Model comparison
Amazon Nova Pro vs o3-mini
o3-mini is the stronger model overall, scoring 36.7 to 31.0 on the Noometry Index.
Last verified . 27 shared benchmarks.
Summary
- They share 27 benchmarks with published results for both. Amazon Nova Pro scores higher in 3 categories and o3-mini in 6 categories; 8 gaps are clear of the uncertainty.
- The widest gap is in agentic & tool use, where o3-mini leads 29.6 to 16.7.
- The biggest single-benchmark swing is LiveBench Reasoning: 32.6% for Amazon Nova Pro and 89.6% for o3-mini.
- Amazon Nova Pro is cheaper at $0.80 / $3.20 per million input/output tokens, against $1.10 / $4.40 for o3-mini.
- Amazon Nova Pro accepts more context: 300K tokens versus 200K.
Side by side
| Amazon Nova Pro | o3-mini | |
|---|---|---|
| Provider | Amazon | OpenAI |
| Noometry Index | 31.0 | 36.7 |
| Released | 2024-12-03 | 2024-12-20 |
| Weights | Proprietary | Proprietary |
| Context window | 300K | 200K |
| Max output | 10K | 100K |
| Input $ / M tokens | $0.80 | $1.10 |
| Output $ / M tokens | $3.20 | $4.40 |
| Results tracked | 38 | 51 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding o3-mini leads
Amazon Nova Pro: 35.1 (#229), o3-mini: 40.8 (#132)
| Benchmark | Amazon Nova Pro | o3-mini |
|---|---|---|
| LiveBench Coding | 38.1% | 82.7% |
| LMArena Coding | 1270 | 1378 |
| Aider Polyglot | — | 60.4% |
| SciCode | — | 39.8% |
| GSO | — | 1.3% |
| WeirdML | — | 43.7% |
| CadEval | — | 54% |
Agentic & Tool Use o3-mini leads
Amazon Nova Pro: 16.7 (#147), o3-mini: 29.6 (#84)
| Benchmark | Amazon Nova Pro | o3-mini |
|---|---|---|
| Berkeley Function Calling Leaderboard | 25% | — |
| TheAgentCompany | 1.7% | — |
| Cybench | — | 22.5% |
Reasoning Amazon Nova Pro leads
Amazon Nova Pro: 20.0 (#243), o3-mini: 16.3 (#305)
| Benchmark | Amazon Nova Pro | o3-mini |
|---|---|---|
| LiveBench Reasoning | 32.6% | 89.6% |
| LMArena Hard Prompts | 1246 | 1366 |
| LiveBench Data Analysis | 48.3% | 70.6% |
| Epoch Capabilities Index | 123.8 | 140.34 |
| LiveBench | 43.5% | 75.9% |
| ARC-AGI-2 | — | 3% |
| SimpleBench | — | 22.8% |
| ARC-AGI-1 | — | 34.5% |
| CritPt | — | 0.3% |
| Chess Puzzles | — | 17% |
| Mystery Game Puzzles | — | 7% |
| DTBench | — | 68.8% |
| LMCA | — | 19% |
| ForecastBench | — | 59.6 |
Math Too close to call
Amazon Nova Pro: 28.5 (#243), o3-mini: 28.1 (#244)
| Benchmark | Amazon Nova Pro | o3-mini |
|---|---|---|
| LiveBench Math | 38% | 77.3% |
| LMArena Math | 1252 | 1396 |
| FrontierMath (Tiers 1-3) | — | 18.6% |
| FrontierMath Tier 4 | — | 0% |
| OTIS Mock AIME 2024-2025 | — | 76.9% |
| Omni-MATH | 24.2% | — |
| MATH Level 5 | — | 96.5% |
| FrontierMath (Feb 2025 set) | — | 12.4% |
| FrontierMath Tier 4 (v1) | — | 4.2% |
Knowledge o3-mini leads
Amazon Nova Pro: 27.4 (#250), o3-mini: 38.3 (#146)
| Benchmark | Amazon Nova Pro | o3-mini |
|---|---|---|
| Confabulations | 30.1% | 17.9% |
| LMArena Expert | 1211 | 1364 |
| GPQA Diamond | — | 77% |
| Humanity's Last Exam | 4.4% | — |
| SimpleQA Verified | — | 15.3% |
| MMLU-Pro | 67.3% | — |
| Vectara Hallucination Rate | 5.1% | — |
| GPQA (HELM) | 44.6% | — |
| MMLU | 82% | — |
Multimodal Not comparable
Amazon Nova Pro: 25.0 (#126), o3-mini: —
| Benchmark | Amazon Nova Pro | o3-mini |
|---|---|---|
| LMArena Vision | 980 | — |
Multilingual o3-mini leads
Amazon Nova Pro: 39.7 (#223), o3-mini: 45.7 (#164)
| Benchmark | Amazon Nova Pro | o3-mini |
|---|---|---|
| LMArena Non-English | 1234 | 1319 |
| LMArena Chinese | 1244 | 1379 |
| LMArena French | 1271 | 1334 |
| LMArena German | 1243 | 1303 |
| LMArena Japanese | 1200 | 1286 |
| LMArena Korean | 1203 | 1314 |
| LMArena Russian | 1240 | 1304 |
| LMArena Spanish | 1182 | 1321 |
Instruction Following o3-mini leads
Amazon Nova Pro: 64.9 (#226), o3-mini: 75.1 (#72)
| Benchmark | Amazon Nova Pro | o3-mini |
|---|---|---|
| LiveBench Instruction Following | 67.1% | 84.4% |
| LMArena Instruction Following | 1235 | 1337 |
| IFEval | 81.5% | — |
Long Context Amazon Nova Pro leads
Amazon Nova Pro: 38.1 (#205), o3-mini: 33.8 (#256)
| Benchmark | Amazon Nova Pro | o3-mini |
|---|---|---|
| LMArena Longer Query | 1255 | 1343 |
| Fiction.LiveBench | — | 50% |
Writing & Preference o3-mini leads
Amazon Nova Pro: 43.9 (#226), o3-mini: 50.3 (#182)
| Benchmark | Amazon Nova Pro | o3-mini |
|---|---|---|
| LMArena Text | 1259 | 1337 |
| LMArena Creative Writing | 1212 | 1286 |
| Short-Story Creative Writing | 60.5% | 61.7% |
| LMArena Multi-Turn | 1246 | 1320 |
| LiveBench Language | 37% | 50.7% |
| WildBench | 77.7% | — |
Frequently asked questions
Is Amazon Nova Pro better than o3-mini?
o3-mini is the stronger model overall, scoring 36.7 to 31.0 on the Noometry Index.
Which is cheaper, Amazon Nova Pro or o3-mini?
Amazon Nova Pro is cheaper. It lists at $0.80 per million input tokens and $3.20 per million output tokens; o3-mini lists at $1.10 and $4.40.
Is Amazon Nova Pro or o3-mini better for coding?
o3-mini scores higher on coding benchmarks: 40.8 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-mini share?
27 benchmarks have published results for both models. Amazon Nova Pro has 38 scored results on Noometry and o3-mini has 51.