Model comparison
Amazon Nova Pro vs o4-mini
o4-mini is the stronger model overall, scoring 41.6 to 30.5 on the Noometry Index.
Last verified . 29 shared benchmarks.
Summary
- They share 29 benchmarks with published results for both. Amazon Nova Pro scores higher in 0 categories and o4-mini in 10 categories; 10 gaps are clear of the uncertainty.
- The widest gap is in knowledge, where o4-mini leads 43.5 to 27.1.
- The biggest single-benchmark swing is Omni-MATH: 24.2% for Amazon Nova Pro and 72% for o4-mini.
- Amazon Nova Pro is cheaper at $0.80 / $3.20 per million input/output tokens, against $1.10 / $4.40 for o4-mini.
- Amazon Nova Pro accepts more context: 300K tokens versus 200K.
Side by side
| Amazon Nova Pro | o4-mini | |
|---|---|---|
| Provider | Amazon | OpenAI |
| Noometry Index | 30.5 | 41.6 |
| Released | 2024-12-03 | 2025-04-16 |
| 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 | 60 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding o4-mini leads
Amazon Nova Pro: 34.6 (#224), o4-mini: 41.6 (#110)
| Benchmark | Amazon Nova Pro | o4-mini |
|---|---|---|
| LMArena Coding | 1270 | 1369 |
| SWE-bench Verified (bash only) | — | 45% |
| Aider Polyglot | — | 72% |
| GSO | — | 3.6% |
| WeirdML | — | 52.6% |
| LiveBench Coding | 38.1% | — |
| CadEval | — | 62% |
| ALE-Bench | — | 826.17 |
| AlgoTune | — | 1.72 |
Agentic & Tool Use o4-mini leads
Amazon Nova Pro: 16.6 (#139), o4-mini: 32.3 (#57)
| Benchmark | Amazon Nova Pro | o4-mini |
|---|---|---|
| Berkeley Function Calling Leaderboard | 25% | 53.2% |
| GDPval | — | 25.3% |
| TheAgentCompany | 1.7% | — |
| METR Time Horizons | — | 63.9% |
Reasoning o4-mini leads
Amazon Nova Pro: 19.2 (#240), o4-mini: 24.6 (#143)
| Benchmark | Amazon Nova Pro | o4-mini |
|---|---|---|
| LMArena Hard Prompts | 1246 | 1351 |
| Epoch Capabilities Index | 123.75 | 145.63 |
| ARC-AGI-2 | — | 6.1% |
| SimpleBench | — | 38.7% |
| Kagi LLM Benchmark | — | 67.6% |
| ARC-AGI-1 | — | 58.7% |
| CritPt | — | 0.6% |
| Chess Puzzles | — | 26% |
| EnigmaEval | — | 9.2% |
| LiveBench Reasoning | 32.6% | — |
| Mystery Game Puzzles | — | 5% |
| DTBench | — | 77.6% |
| LiveBench Data Analysis | 48.3% | — |
| LMCA | — | 26.5% |
| ForecastBench | — | 61.8 |
| LiveBench | 43.5% | — |
Math o4-mini leads
Amazon Nova Pro: 26.4 (#240), o4-mini: 40.2 (#79)
| Benchmark | Amazon Nova Pro | o4-mini |
|---|---|---|
| Omni-MATH | 24.2% | 72% |
| LMArena Math | 1252 | 1390 |
| FrontierMath (Tiers 1-3) | — | 36.1% |
| FrontierMath Tier 4 | — | 4.9% |
| OTIS Mock AIME 2024-2025 | — | 81.7% |
| LiveBench Math | 38% | — |
| MATH Level 5 | — | 97.8% |
| FrontierMath (Feb 2025 set) | — | 24.8% |
| FrontierMath Tier 4 (v1) | — | 6.3% |
Knowledge o4-mini leads
Amazon Nova Pro: 27.1 (#246), o4-mini: 43.5 (#83)
| Benchmark | Amazon Nova Pro | o4-mini |
|---|---|---|
| Humanity's Last Exam | 4.4% | 18.1% |
| MMLU-Pro | 67.3% | 82% |
| Confabulations | 30.1% | 15.8% |
| Vectara Hallucination Rate | 5.1% | 18.6% |
| GPQA (HELM) | 44.6% | 73.5% |
| LMArena Expert | 1211 | 1344 |
| GPQA Diamond | — | 79.6% |
| SimpleQA Verified | — | 19.6% |
| MMLU | 82% | — |
Multimodal o4-mini leads
Amazon Nova Pro: 24.5 (#121), o4-mini: 39.5 (#46)
| Benchmark | Amazon Nova Pro | o4-mini |
|---|---|---|
| LMArena Vision | 980 | 1194 |
| GeoBench | — | 64% |
| VPCT | — | 57.5% |
Multilingual o4-mini leads
Amazon Nova Pro: 39.9 (#218), o4-mini: 47.2 (#149)
| Benchmark | Amazon Nova Pro | o4-mini |
|---|---|---|
| LMArena Non-English | 1234 | 1336 |
| LMArena Chinese | 1244 | 1355 |
| LMArena French | 1270 | 1362 |
| LMArena German | 1243 | 1336 |
| LMArena Japanese | 1200 | 1308 |
| LMArena Korean | 1203 | 1313 |
| LMArena Russian | 1240 | 1334 |
| LMArena Spanish | 1182 | 1346 |
Instruction Following o4-mini leads
Amazon Nova Pro: 65.1 (#221), o4-mini: 75.4 (#63)
| Benchmark | Amazon Nova Pro | o4-mini |
|---|---|---|
| IFEval | 81.5% | 92.8% |
| LMArena Instruction Following | 1235 | 1321 |
| LiveBench Instruction Following | 67.1% | — |
Long Context o4-mini leads
Amazon Nova Pro: 38.1 (#199), o4-mini: 45.5 (#31)
| Benchmark | Amazon Nova Pro | o4-mini |
|---|---|---|
| LMArena Longer Query | 1255 | 1315 |
| Fiction.LiveBench | — | 77.8% |
Writing & Preference o4-mini leads
Amazon Nova Pro: 44.1 (#221), o4-mini: 54.2 (#148)
| Benchmark | Amazon Nova Pro | o4-mini |
|---|---|---|
| LMArena Text | 1259 | 1353 |
| LMArena Creative Writing | 1212 | 1294 |
| Short-Story Creative Writing | 60.5% | 75% |
| WildBench | 77.7% | 85.4% |
| LMArena Multi-Turn | 1245 | 1350 |
| LiveBench Language | 37% | — |
Frequently asked questions
Is Amazon Nova Pro better than o4-mini?
o4-mini is the stronger model overall, scoring 41.6 to 30.5 on the Noometry Index.
Which is cheaper, Amazon Nova Pro or o4-mini?
Amazon Nova Pro is cheaper. It lists at $0.80 per million input tokens and $3.20 per million output tokens; o4-mini lists at $1.10 and $4.40.
Is Amazon Nova Pro or o4-mini better for coding?
o4-mini scores higher on coding benchmarks: 41.6 versus 34.6 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 o4-mini share?
29 benchmarks have published results for both models. Amazon Nova Pro has 38 scored results on Noometry and o4-mini has 60.