Model comparison
Amazon Nova Pro vs o3-pro
o3-pro is the stronger model overall, scoring 42.9 to 31.0 on the Noometry Index. Amazon Nova Pro costs 25× less per token, which makes it the better buy when o3-pro's lead doesn't matter for your workload.
Last verified . 4 shared benchmarks.
Summary
- They share 4 benchmarks with published results for both. Amazon Nova Pro scores higher in 0 categories and o3-pro in 5 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in long context, where o3-pro leads 72.2 to 38.1.
- The biggest single-benchmark swing is Short-Story Creative Writing: 60.5% for Amazon Nova Pro and 84.4% for o3-pro.
- Amazon Nova Pro is cheaper at $0.80 / $3.20 per million input/output tokens, against $20 / $80 for o3-pro.
- Amazon Nova Pro accepts more context: 300K tokens versus 200K.
Side by side
| Amazon Nova Pro | o3-pro | |
|---|---|---|
| Provider | Amazon | OpenAI |
| Noometry Index | 31.0 | 42.9 |
| Released | 2024-12-03 | 2025-06-10 |
| Weights | Proprietary | Proprietary |
| Context window | 300K | 200K |
| Max output | 10K | 100K |
| Input $ / M tokens | $0.80 | $20 |
| Output $ / M tokens | $3.20 | $80 |
| Results tracked | 38 | 12 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding o3-pro leads
Amazon Nova Pro: 35.1 (#229), o3-pro: 55.5 (#24)
| Benchmark | Amazon Nova Pro | o3-pro |
|---|---|---|
| Aider Polyglot | — | 84.9% |
| WeirdML | — | 58.2% |
| LiveBench Coding | 38.1% | — |
| LMArena Coding | 1270 | — |
Agentic & Tool Use Not comparable
Amazon Nova Pro: 16.7 (#147), o3-pro: —
| Benchmark | Amazon Nova Pro | o3-pro |
|---|---|---|
| Berkeley Function Calling Leaderboard | 25% | — |
| TheAgentCompany | 1.7% | — |
Reasoning o3-pro leads
Amazon Nova Pro: 20.0 (#243), o3-pro: 23.8 (#171)
| Benchmark | Amazon Nova Pro | o3-pro |
|---|---|---|
| Epoch Capabilities Index | 123.8 | 147.42 |
| ARC-AGI-2 | — | 4.9% |
| Kagi LLM Benchmark | — | 72.1% |
| ARC-AGI-1 | — | 59.3% |
| LiveBench Reasoning | 32.6% | — |
| LMArena Hard Prompts | 1246 | — |
| DTBench | — | 86.9% |
| LiveBench Data Analysis | 48.3% | — |
| LMCA | — | 38.5% |
| LiveBench | 43.5% | — |
Math Not comparable
Amazon Nova Pro: 28.5 (#243), o3-pro: —
| Benchmark | Amazon Nova Pro | o3-pro |
|---|---|---|
| Omni-MATH | 24.2% | — |
| LiveBench Math | 38% | — |
| LMArena Math | 1252 | — |
Knowledge o3-pro leads
Amazon Nova Pro: 27.4 (#250), o3-pro: 29.5 (#238)
| Benchmark | Amazon Nova Pro | o3-pro |
|---|---|---|
| Confabulations | 30.1% | 14.2% |
| Vectara Hallucination Rate | 5.1% | 23.3% |
| Humanity's Last Exam | 4.4% | — |
| MMLU-Pro | 67.3% | — |
| GPQA (HELM) | 44.6% | — |
| LMArena Expert | 1211 | — |
| MMLU | 82% | — |
Multimodal Not comparable
Amazon Nova Pro: 25.0 (#126), o3-pro: —
| Benchmark | Amazon Nova Pro | o3-pro |
|---|---|---|
| LMArena Vision | 980 | — |
Multilingual Not comparable
Amazon Nova Pro: 39.7 (#223), o3-pro: —
| Benchmark | Amazon Nova Pro | o3-pro |
|---|---|---|
| LMArena Non-English | 1234 | — |
| LMArena Chinese | 1244 | — |
| LMArena French | 1271 | — |
| LMArena German | 1243 | — |
| LMArena Japanese | 1200 | — |
| LMArena Korean | 1203 | — |
| LMArena Russian | 1240 | — |
| LMArena Spanish | 1182 | — |
Instruction Following Not comparable
Amazon Nova Pro: 64.9 (#226), o3-pro: —
| Benchmark | Amazon Nova Pro | o3-pro |
|---|---|---|
| LiveBench Instruction Following | 67.1% | — |
| IFEval | 81.5% | — |
| LMArena Instruction Following | 1235 | — |
Long Context o3-pro leads
Amazon Nova Pro: 38.1 (#205), o3-pro: 72.2 (#1)
| Benchmark | Amazon Nova Pro | o3-pro |
|---|---|---|
| Fiction.LiveBench | — | 97.2% |
| LMArena Longer Query | 1255 | — |
Writing & Preference o3-pro leads
Amazon Nova Pro: 43.9 (#226), o3-pro: 57.1 (#133)
| Benchmark | Amazon Nova Pro | o3-pro |
|---|---|---|
| Short-Story Creative Writing | 60.5% | 84.4% |
| LMArena Text | 1259 | — |
| LMArena Creative Writing | 1212 | — |
| WildBench | 77.7% | — |
| LMArena Multi-Turn | 1246 | — |
| LiveBench Language | 37% | — |
Frequently asked questions
Is Amazon Nova Pro better than o3-pro?
o3-pro is the stronger model overall, scoring 42.9 to 31.0 on the Noometry Index. Amazon Nova Pro costs 25× less per token, which makes it the better buy when o3-pro's lead doesn't matter for your workload.
Which is cheaper, Amazon Nova Pro or o3-pro?
Amazon Nova Pro is cheaper. It lists at $0.80 per million input tokens and $3.20 per million output tokens; o3-pro lists at $20 and $80.
Is Amazon Nova Pro or o3-pro better for coding?
o3-pro scores higher on coding benchmarks: 55.5 versus 35.1 in the Noometry coding category.
Which has the bigger context window?
Amazon Nova Pro does, with 300K tokens against 200K.
How many benchmarks do Amazon Nova Pro and o3-pro share?
4 benchmarks have published results for both models. Amazon Nova Pro has 38 scored results on Noometry and o3-pro has 12.