Model comparison
Amazon Nova Micro vs GPT-3.5-turbo
Amazon Nova Micro is the stronger model overall, scoring 30.4 to 23.2 on the Noometry Index.
Last verified . 18 shared benchmarks.
Summary
- They share 18 benchmarks with published results for both. Amazon Nova Micro scores higher in 7 categories and GPT-3.5-turbo in 1 category; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Amazon Nova Micro leads 26.9 to 6.3.
- Amazon Nova Micro is cheaper at $0.035 / $0.14 per million input/output tokens, against $0.50 / $1.50 for GPT-3.5-turbo.
- Amazon Nova Micro accepts more context: 128K tokens versus 16K.
Side by side
| Amazon Nova Micro | GPT-3.5-turbo | |
|---|---|---|
| Provider | Amazon | OpenAI |
| Noometry Index | 30.4 | 23.2 |
| Released | 2024-12-03 | 2023-03-01 |
| Weights | Proprietary | Proprietary |
| Context window | 128K | 16K |
| Max output | 10K | 4K |
| Input $ / M tokens | $0.035 | $0.50 |
| Output $ / M tokens | $0.14 | $1.50 |
| Results tracked | 32 | 44 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Amazon Nova Micro leads
Amazon Nova Micro: 30.5 (#295), GPT-3.5-turbo: 23.9 (#331)
| Benchmark | Amazon Nova Micro | GPT-3.5-turbo |
|---|---|---|
| LMArena Coding | 1218 | 1136 |
| WeirdML | — | 3.5% |
| BigCodeBench Instruct | — | 39.1% |
| LiveBench Coding | 20.2% | — |
| BigCodeBench Complete | — | 50.6% |
| HumanEval+ | — | 70.7% |
| MBPP+ | — | 69.7% |
Agentic & Tool Use Not comparable
Amazon Nova Micro: 22.1 (#132), GPT-3.5-turbo: —
| Benchmark | Amazon Nova Micro | GPT-3.5-turbo |
|---|---|---|
| Berkeley Function Calling Leaderboard | 22.3% | — |
| METR Time Horizons | — | 21.5% |
Reasoning Amazon Nova Micro leads
Amazon Nova Micro: 17.4 (#294), GPT-3.5-turbo: 13.8 (#332)
| Benchmark | Amazon Nova Micro | GPT-3.5-turbo |
|---|---|---|
| LMArena Hard Prompts | 1191 | 1108 |
| Chess Puzzles | — | 0% |
| LiveBench Reasoning | 25.1% | — |
| Mystery Game Puzzles | — | 3% |
| DTBench | — | 48.5% |
| LiveBench Data Analysis | 34% | — |
| LMCA | — | 9.7% |
| Adversarial NLI | — | 58.1% |
| BIG-Bench Hard | — | 61.6% |
| CommonsenseQA 2.0 | — | 57% |
| Epoch Capabilities Index | — | 118.55 |
| ForecastBench | — | 50.4 |
| LiveBench | 29.6% | — |
| WinoGrande | — | 81.6% |
Math Amazon Nova Micro leads
Amazon Nova Micro: 26.9 (#254), GPT-3.5-turbo: 6.3 (#327)
| Benchmark | Amazon Nova Micro | GPT-3.5-turbo |
|---|---|---|
| LMArena Math | 1206 | 1142 |
| FrontierMath (Tiers 1-3) | — | 0% |
| OTIS Mock AIME 2024-2025 | — | 2.2% |
| Omni-MATH | 21.4% | — |
| LiveBench Math | 34.5% | — |
| MATH Level 5 | — | 15.9% |
| GSM8K | — | 57.8% |
Knowledge Amazon Nova Micro leads
Amazon Nova Micro: 29.6 (#237), GPT-3.5-turbo: 10.0 (#303)
| Benchmark | Amazon Nova Micro | GPT-3.5-turbo |
|---|---|---|
| LMArena Expert | 1184 | 1070 |
| MMLU | 70.8% | 71.4% |
| GPQA Diamond | — | 28% |
| MMLU-Pro | 51.1% | — |
| Vectara Hallucination Rate | 5.5% | — |
| GPQA (HELM) | 38.3% | — |
| ARC (AI2) Challenge | — | 87.4% |
| BoolQ | — | 87% |
| OpenBookQA | — | 86% |
| TriviaQA | — | 85.8% |
Multilingual Amazon Nova Micro leads
Amazon Nova Micro: 36.5 (#239), GPT-3.5-turbo: 31.5 (#258)
| Benchmark | Amazon Nova Micro | GPT-3.5-turbo |
|---|---|---|
| LMArena Non-English | 1186 | 1108 |
| LMArena Chinese | 1209 | 1075 |
| LMArena French | 1238 | 1118 |
| LMArena German | 1192 | 1090 |
| LMArena Japanese | 1154 | 1043 |
| LMArena Korean | 1150 | 1019 |
| LMArena Russian | 1185 | 1123 |
| LMArena Spanish | 1225 | 1121 |
Instruction Following GPT-3.5-turbo leads
Amazon Nova Micro: 56.3 (#272), GPT-3.5-turbo: 57.9 (#262)
| Benchmark | Amazon Nova Micro | GPT-3.5-turbo |
|---|---|---|
| LMArena Instruction Following | 1174 | 1119 |
| LiveBench Instruction Following | 48% | — |
| IFEval | 76% | — |
Long Context Amazon Nova Micro leads
Amazon Nova Micro: 36.5 (#229), GPT-3.5-turbo: 34.0 (#254)
| Benchmark | Amazon Nova Micro | GPT-3.5-turbo |
|---|---|---|
| LMArena Longer Query | 1205 | 1121 |
Writing & Preference Amazon Nova Micro leads
Amazon Nova Micro: 39.5 (#247), GPT-3.5-turbo: 25.3 (#305)
| Benchmark | Amazon Nova Micro | GPT-3.5-turbo |
|---|---|---|
| LMArena Text | 1208 | 1125 |
| LMArena Creative Writing | 1172 | 1092 |
| LMArena Multi-Turn | 1178 | 1117 |
| EQ-Bench Creative Writing | — | 451 |
| WildBench | 74.3% | — |
| LiveBench Language | 15.8% | — |
Frequently asked questions
Is Amazon Nova Micro better than GPT-3.5-turbo?
Amazon Nova Micro is the stronger model overall, scoring 30.4 to 23.2 on the Noometry Index.
Which is cheaper, Amazon Nova Micro or GPT-3.5-turbo?
Amazon Nova Micro is cheaper. It lists at $0.035 per million input tokens and $0.14 per million output tokens; GPT-3.5-turbo lists at $0.50 and $1.50.
Is Amazon Nova Micro or GPT-3.5-turbo better for coding?
Amazon Nova Micro scores higher on coding benchmarks: 30.5 versus 23.9 in the Noometry coding category.
Which has the bigger context window?
Amazon Nova Micro does, with 128K tokens against 16K.
How many benchmarks do Amazon Nova Micro and GPT-3.5-turbo share?
18 benchmarks have published results for both models. Amazon Nova Micro has 32 scored results on Noometry and GPT-3.5-turbo has 44.