Model comparison
Amazon Nova Pro vs GPT-3.5-turbo
Amazon Nova Pro is the stronger model overall, scoring 31.0 to 23.2 on the Noometry Index. GPT-3.5-turbo costs 1.9× less per token, which makes it the better buy when Amazon Nova Pro's lead doesn't matter for your workload.
Last verified . 19 shared benchmarks.
Summary
- They share 19 benchmarks with published results for both. Amazon Nova Pro scores higher in 8 categories and GPT-3.5-turbo in 0 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in math, where Amazon Nova Pro leads 28.5 to 6.3.
- GPT-3.5-turbo is cheaper at $0.50 / $1.50 per million input/output tokens, against $0.80 / $3.20 for Amazon Nova Pro.
- Amazon Nova Pro accepts more context: 300K tokens versus 16K.
Side by side
| Amazon Nova Pro | GPT-3.5-turbo | |
|---|---|---|
| Provider | Amazon | OpenAI |
| Noometry Index | 31.0 | 23.2 |
| Released | 2024-12-03 | 2023-03-01 |
| Weights | Proprietary | Proprietary |
| Context window | 300K | 16K |
| Max output | 10K | 4K |
| Input $ / M tokens | $0.80 | $0.50 |
| Output $ / M tokens | $3.20 | $1.50 |
| Results tracked | 38 | 44 |
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), GPT-3.5-turbo: 23.9 (#331)
| Benchmark | Amazon Nova Pro | GPT-3.5-turbo |
|---|---|---|
| LMArena Coding | 1270 | 1136 |
| WeirdML | — | 3.5% |
| BigCodeBench Instruct | — | 39.1% |
| LiveBench Coding | 38.1% | — |
| BigCodeBench Complete | — | 50.6% |
| HumanEval+ | — | 70.7% |
| MBPP+ | — | 69.7% |
Agentic & Tool Use Not comparable
Amazon Nova Pro: 16.7 (#147), GPT-3.5-turbo: —
| Benchmark | Amazon Nova Pro | GPT-3.5-turbo |
|---|---|---|
| Berkeley Function Calling Leaderboard | 25% | — |
| TheAgentCompany | 1.7% | — |
| METR Time Horizons | — | 21.5% |
Reasoning Amazon Nova Pro leads
Amazon Nova Pro: 20.0 (#243), GPT-3.5-turbo: 13.8 (#332)
| Benchmark | Amazon Nova Pro | GPT-3.5-turbo |
|---|---|---|
| LMArena Hard Prompts | 1246 | 1108 |
| Epoch Capabilities Index | 123.8 | 118.55 |
| Chess Puzzles | — | 0% |
| LiveBench Reasoning | 32.6% | — |
| Mystery Game Puzzles | — | 3% |
| DTBench | — | 48.5% |
| LiveBench Data Analysis | 48.3% | — |
| LMCA | — | 9.7% |
| Adversarial NLI | — | 58.1% |
| BIG-Bench Hard | — | 61.6% |
| CommonsenseQA 2.0 | — | 57% |
| ForecastBench | — | 50.4 |
| LiveBench | 43.5% | — |
| WinoGrande | — | 81.6% |
Math Amazon Nova Pro leads
Amazon Nova Pro: 28.5 (#243), GPT-3.5-turbo: 6.3 (#327)
| Benchmark | Amazon Nova Pro | GPT-3.5-turbo |
|---|---|---|
| LMArena Math | 1252 | 1142 |
| FrontierMath (Tiers 1-3) | — | 0% |
| OTIS Mock AIME 2024-2025 | — | 2.2% |
| Omni-MATH | 24.2% | — |
| LiveBench Math | 38% | — |
| MATH Level 5 | — | 15.9% |
| GSM8K | — | 57.8% |
Knowledge Amazon Nova Pro leads
Amazon Nova Pro: 27.4 (#250), GPT-3.5-turbo: 10.0 (#303)
| Benchmark | Amazon Nova Pro | GPT-3.5-turbo |
|---|---|---|
| LMArena Expert | 1211 | 1070 |
| MMLU | 82% | 71.4% |
| GPQA Diamond | — | 28% |
| Humanity's Last Exam | 4.4% | — |
| MMLU-Pro | 67.3% | — |
| Confabulations | 30.1% | — |
| Vectara Hallucination Rate | 5.1% | — |
| GPQA (HELM) | 44.6% | — |
| ARC (AI2) Challenge | — | 87.4% |
| BoolQ | — | 87% |
| OpenBookQA | — | 86% |
| TriviaQA | — | 85.8% |
Multimodal Not comparable
Amazon Nova Pro: 25.0 (#126), GPT-3.5-turbo: —
| Benchmark | Amazon Nova Pro | GPT-3.5-turbo |
|---|---|---|
| LMArena Vision | 980 | — |
Multilingual Amazon Nova Pro leads
Amazon Nova Pro: 39.7 (#223), GPT-3.5-turbo: 31.5 (#258)
| Benchmark | Amazon Nova Pro | GPT-3.5-turbo |
|---|---|---|
| LMArena Non-English | 1234 | 1108 |
| LMArena Chinese | 1244 | 1075 |
| LMArena French | 1271 | 1118 |
| LMArena German | 1243 | 1090 |
| LMArena Japanese | 1200 | 1043 |
| LMArena Korean | 1203 | 1019 |
| LMArena Russian | 1240 | 1123 |
| LMArena Spanish | 1182 | 1121 |
Instruction Following Amazon Nova Pro leads
Amazon Nova Pro: 64.9 (#226), GPT-3.5-turbo: 57.9 (#262)
| Benchmark | Amazon Nova Pro | GPT-3.5-turbo |
|---|---|---|
| LMArena Instruction Following | 1235 | 1119 |
| LiveBench Instruction Following | 67.1% | — |
| IFEval | 81.5% | — |
Long Context Amazon Nova Pro leads
Amazon Nova Pro: 38.1 (#205), GPT-3.5-turbo: 34.0 (#254)
| Benchmark | Amazon Nova Pro | GPT-3.5-turbo |
|---|---|---|
| LMArena Longer Query | 1255 | 1121 |
Writing & Preference Amazon Nova Pro leads
Amazon Nova Pro: 43.9 (#226), GPT-3.5-turbo: 25.3 (#305)
| Benchmark | Amazon Nova Pro | GPT-3.5-turbo |
|---|---|---|
| LMArena Text | 1259 | 1125 |
| LMArena Creative Writing | 1212 | 1092 |
| LMArena Multi-Turn | 1246 | 1117 |
| Short-Story Creative Writing | 60.5% | — |
| EQ-Bench Creative Writing | — | 451 |
| WildBench | 77.7% | — |
| LiveBench Language | 37% | — |
Frequently asked questions
Is Amazon Nova Pro better than GPT-3.5-turbo?
Amazon Nova Pro is the stronger model overall, scoring 31.0 to 23.2 on the Noometry Index. GPT-3.5-turbo costs 1.9× 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 GPT-3.5-turbo?
GPT-3.5-turbo is cheaper. It lists at $0.50 per million input tokens and $1.50 per million output tokens; Amazon Nova Pro lists at $0.80 and $3.20.
Is Amazon Nova Pro or GPT-3.5-turbo better for coding?
Amazon Nova Pro scores higher on coding benchmarks: 35.1 versus 23.9 in the Noometry coding category.
Which has the bigger context window?
Amazon Nova Pro does, with 300K tokens against 16K.
How many benchmarks do Amazon Nova Pro and GPT-3.5-turbo share?
19 benchmarks have published results for both models. Amazon Nova Pro has 38 scored results on Noometry and GPT-3.5-turbo has 44.