Fiction.LiveBench | — | 33.3% |
Writing & Preference Llama-3.3-70B-Instruct leads
Amazon Nova Micro: 39.5 (#247), Llama-3.3-70B-Instruct: 47.6 (#207)
| Benchmark | Amazon Nova Micro | Llama-3.3-70B-Instruct |
|---|---|---|
| LMArena Text | 1208 | 1274 |
| LMArena Creative Writing | 1172 | 1250 |
| LMArena Multi-Turn | 1178 | 1280 |
| LiveBench Language | 15.8% | 39.2% |
| WildBench | 74.3% | — |
Frequently asked questions
Is Amazon Nova Micro better than Llama-3.3-70B-Instruct?
Amazon Nova Micro and Llama-3.3-70B-Instruct score almost the same on the Noometry Index (30.4 vs 30.6), so choose on price, context window or the category you care about most.
Which is cheaper, Amazon Nova Micro or Llama-3.3-70B-Instruct?
Amazon Nova Micro is cheaper. It lists at $0.035 per million input tokens and $0.14 per million output tokens; Llama-3.3-70B-Instruct lists at $0.10 and $0.32.
Is Amazon Nova Micro or Llama-3.3-70B-Instruct better for coding?
They score almost the same on coding (30.5 vs 31.0); test both on your own repository before choosing.
Which has the bigger context window?
Both accept 128K tokens.
How many benchmarks do Amazon Nova Micro and Llama-3.3-70B-Instruct share?
27 benchmarks have published results for both models. Amazon Nova Micro has 32 scored results on Noometry and Llama-3.3-70B-Instruct has 43.