Model comparison
Amazon Nova Pro vs GPT-4o
Amazon Nova Pro is the stronger model overall, scoring 31.0 to 28.6 on the Noometry Index.
Last verified . 37 shared benchmarks.
Summary
- They share 37 benchmarks with published results for both. Amazon Nova Pro scores higher in 3 categories and GPT-4o in 7 categories; 10 gaps are clear of the uncertainty.
- The widest gap is in math, where Amazon Nova Pro leads 28.5 to 10.6.
- The biggest single-benchmark swing is LiveBench Reasoning: 32.6% for Amazon Nova Pro and 55.8% for GPT-4o.
- Amazon Nova Pro is cheaper at $0.80 / $3.20 per million input/output tokens, against $2.50 / $10 for GPT-4o.
- Amazon Nova Pro accepts more context: 300K tokens versus 128K.
Side by side
| Amazon Nova Pro | GPT-4o | |
|---|---|---|
| Provider | Amazon | OpenAI |
| Noometry Index | 31.0 | 28.6 |
| Released | 2024-12-03 | 2024-05-13 |
| Weights | Proprietary | Proprietary |
| Context window | 300K | 128K |
| Max output | 10K | 16K |
| Input $ / M tokens | $0.80 | $2.50 |
| Output $ / M tokens | $3.20 | $10 |
| Results tracked | 38 | 72 |
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-4o: 24.8 (#328)
| Benchmark | Amazon Nova Pro | GPT-4o |
|---|---|---|
| LiveBench Coding | 38.1% | 51.4% |
| LMArena Coding | 1270 | 1297 |
| SWE-bench Verified | — | 31% |
| SWE-bench Verified (bash only) | — | 21.6% |
| Aider Polyglot | — | 45.3% |
| GSO | — | 0% |
| WeirdML | — | 25.1% |
| BigCodeBench Instruct | — | 51.1% |
| BigCodeBench Complete | — | 61.1% |
| CadEval | — | 26% |
| HumanEval+ | — | 87.2% |
| MBPP+ | — | 72.2% |
Agentic & Tool Use GPT-4o leads
Amazon Nova Pro: 16.7 (#147), GPT-4o: 21.0 (#141)
| Benchmark | Amazon Nova Pro | GPT-4o |
|---|---|---|
| TheAgentCompany | 1.7% | 8.6% |
| Berkeley Function Calling Leaderboard | 25% | — |
| GDPval | — | 9.9% |
| Cybench | — | 12.5% |
| BALROG | — | 32.3% |
| LMArena Search | — | 1006 |
| METR Time Horizons | — | 40.8% |
Reasoning Amazon Nova Pro leads
Amazon Nova Pro: 20.0 (#243), GPT-4o: 9.4 (#343)
| Benchmark | Amazon Nova Pro | GPT-4o |
|---|---|---|
| LiveBench Reasoning | 32.6% | 55.8% |
| LMArena Hard Prompts | 1246 | 1281 |
| LiveBench Data Analysis | 48.3% | 60.9% |
| Epoch Capabilities Index | 123.8 | 128.97 |
| LiveBench | 43.5% | 55.3% |
| ARC-AGI-2 | — | 0% |
| SimpleBench | — | 17.8% |
| ARC-AGI-1 | — | 4.5% |
| CritPt | — | 0% |
| Chess Puzzles | — | 13% |
| EnigmaEval | — | 0.8% |
| DTBench | — | 64.5% |
| LMCA | — | 16.6% |
| ForecastBench | — | 57.7 |
Math Amazon Nova Pro leads
Amazon Nova Pro: 28.5 (#243), GPT-4o: 10.6 (#312)
| Benchmark | Amazon Nova Pro | GPT-4o |
|---|---|---|
| Omni-MATH | 24.2% | 29.3% |
| LiveBench Math | 38% | 49.5% |
| LMArena Math | 1252 | 1285 |
| FrontierMath (Tiers 1-3) | — | 0.4% |
| OTIS Mock AIME 2024-2025 | — | 6.4% |
| MATH Level 5 | — | 53.3% |
| FrontierMath (Feb 2025 set) | — | 0.3% |
Knowledge GPT-4o leads
Amazon Nova Pro: 27.4 (#250), GPT-4o: 28.8 (#242)
| Benchmark | Amazon Nova Pro | GPT-4o |
|---|---|---|
| Humanity's Last Exam | 4.4% | 2.7% |
| MMLU-Pro | 67.3% | 71.3% |
| Confabulations | 30.1% | 15.3% |
| Vectara Hallucination Rate | 5.1% | 9.6% |
| GPQA (HELM) | 44.6% | 52% |
| LMArena Expert | 1211 | 1250 |
| MMLU | 82% | 88.1% |
| GPQA Diamond | — | 49.2% |
| SimpleQA Verified | — | 26% |
Multimodal GPT-4o leads
Amazon Nova Pro: 25.0 (#126), GPT-4o: 34.5 (#91)
| Benchmark | Amazon Nova Pro | GPT-4o |
|---|---|---|
| LMArena Vision | 980 | 1137 |
| Video-MME | — | 71.9% |
| GeoBench | — | 71% |
| VPCT | — | 40% |
| ScienceQA | — | 88.5% |
Multilingual GPT-4o leads
Amazon Nova Pro: 39.7 (#223), GPT-4o: 43.2 (#186)
| Benchmark | Amazon Nova Pro | GPT-4o |
|---|---|---|
| LMArena Non-English | 1234 | 1283 |
| LMArena Chinese | 1244 | 1277 |
| LMArena French | 1271 | 1304 |
| LMArena German | 1243 | 1282 |
| LMArena Japanese | 1200 | 1257 |
| LMArena Korean | 1203 | 1234 |
| LMArena Russian | 1240 | 1286 |
| LMArena Spanish | 1182 | 1292 |
Instruction Following GPT-4o leads
Amazon Nova Pro: 64.9 (#226), GPT-4o: 66.6 (#207)
| Benchmark | Amazon Nova Pro | GPT-4o |
|---|---|---|
| LiveBench Instruction Following | 67.1% | 68.6% |
| IFEval | 81.5% | 81.7% |
| LMArena Instruction Following | 1235 | 1278 |
Long Context GPT-4o leads
Amazon Nova Pro: 38.1 (#205), GPT-4o: 39.4 (#179)
| Benchmark | Amazon Nova Pro | GPT-4o |
|---|---|---|
| LMArena Longer Query | 1255 | 1289 |
| Fiction.LiveBench | — | 66.7% |
Writing & Preference GPT-4o leads
Amazon Nova Pro: 43.9 (#226), GPT-4o: 52.6 (#166)
| Benchmark | Amazon Nova Pro | GPT-4o |
|---|---|---|
| LMArena Text | 1259 | 1300 |
| LMArena Creative Writing | 1212 | 1292 |
| Short-Story Creative Writing | 60.5% | 81.8% |
| WildBench | 77.7% | 82.8% |
| LMArena Multi-Turn | 1246 | 1302 |
| LiveBench Language | 37% | 47.6% |
Frequently asked questions
Is Amazon Nova Pro better than GPT-4o?
Amazon Nova Pro is the stronger model overall, scoring 31.0 to 28.6 on the Noometry Index.
Which is cheaper, Amazon Nova Pro or GPT-4o?
Amazon Nova Pro is cheaper. It lists at $0.80 per million input tokens and $3.20 per million output tokens; GPT-4o lists at $2.50 and $10.
Is Amazon Nova Pro or GPT-4o better for coding?
Amazon Nova Pro scores higher on coding benchmarks: 35.1 versus 24.8 in the Noometry coding category.
Which has the bigger context window?
Amazon Nova Pro does, with 300K tokens against 128K.
How many benchmarks do Amazon Nova Pro and GPT-4o share?
37 benchmarks have published results for both models. Amazon Nova Pro has 38 scored results on Noometry and GPT-4o has 72.