Model comparison
Amazon Nova Pro vs GPT-5.3 Codex
GPT-5.3 Codex is the stronger model overall, scoring 45.8 to 31.0 on the Noometry Index. Amazon Nova Pro costs 3.4× less per token, which makes it the better buy when GPT-5.3 Codex's lead doesn't matter for your workload.
Last verified . 1 shared benchmarks.
Summary
- They share 1 benchmark with published results for both. Amazon Nova Pro scores higher in 0 categories and GPT-5.3 Codex in 2 categories; 2 gaps are clear of the uncertainty.
- The widest gap is in agentic & tool use, where GPT-5.3 Codex leads 48.0 to 16.7.
- Amazon Nova Pro is cheaper at $0.80 / $3.20 per million input/output tokens, against $1.75 / $14 for GPT-5.3 Codex.
- GPT-5.3 Codex accepts more context: 400K tokens versus 300K.
Side by side
| Amazon Nova Pro | GPT-5.3 Codex | |
|---|---|---|
| Provider | Amazon | OpenAI |
| Noometry Index | 31.0 | 45.8 |
| Released | 2024-12-03 | 2026-02-05 |
| Weights | Proprietary | Proprietary |
| Context window | 300K | 400K |
| Max output | 10K | 128K |
| Input $ / M tokens | $0.80 | $1.75 |
| Output $ / M tokens | $3.20 | $14 |
| Results tracked | 38 | 8 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding GPT-5.3 Codex leads
Amazon Nova Pro: 35.1 (#229), GPT-5.3 Codex: 48.6 (#56)
| Benchmark | Amazon Nova Pro | GPT-5.3 Codex |
|---|---|---|
| SWE-bench Verified | — | 74.8% |
| LMArena WebDev | — | 1409 |
| WeirdML | — | 79.3% |
| LiveBench Coding | 38.1% | — |
| LMArena Coding | 1270 | — |
| ALE-Bench | — | 1,655 |
Agentic & Tool Use GPT-5.3 Codex leads
Amazon Nova Pro: 16.7 (#147), GPT-5.3 Codex: 48.0 (#9)
| Benchmark | Amazon Nova Pro | GPT-5.3 Codex |
|---|---|---|
| Terminal-Bench | — | 78.4% |
| Berkeley Function Calling Leaderboard | 25% | — |
| TheAgentCompany | 1.7% | — |
| METR Time Horizons | — | 74.5% |
| Vending-Bench 2 | — | 5,940 |
Reasoning Not comparable
Amazon Nova Pro: 20.0 (#243), GPT-5.3 Codex: —
| Benchmark | Amazon Nova Pro | GPT-5.3 Codex |
|---|---|---|
| Epoch Capabilities Index | 123.8 | 156.77 |
| LiveBench Reasoning | 32.6% | — |
| LMArena Hard Prompts | 1246 | — |
| LiveBench Data Analysis | 48.3% | — |
| LiveBench | 43.5% | — |
Math Not comparable
Amazon Nova Pro: 28.5 (#243), GPT-5.3 Codex: —
| Benchmark | Amazon Nova Pro | GPT-5.3 Codex |
|---|---|---|
| Omni-MATH | 24.2% | — |
| LiveBench Math | 38% | — |
| LMArena Math | 1252 | — |
Knowledge Not comparable
Amazon Nova Pro: 27.4 (#250), GPT-5.3 Codex: —
| Benchmark | Amazon Nova Pro | GPT-5.3 Codex |
|---|---|---|
| Humanity's Last Exam | 4.4% | — |
| MMLU-Pro | 67.3% | — |
| Confabulations | 30.1% | — |
| Vectara Hallucination Rate | 5.1% | — |
| GPQA (HELM) | 44.6% | — |
| LMArena Expert | 1211 | — |
| MMLU | 82% | — |
Multimodal Not comparable
Amazon Nova Pro: 25.0 (#126), GPT-5.3 Codex: —
| Benchmark | Amazon Nova Pro | GPT-5.3 Codex |
|---|---|---|
| LMArena Vision | 980 | — |
Multilingual Not comparable
Amazon Nova Pro: 39.7 (#223), GPT-5.3 Codex: —
| Benchmark | Amazon Nova Pro | GPT-5.3 Codex |
|---|---|---|
| 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), GPT-5.3 Codex: —
| Benchmark | Amazon Nova Pro | GPT-5.3 Codex |
|---|---|---|
| LiveBench Instruction Following | 67.1% | — |
| IFEval | 81.5% | — |
| LMArena Instruction Following | 1235 | — |
Long Context Not comparable
Amazon Nova Pro: 38.1 (#205), GPT-5.3 Codex: —
| Benchmark | Amazon Nova Pro | GPT-5.3 Codex |
|---|---|---|
| LMArena Longer Query | 1255 | — |
Writing & Preference Not comparable
Amazon Nova Pro: 43.9 (#226), GPT-5.3 Codex: —
| Benchmark | Amazon Nova Pro | GPT-5.3 Codex |
|---|---|---|
| LMArena Text | 1259 | — |
| LMArena Creative Writing | 1212 | — |
| Short-Story Creative Writing | 60.5% | — |
| WildBench | 77.7% | — |
| LMArena Multi-Turn | 1246 | — |
| LiveBench Language | 37% | — |
Frequently asked questions
Is Amazon Nova Pro better than GPT-5.3 Codex?
GPT-5.3 Codex is the stronger model overall, scoring 45.8 to 31.0 on the Noometry Index. Amazon Nova Pro costs 3.4× less per token, which makes it the better buy when GPT-5.3 Codex's lead doesn't matter for your workload.
Which is cheaper, Amazon Nova Pro or GPT-5.3 Codex?
Amazon Nova Pro is cheaper. It lists at $0.80 per million input tokens and $3.20 per million output tokens; GPT-5.3 Codex lists at $1.75 and $14.
Is Amazon Nova Pro or GPT-5.3 Codex better for coding?
GPT-5.3 Codex scores higher on coding benchmarks: 48.6 versus 35.1 in the Noometry coding category.
Which has the bigger context window?
GPT-5.3 Codex does, with 400K tokens against 300K.
How many benchmarks do Amazon Nova Pro and GPT-5.3 Codex share?
1 benchmark has published results for both models. Amazon Nova Pro has 38 scored results on Noometry and GPT-5.3 Codex has 8.